Whiskey Web and Whatnot: Web Development, Neat

A whiskey fueled fireside chat with your favorite web developers.

217: Open Source, Agents, and the Next AI Wave w/ Angie Jones

Recorded live at All Things Open, Robbie Wagner and guest co-host Jason Lengstorf talk with Angie Jones about AI, coding models, and the evolving landscape of open source. They unpack the importance of community-driven tooling, skill gaps in using AI, the futu...

Show Notes

Recorded live at All Things Open, Robbie Wagner and guest co-host Jason Lengstorf talk with Angie Jones about AI, coding models, and the evolving landscape of open source. They unpack the importance of community-driven tooling, skill gaps in using AI, the future of agentic systems, and why open communities matter in shaping technology.

In this episode:

  • (00:00) - Intro
  • (01:18) - Wine rating & review
  • (03:30) - Hot Take: Claude vs ChatGPT
  • (04:20) - Hot Take: Is HTML a programming language?
  • (04:56) - Hot Take: Is CSS a programming language?
  • (05:31) - Hot Take: Is AI to blame when people do dumb shit with it?
  • (09:50) - How open source shaped Angie’s career
  • (14:54) - The problem with AI training on open source data
  • (23:02) - What is MCP and why does it matter?
  • (25:10) - Using MCP when you don’t follow every part of the spec
  • (26:25) - Are we building new walled gardens inside MCP?
  • (31:16) - Building DevRel in a rapidly-changing AI landscape
  • (36:06) - Conference season stress & preparing new talks
  • (39:41) - Where to find Angie online

Links

Connect with Jason

Connect with Angie

Connect with the hosts

Subscribe and stay in touch

Whiskey Web and Whatnot Merch
Enjoying the podcast and want us to make more? Help support us by picking up some of our fresh merch at https://whiskey.fund.

Episode Transcript

[00:00:00] Intro: Welcome to Syntax. Welcome to a brand new episode of the Front End Happy Hour podcast. Welcome to this week’s JS Party. Live from Ship Shape Studios, this is Whiskey Web and Whatnot. With your hosts, Robbie the Wagner, and me, Charles William Carpenter III. That’s right Charles. We drink whiskey and talk about web development.

[00:00:27] Intro: I mean, it’s all in the name. It’s not that deep. This is Whiskey Web and Whatnot. Do not adjust your set.

[00:00:36] Robbie Wagner: Hey,

[00:00:36] Robbie Wagner: what’s up everybody? Welcome to Prosecco Programming and Patter.

[00:00:44] Robbie Wagner: You might have heard of Whiskey Web and whatnot, but we’ve changed today. , We’ve got some, some lovely Prosecco. We have guest host Jason Langsdorf and our guest Angie Jones. How’s it going? Oh, okay. So you’ve been on the show before, but for anyone who has not heard that one and has not heard of you, could you please give a few [00:01:00] sentences about who you are and what you do?

[00:01:01] Robbie Wagner: Yeah,

[00:01:01] Angie Jones: Yeah, so I’m Angie Jones. I am VP of engineering over AI Tools and Enablement at Block.

[00:01:09] Angie Jones: worked in various roles throughout tech over the decades, but yeah, I love, teaching and speaking and talking about tech.

[00:01:18] Robbie Wagner: Nice, nice. All right, so the thing we’re all here for, we’ve got this Prosecco. It is a hundred percent Prosecco.

[00:01:25] Robbie Wagner: And it is from Costco, so you know, it’s good. Yeah, let’s get into it.

[00:01:29] Angie Jones: Bubbly,

[00:01:31] Robbie Wagner: I guess I should be pouring this here. I don’t know if you could even hear it if I did. Oh, you kind of

[00:01:34] Robbie Wagner: can

[00:01:34] Angie Jones: Oh,

[00:01:35] Jason: Yeah, there it is.

[00:01:35] Jason: Cheers.

[00:01:37] Jason: You

[00:01:37] Jason: got

[00:01:37] Jason: a toast for us?

[00:01:38] Robbie Wagner: I do.

[00:01:39] Robbie Wagner: Okay.

[00:01:40] Robbie Wagner: To MCP, the protocol that finally made our ais talk to each other instead of just hallucinating alone. Cheers to context, connection, and controlled chaos.

[00:01:49] Angie Jones: love that.

[00:01:51] Angie Jones: Oh, Alright,

[00:01:52] Robbie Wagner: so this one tastes remarkably more like wine than the last one.

[00:01:57] Jason: Yeah,

[00:01:58] Jason: last time we had bubbly juice.[00:02:00]

[00:02:00] Jason: This time it tastes like wine and it tastes like Costco wine.

[00:02:06] Robbie Wagner: Is that high praise or

[00:02:09] Angie Jones: ah, yeah.

[00:02:09] Angie Jones: May

[00:02:09] Jason: are we starting

[00:02:10] Robbie Wagner: a headache? Yeah. Okay. yeah. Not a lot of flavor notes or anything to write home about. , It’s a Prosecco.

[00:02:15] Robbie Wagner: Alright. Our rating system is zero to eight tentacles, zero being the worst, eight being the best.

[00:02:20] Robbie Wagner: Four and a half-ish being middle of the road. What do you think, Jason?

[00:02:23] Jason: know.

[00:02:23] Jason: I, I think I gotta be, , maybe more gentle because Prosecco is not typically my favorite.

[00:02:28] Jason: But this one

[00:02:29] Jason: in particular, it’s a little metallic.

[00:02:31] Robbie Wagner: So the thing about Italian wine though, is that it all has to be like approved by some guy who says, this tastes like Prosecco, check mark. yes, it’s DOC labeled.

[00:02:42] Robbie Wagner: I ripped it all off. But,

[00:02:43] Robbie Wagner: yeah.

[00:02:44] Jason: Well then

[00:02:44] Jason: my apologies to

[00:02:45] Jason: Italy cause I’m rating this at two.

[00:02:47] Angie Jones: oh my God.

[00:02:50] Robbie Wagner: oh, what do you think,

[00:02:51] Robbie Wagner: Angie?

[00:02:52] Angie Jones: You know, I like,

[00:02:53] Angie Jones: , My Prosecco and wines on the sweeter side, and this does give me those sweeter notes, so I

[00:02:59] Angie Jones: really like [00:03:00] that.

[00:03:00] Angie Jones: I usually will drink something like this as a mimosa with some orange juice. So I’m thinking about it in that regard. And it would, I think it would, I think it would be really good. So I’m gonna go with like,

[00:03:11] Angie Jones: maybe like a four

[00:03:12] Angie Jones: and a

[00:03:12] Angie Jones: half.

[00:03:13] Robbie Wagner: Okay. Alright.

[00:03:14] Robbie Wagner: Yeah. I’m gonna say, I’m gonna say five.

[00:03:17] Robbie Wagner: It’s, it’s

[00:03:17] Robbie Wagner: a Prosecco.

[00:03:18] Angie Jones: It’s Prosecco.

[00:03:19] Robbie Wagner: Prosecco.

[00:03:19] Robbie Wagner: Simple Pro.

[00:03:21] Robbie Wagner: We

[00:03:22] Robbie Wagner: could mix the other one in, which is kind of like

[00:03:24] Robbie Wagner: a

[00:03:24] Jason: That’s it there. Yeah, then it’s, then it’s kind of a

[00:03:27] Angie Jones: Then I get a mimosa.

[00:03:30] Robbie Wagner: Alright.

[00:03:31] Robbie Wagner: got

[00:03:31] Robbie Wagner: a few lukewarm takes here. Claude or

[00:03:34] Robbie Wagner: GPT

[00:03:35] Angie Jones: as

[00:03:35] Angie Jones: far

[00:03:35] Angie Jones: as

[00:03:35] Angie Jones: models.

[00:03:36] Robbie Wagner: Yeah, no context at all as to when you would be picking. Which, just which one? Oh, wow.

[00:03:42] Angie Jones: I can’t

[00:03:42] Angie Jones: go

[00:03:43] Angie Jones: the, it

[00:03:43] Angie Jones: depends

[00:03:43] Angie Jones: route.

[00:03:44] Robbie Wagner: No, You can, I’m,

[00:03:44] Robbie Wagner: I’m just kidding. I’m just

[00:03:46] Angie Jones: okay. Okay. So it

[00:03:46] Angie Jones: definitely depends on what I’m trying to do. So if I’m trying to code, do anything like really technical, I’m gonna grab Claude all day. , If I’m having a discussion, I’m trying to brainstorm something like that, I’m gonna go with GPT.

[00:03:59] Angie Jones: You know, they say the [00:04:00] GPT five is pretty good at coding. , I don’t know. I haven’t tried it. I don’t like it so much for even discussions. So I definitely don’t wanna try it

[00:04:08] Angie Jones: for coding.

[00:04:09] Angie Jones: , But yeah,

[00:04:09] Angie Jones: , That’s

[00:04:10] Angie Jones: my

[00:04:10] Angie Jones: take. Okay.

[00:04:10] Robbie Wagner: Okay. Yeah, I’ve not had much success with GPT and coding. It gives me a

[00:04:14] Robbie Wagner: lot of trash. Yeah.

[00:04:15] Robbie Wagner: Yeah.

[00:04:16] Angie Jones: yeah.

[00:04:16] Robbie Wagner: alright, So,

[00:04:17] Robbie Wagner: I won’t

[00:04:17] Angie Jones: waste my time.

[00:04:18] Robbie Wagner: Yeah.

[00:04:19] Angie Jones: Yeah.

[00:04:20] Robbie Wagner: Is H-T-M-L-A programming language?

[00:04:21] Angie Jones: No.

[00:04:28] Angie Jones: It’s a

[00:04:28] Angie Jones: language,

[00:04:29] Angie Jones: it’s a

[00:04:29] Angie Jones: markdown Language.

[00:04:31] Angie Jones: There’s specific criteria that a programming language has. Things like conditional statements or iterations and things like that,

[00:04:41] Angie Jones: that

[00:04:41] Angie Jones: does

[00:04:41] Angie Jones: not exist.

[00:04:42] Angie Jones: And HTML. There’s some structure. Yes, there’s some rules, yes,

[00:04:47] Angie Jones: but not quite

[00:04:48] Angie Jones: programming.

[00:04:49] Angie Jones: That

[00:04:50] Angie Jones: does

[00:04:50] Angie Jones: not

[00:04:50] Angie Jones: mean

[00:04:51] Angie Jones: I’m a

[00:04:52] Angie Jones: gatekeeper.

[00:04:53] Angie Jones: Let the record show.

[00:04:56] Robbie Wagner: Okay,

[00:04:57] Robbie Wagner: so follow up is CSSA programming [00:05:00] language, You know

[00:05:00] Angie Jones: that one I would’ve said no a while back, but they have gotten. Really deep. And I’m not a CSS wiz

[00:05:07] Angie Jones: at

[00:05:07] Angie Jones: all, so I

[00:05:08] Angie Jones: don’t

[00:05:08] Angie Jones: even

[00:05:08] Angie Jones: cooking

[00:05:08] Angie Jones: these

[00:05:09] Angie Jones: days. They

[00:05:09] Angie Jones: are cooking. like

[00:05:10] Angie Jones: there’s a lot that you can do, or other people

[00:05:12] Angie Jones: can

[00:05:12] Angie Jones: do.

[00:05:13] Angie Jones: I

[00:05:13] Angie Jones: cannot do.

[00:05:15] Angie Jones: But there’s

[00:05:15] Angie Jones: a lot

[00:05:15] Angie Jones: you

[00:05:15] Angie Jones: can do

[00:05:16] Angie Jones: with CSS, you know, nowadays as far as

[00:05:19] Angie Jones: like logic

[00:05:20] Angie Jones: and

[00:05:20] Angie Jones: hierarchy

[00:05:21] Angie Jones: and stuff

[00:05:22] Angie Jones: like

[00:05:22] Angie Jones: that. So,

[00:05:22] Angie Jones: I don’t know.

[00:05:23] Robbie Wagner: now?

[00:05:24] Jason: they got

[00:05:24] Jason: functions. they

[00:05:25] Jason: got

[00:05:25] Jason: if else

[00:05:25] Jason: now.

[00:05:25] Jason: Okay.

[00:05:26] Jason: Like it’s, we’re, I think we’re

[00:05:27] Jason: touring

[00:05:28] Angie Jones: at this.

[00:05:28] Robbie Wagner: I think so. Yes. All

[00:05:30] Angie Jones: Alright.

[00:05:30] Robbie Wagner: You heard it

[00:05:31] Robbie Wagner: here first.

[00:05:31] Robbie Wagner: Is AI to blame when people do dumb shit with it?

[00:05:41] Robbie Wagner: Like,

[00:05:41] Robbie Wagner: I don’t know. I guess, , like should there be guardrails or, I don’t know. I don’t know what, what the context is,

[00:05:46] Robbie Wagner: but you know.

[00:05:46] Angie Jones: you know?

[00:05:47] Angie Jones: I

[00:05:47] Angie Jones: found myself this weekend,

[00:05:49] Angie Jones: uh,

[00:05:51] Angie Jones: telling

[00:05:51] Angie Jones: some

[00:05:51] Angie Jones: reply

[00:05:52] Angie Jones: guy

[00:05:53] Angie Jones: skills

[00:05:53] Angie Jones: issue.

[00:05:57] Angie Jones: You

[00:05:58] Angie Jones: know,

[00:05:58] Angie Jones: like

[00:05:58] Angie Jones: I, I

[00:05:59] Angie Jones: do

[00:05:59] Angie Jones: [00:06:00] think that

[00:06:01] Angie Jones: this is a

[00:06:02] Angie Jones: non-deterministic tool.

[00:06:04] Angie Jones: AI is

[00:06:04] Angie Jones: right?

[00:06:05] Angie Jones: Yeah. This is non-deterministic.

[00:06:07] Angie Jones: So when you say it

[00:06:09] Angie Jones: did

[00:06:09] Angie Jones: something

[00:06:09] Angie Jones: wrong, like

[00:06:11] Angie Jones: What does that mean? Like there

[00:06:13] Angie Jones: there is no

[00:06:13] Angie Jones: right.

[00:06:14] Angie Jones: You

[00:06:14] Angie Jones: know

[00:06:14] Angie Jones: what I mean? ,

[00:06:15] Angie Jones: And

[00:06:16] Angie Jones: so the

[00:06:16] Angie Jones: way that

[00:06:17] Angie Jones: you

[00:06:17] Angie Jones: get

[00:06:17] Angie Jones: it to perform

[00:06:19] Angie Jones: what you want it to do is

[00:06:20] Angie Jones: very

[00:06:21] Angie Jones: much

[00:06:21] Angie Jones: so

[00:06:21] Angie Jones: a

[00:06:21] Angie Jones: human

[00:06:22] Angie Jones: skill.

[00:06:23] Angie Jones: Mm-hmm.

[00:06:23] Angie Jones: Right?

[00:06:24] Angie Jones: Yep.

[00:06:24] Angie Jones: ,

[00:06:24] Angie Jones: And so

[00:06:25] Angie Jones: I would

[00:06:25] Angie Jones: say

[00:06:26] Angie Jones: it’s

[00:06:26] Angie Jones: not the

[00:06:27] Angie Jones: AI’s fault,

[00:06:28] Angie Jones: , But I don’t wanna blame humans either. Like this is new to all of us. We’re all trying to figure out how do

[00:06:33] Angie Jones: we work with non-deterministic.

[00:06:35] Angie Jones: Very

[00:06:36] Angie Jones: powerful.

[00:06:37] Angie Jones: Systems now,

[00:06:38] Angie Jones: right? Yeah. And so

[00:06:39] Angie Jones: it is a skill issue. I, I wasn’t trying to be

[00:06:42] Angie Jones: mean, but

[00:06:42] Angie Jones: it

[00:06:42] Angie Jones: really

[00:06:43] Angie Jones: is a

[00:06:43] Angie Jones: skill issue.

[00:06:44] Jason: Well, I, I think too, it is really important to keep in mind that like AI can’t be blamed because AI is a tool.

[00:06:51] Jason: Like if you, if you hit yourself

[00:06:53] Jason: in the

[00:06:53] Jason: head

[00:06:53] Jason: with a

[00:06:53] Jason: hammer,

[00:06:54] Jason: it’s

[00:06:55] Jason: not the

[00:06:55] Jason: hammer’s

[00:06:55] Jason: fault,

[00:06:56] Robbie Wagner: but should there have been a warning on the hammer that said, if you hit

[00:06:58] Jason: Well, and

[00:06:59] Jason: and this is [00:07:00] sort of the question is like, you know, is it, necessary to put a, the contents hot label on a cup of coffee or things like that? And, you know, it, it sounds silly like that McDonald’s, , lawsuit is always pointed to as like the frivolous lawsuit.

[00:07:13] Jason: But if you actually

[00:07:13] Jason: look into it,

[00:07:14] Jason: that coffee was so dang hot that it gave that woman, like, it fused her skin together. It was so hot, right? So it wasn’t

[00:07:21] Jason: really

[00:07:21] Jason: a frivolous lawsuit.

[00:07:22] Jason: But it, it does kind of point to like, okay, where does responsibility end? Like if, if I have a

[00:07:27] Jason: knife in

[00:07:27] Jason: my house, do I need to have a posted placard on my front door that says caution sharp things contained within this house.

[00:07:35] Jason: and I think , the same is kind of true with digital tools like LLMs are

[00:07:40] Jason: not

[00:07:40] Jason: intelligent,

[00:07:41] Jason: We don’t have. They, well, they’re anthropomorphized, which is a really dangerous thing because

[00:07:46] Jason: we think of them

[00:07:47] Jason: as people,

[00:07:48] Jason: despite them just

[00:07:49] Jason: being complicated

[00:07:50] Jason: calculators. And so if you go to your complicated calculator that’s been explicitly prompted like in the GPT-4 era

[00:07:57] Jason: to be a sycophant, and you say, I [00:08:00] don’t like what you said to me, tell me something else.

[00:08:01] Jason: And it says, you’re absolutely right. Here’s the thing you wanted to hear.

[00:08:04] Jason: And

[00:08:04] Jason: then people are like, oh, it’s

[00:08:05] Jason: the AI’s fault. It’s

[00:08:06] Jason: like, no, it’s not

[00:08:07] Jason: like if, like this is the, this is the the billionaire problem. If you only surround yourself with people who tell you what you want to hear, and they give you bad advice because you push everybody who gives you good advice away,

[00:08:18] Jason: that is not their fault.

[00:08:20] Jason: That’s your fault. Right. And if you won’t listen to a tool and it tells you the thing you already wanted it

[00:08:25] Jason: to say,

[00:08:26] Jason: that’s still

[00:08:27] Jason: on you.

[00:08:28] Robbie Wagner: yeah,

[00:08:28] Angie Jones: That’s spicy.

[00:08:29] Angie Jones: Jason.

[00:08:30] Jason: I don’t even

[00:08:30] Jason: think that’s spicy. That’s like, like if I, if I hold my calculator

[00:08:34] Jason: upside

[00:08:34] Jason: down and

[00:08:35] Jason: write boobs,

[00:08:35] Jason: my

[00:08:36] Jason: calculator is

[00:08:36] Jason: not being inappropriate. Right.

[00:08:42] Robbie Wagner: Yeah,

[00:08:42] Robbie Wagner: I don’t know. It’s a hard problem because I feel like there’s not enough education around, like for the casual, non-technical person, they just pick up some AI and they’re like, oh, this is like super smart. It knows what it’s talking about. You tell it to make you a plan and that plan sounds

[00:08:56] Robbie Wagner: smart.

[00:08:56] Jason: this is the thing,

[00:08:57] Jason: that I think needs a warning is I think whenever you start a [00:09:00] ChatGPT 4 session, ? It should come with an acknowledgement that says like before you start this, you know

[00:09:06] Jason: this

[00:09:06] Jason: isn’t

[00:09:07] Jason: alive, This

[00:09:08] Jason: is a calculator. You

[00:09:09] Jason: are using

[00:09:09] Jason: a

[00:09:10] Jason: tool.

[00:09:11] Jason: This is not a person, it’s not a friend, it’s not

[00:09:13] Jason: a conscious entity.

[00:09:14] Jason: It’s a tool.

[00:09:15] Jason: And that to me seems like a reasonable thing because it is masquerading as a, conscious person,

[00:09:22] Robbie Wagner: Yeah.

[00:09:22] Angie Jones: But it’ll tell you,

[00:09:23] Angie Jones: it’ll say I’m

[00:09:24] Angie Jones: not

[00:09:24] Angie Jones: intelligent,

[00:09:25] Angie Jones: I’m

[00:09:25] Angie Jones: not human.

[00:09:27] Jason: so well sometimes

[00:09:28] Jason: until you ask it, like, do you have feelings? And it’s like, I have feelings. And it, like, it’ll do, it’ll do stuff that’s really interesting

[00:09:34] Jason: where

[00:09:35] Jason: it

[00:09:35] Jason: it, you know,

[00:09:35] Jason: it puts on,

[00:09:36] Jason: its, its

[00:09:36] Jason: anthropomorphized

[00:09:38] Jason: face.

[00:09:38] Angie Jones: My

[00:09:38] Angie Jones: ChatGPT Don’t

[00:09:39] Angie Jones: play that

[00:09:41] Angie Jones: Like it knows. Stay

[00:09:42] Angie Jones: your place.

[00:09:43] Angie Jones: You are not

[00:09:44] Angie Jones: me.

[00:09:44] Angie Jones: You are not one

[00:09:45] Angie Jones: of

[00:09:45] Angie Jones: us.

[00:09:46] Robbie Wagner: Yeah.

[00:09:50] Robbie Wagner: All right, so we’re at all Things Open. So I want to ask open source things. , How has Open source influenced your

[00:09:56] Robbie Wagner: life?

[00:09:57] Angie Jones: Oh

[00:09:58] Angie Jones: my

[00:09:58] Angie Jones: God.

[00:09:59] Angie Jones: I

[00:09:59] Angie Jones: think

[00:09:59] Angie Jones: it

[00:09:59] Angie Jones: [00:10:00] gave

[00:10:00] Angie Jones: me

[00:10:00] Angie Jones: a great

[00:10:01] Angie Jones: , Pathway

[00:10:02] Angie Jones: to,

[00:10:03] Angie Jones: I

[00:10:03] Angie Jones: guess like

[00:10:03] Angie Jones: work

[00:10:04] Angie Jones: out loud,

[00:10:05] Angie Jones: When you’re working at a company on enterprise software, like you can’t

[00:10:08] Angie Jones: really

[00:10:09] Angie Jones: get into the nitty gritty of like.

[00:10:11] Angie Jones: What

[00:10:11] Angie Jones: you’re building

[00:10:12] Angie Jones: or

[00:10:12] Angie Jones: the techniques and things that you all using just a little

[00:10:15] Angie Jones: bit, right? You can share

[00:10:16] Angie Jones: a

[00:10:16] Angie Jones: little bit, but not the whole story and open source.

[00:10:19] Angie Jones: ,

[00:10:19] Angie Jones: Once I started working on

[00:10:21] Angie Jones: open source

[00:10:22] Angie Jones: projects that

[00:10:23] Angie Jones: gave

[00:10:24] Angie Jones: me something that I can publicly talk about, , and, you know, talk with

[00:10:28] Angie Jones: others about,

[00:10:29] Angie Jones: you

[00:10:29] Angie Jones: know,

[00:10:29] Angie Jones: now

[00:10:30] Angie Jones: we have like

[00:10:31] Angie Jones: this common thing that we use or we invest

[00:10:34] Angie Jones: in

[00:10:34] Angie Jones: or we

[00:10:35] Angie Jones: love or we hate,

[00:10:36] Angie Jones: or whatever,

[00:10:36] Angie Jones: you know.

[00:10:37] Angie Jones: But that gave

[00:10:38] Angie Jones: us something,

[00:10:39] Angie Jones: , To talk about in the public domain, right? And

[00:10:42] Angie Jones: so,

[00:10:43] Angie Jones: that

[00:10:43] Angie Jones: was

[00:10:44] Angie Jones: really big for

[00:10:45] Angie Jones: me because

[00:10:46] Angie Jones: it gave me a platform and a stage and, you know, , the

[00:10:49] Angie Jones: opportunity

[00:10:50] Angie Jones: to

[00:10:51] Angie Jones: make myself known in this space.

[00:10:53] Angie Jones: But

[00:10:53] Angie Jones: more

[00:10:54] Angie Jones: than

[00:10:54] Angie Jones: that, like I actually

[00:10:56] Angie Jones: studied,

[00:10:57] Angie Jones: ,

[00:10:57] Angie Jones: Open

[00:10:57] Angie Jones: source

[00:10:58] Angie Jones: while doing my master’s.

[00:10:59] Angie Jones: We had a [00:11:00] open source, class.

[00:11:01] Angie Jones: And

[00:11:02] Angie Jones: so

[00:11:02] Angie Jones: I

[00:11:02] Angie Jones: learned

[00:11:02] Angie Jones: a lot

[00:11:03] Angie Jones: about

[00:11:03] Angie Jones: just

[00:11:03] Angie Jones: like

[00:11:03] Angie Jones: governance

[00:11:04] Angie Jones: of projects and, , maintainers and, how to be

[00:11:08] Angie Jones: nice

[00:11:08] Angie Jones: to

[00:11:08] Angie Jones: contributors and

[00:11:09] Angie Jones: welcome it and, how not to do this with your

[00:11:12] Angie Jones: project.

[00:11:13] Angie Jones: For those listening, I’m doing my arms like I’m hoarding

[00:11:17] Angie Jones: something.

[00:11:18] Angie Jones: basically, it was

[00:11:19] Angie Jones: different.

[00:11:20] Angie Jones: Like, you know, I grew up in the era of like Microsoft software where. Everything was so proprietary no way could you like look at it, , let alone contribute to it. And, you know, everything

[00:11:33] Angie Jones: was

[00:11:33] Angie Jones: a pay to play

[00:11:34] Angie Jones: model.

[00:11:34] Angie Jones: And so to see like open source come and like really shake that up and just change

[00:11:40] Angie Jones: the minds in how

[00:11:42] Angie Jones: we

[00:11:43] Angie Jones: software

[00:11:44] Angie Jones: that’s been

[00:11:45] Angie Jones: I

[00:11:45] Angie Jones: don’t know,

[00:11:46] Angie Jones: like

[00:11:46] Angie Jones: just groundbreaking

[00:11:47] Angie Jones: for me

[00:11:47] Angie Jones: personally.

[00:11:49] Jason: I mean, and

[00:11:49] Jason: not, and

[00:11:49] Jason: not

[00:11:50] Jason: just

[00:11:50] Jason: shake

[00:11:50] Jason: it

[00:11:50] Jason: up, but

[00:11:50] Jason: like

[00:11:52] Jason: almost

[00:11:52] Jason: completely extinguished. The

[00:11:53] Jason: other model. Yeah.

[00:11:54] Jason: Like even the, even the hardcore closed source people are still, they’re using [00:12:00] and often shipping

[00:12:01] Jason: open source, like Microsoft was the

[00:12:03] Jason: number one opponent. And here they are.

[00:12:06] Jason: They’re like

[00:12:06] Jason: the champions

[00:12:07] Jason: of open source. these days. Yes.

[00:12:08] Robbie Wagner: Yeah.

[00:12:10] Angie Jones: oh,

[00:12:10] Angie Jones: so

[00:12:12] Angie Jones: Yeah,

[00:12:12] Angie Jones: that’s exactly

[00:12:13] Angie Jones: right.

[00:12:14] Angie Jones: and that,

[00:12:14] Angie Jones: that’s been really interesting to

[00:12:16] Angie Jones: watch.

[00:12:16] Angie Jones: So

[00:12:16] Angie Jones: much

[00:12:17] Angie Jones: so

[00:12:17] Angie Jones: that

[00:12:17] Angie Jones: they

[00:12:17] Angie Jones: acquire GitHub,

[00:12:19] Robbie Wagner: and

[00:12:19] Robbie Wagner: NPM

[00:12:20] Angie Jones: and

[00:12:20] Angie Jones: NPM and NPM. So, yeah. That’s been really interesting to watch. I, I love the open source community, I work on an open source,

[00:12:29] Angie Jones: ,

[00:12:29] Angie Jones: AI agent now named Goose, and I

[00:12:32] Angie Jones: did

[00:12:32] Angie Jones: a

[00:12:32] Angie Jones: talk

[00:12:33] Angie Jones: a

[00:12:33] Angie Jones: couple of weeks ago.

[00:12:34] Angie Jones: Just

[00:12:35] Angie Jones: talking

[00:12:35] Angie Jones: about the open source nature

[00:12:37] Angie Jones: of

[00:12:37] Angie Jones: it

[00:12:37] Angie Jones: and

[00:12:37] Angie Jones: how important open source is right now when

[00:12:42] Angie Jones: we

[00:12:42] Angie Jones: look

[00:12:42] Angie Jones: at like

[00:12:43] Angie Jones: the agentic

[00:12:44] Angie Jones: AI movement,

[00:12:45] Angie Jones: so

[00:12:45] Angie Jones: we’re starting

[00:12:46] Angie Jones: to see

[00:12:47] Angie Jones: these kind of

[00:12:48] Angie Jones: walled

[00:12:49] Angie Jones: gardens again, where you have proprietary companies

[00:12:53] Angie Jones: that are

[00:12:53] Angie Jones: controlling both the models

[00:12:55] Angie Jones: as

[00:12:55] Angie Jones: well as the

[00:12:55] Angie Jones: agent.

[00:12:56] Angie Jones: call

[00:12:57] Angie Jones: me

[00:12:57] Angie Jones: a

[00:12:57] Angie Jones: conspiracy

[00:12:57] Angie Jones: theorist,

[00:12:58] Angie Jones: but

[00:12:59] Angie Jones: [00:13:00] if

[00:13:00] Angie Jones: I’m

[00:13:00] Angie Jones: gonna benefit from the agent taking the long way to solve your problem because

[00:13:05] Angie Jones: you’re

[00:13:05] Angie Jones: spending

[00:13:05] Angie Jones: more money

[00:13:06] Angie Jones: on

[00:13:06] Angie Jones: tokens.

[00:13:07] Angie Jones: I don’t

[00:13:08] Angie Jones: know. I might bake

[00:13:09] Angie Jones: that

[00:13:09] Angie Jones: into

[00:13:11] Angie Jones: Yeah.

[00:13:12] Angie Jones: You

[00:13:12] Angie Jones: know

[00:13:12] Angie Jones: what

[00:13:12] Angie Jones: I

[00:13:12] Angie Jones: mean?

[00:13:13] Angie Jones: I don’t

[00:13:13] Angie Jones: know.

[00:13:13] Angie Jones: I’m

[00:13:13] Angie Jones: not saying

[00:13:14] Angie Jones: anybody’s

[00:13:14] Angie Jones: doing that,

[00:13:15] Angie Jones: but just things that cross my mind, you know what I mean? And so, , I think that even

[00:13:20] Angie Jones: right

[00:13:20] Angie Jones: now

[00:13:21] Angie Jones: as

[00:13:21] Angie Jones: we are like.

[00:13:22] Angie Jones: Looking at ai, we’re trying to figure it out, is really important for the open source players to have a seat

[00:13:29] Angie Jones: at

[00:13:29] Angie Jones: this table

[00:13:29] Angie Jones: and to help, basically guide where we’re

[00:13:32] Angie Jones: going,

[00:13:32] Angie Jones: which is

[00:13:33] Angie Jones: what I think

[00:13:33] Angie Jones: that, , goose does, right? So Goose is not , the most used agent

[00:13:38] Angie Jones: or

[00:13:38] Angie Jones: anything

[00:13:39] Angie Jones: like that, but I’ll tell you what it

[00:13:40] Angie Jones: is.

[00:13:41] Angie Jones: It

[00:13:41] Angie Jones: was

[00:13:41] Angie Jones: the

[00:13:41] Angie Jones: reference implementation for

[00:13:43] Angie Jones: MCP from

[00:13:44] Angie Jones: the client

[00:13:45] Angie Jones: side,

[00:13:46] Angie Jones: and

[00:13:46] Angie Jones: because it’s open

[00:13:47] Angie Jones: source.

[00:13:48] Angie Jones: The community decides

[00:13:50] Angie Jones: what Ag

[00:13:51] Angie Jones: agentic AI will be for them because

[00:13:54] Angie Jones: we

[00:13:55] Angie Jones: have

[00:13:55] Angie Jones: the

[00:13:55] Angie Jones: most

[00:13:55] Angie Jones: permissible

[00:13:56] Angie Jones: license. People can fork it, people can contribute to it, [00:14:00] and , they contribute the features they want to see.

[00:14:03] Angie Jones: And

[00:14:04] Angie Jones: a

[00:14:04] Angie Jones: lot of

[00:14:04] Angie Jones: that is

[00:14:05] Angie Jones: transparency.

[00:14:06] Angie Jones: and

[00:14:06] Angie Jones: this forces

[00:14:08] Angie Jones: the other big players to then adopt that. So Goose usually

[00:14:12] Angie Jones: is

[00:14:12] Angie Jones: the

[00:14:13] Angie Jones: first one that’s

[00:14:13] Angie Jones: gonna

[00:14:14] Angie Jones: have things

[00:14:14] Angie Jones: like.

[00:14:15] Angie Jones: Huh? Why are we stuck with one model and one provider? What

[00:14:19] Angie Jones: if

[00:14:19] Angie Jones: we

[00:14:20] Angie Jones: opened

[00:14:20] Angie Jones: this

[00:14:20] Angie Jones: up

[00:14:20] Angie Jones: and you bring

[00:14:21] Angie Jones: any model, you

[00:14:22] Angie Jones: want to this, right?

[00:14:24] Angie Jones: People

[00:14:24] Angie Jones: weren’t

[00:14:24] Angie Jones: doing that, and now

[00:14:25] Angie Jones: you’re starting

[00:14:26] Angie Jones: to see this is now being forced because consumers are saying, Hey, I don’t want just one model.

[00:14:32] Angie Jones: I might want GPT for my planning and reasoning,

[00:14:35] Angie Jones: and I

[00:14:35] Angie Jones: want to Use

[00:14:36] Angie Jones: Claude when

[00:14:37] Angie Jones: it’s time to execute.

[00:14:38] Angie Jones: Or

[00:14:39] Angie Jones: even

[00:14:39] Angie Jones: a cheaper local model for execution

[00:14:41] Angie Jones: or

[00:14:41] Angie Jones: something like that, right? And so, , the community,

[00:14:44] Angie Jones: the

[00:14:44] Angie Jones: open

[00:14:45] Angie Jones: source

[00:14:45] Angie Jones: community is the one that is pushing,

[00:14:48] Angie Jones: what

[00:14:48] Angie Jones: agen AI will be. And I, I’m

[00:14:50] Angie Jones: proud that

[00:14:51] Angie Jones: Goose is a

[00:14:52] Angie Jones: one of the

[00:14:52] Angie Jones: vehicles

[00:14:53] Angie Jones: that

[00:14:53] Angie Jones: allows them

[00:14:53] Angie Jones: to do that.

[00:14:54] Robbie Wagner: So somewhat related to open source and ai. Lemme think how I can say [00:15:00] this. Like, you know the thing recently, everyone’s been all.

[00:15:02] Robbie Wagner: Like, oh, if you can’t take art for free and use it in ai, then it’s like AI would die like you. We need all this free stuff. How do you think that relates to like code and like all the code it’s getting from GitHub and , is there a problem there and how do we like

[00:15:17] Robbie Wagner: have

[00:15:18] Robbie Wagner: some sort of funding back from that or something to keep sustaining open source?

[00:15:21] Robbie Wagner: ‘cause if there’s nothing to pull from, then where does it get its data from?

[00:15:25] Angie Jones: That’s

[00:15:25] Angie Jones: a

[00:15:25] Angie Jones: hard

[00:15:26] Angie Jones: problem.

[00:15:26] Angie Jones: I am not a fan

[00:15:29] Angie Jones: of.

[00:15:30] Angie Jones: How these models

[00:15:31] Angie Jones: were born

[00:15:32] Angie Jones: and trained on,

[00:15:34] Angie Jones: ,

[00:15:34] Angie Jones: Data,

[00:15:35] Angie Jones: essentially without people’s

[00:15:36] Angie Jones: permission.

[00:15:37] Angie Jones: Right. I,

[00:15:38] Angie Jones: don’t

[00:15:38] Angie Jones: like that

[00:15:39] Angie Jones: the

[00:15:40] Angie Jones: world

[00:15:40] Angie Jones: seems to have decided though, that

[00:15:43] Angie Jones: this is

[00:15:43] Angie Jones: so

[00:15:43] Angie Jones: valuable

[00:15:45] Angie Jones: that we are willing to

[00:15:46] Angie Jones: overlook

[00:15:47] Angie Jones: that

[00:15:47] Angie Jones: you

[00:15:47] Angie Jones: stole

[00:15:48] Angie Jones: all

[00:15:49] Angie Jones: of the

[00:15:49] Angie Jones: data

[00:15:50] Angie Jones: Yeah.

[00:15:50] Angie Jones: From

[00:15:50] Angie Jones: the internet

[00:15:51] Angie Jones: to

[00:15:51] Angie Jones: build these

[00:15:52] Angie Jones: tools.

[00:15:53] Angie Jones: Right?

[00:15:53] Angie Jones: Yeah.

[00:15:53] Angie Jones: So

[00:15:54] Angie Jones: I

[00:15:54] Angie Jones: don’t know.

[00:15:54] Angie Jones: where we go from here on. I

[00:15:57] Jason: there’s some precedent for ways to make this stuff work. Because [00:16:00] basically what we’re looking for is, if a private company is gonna go into a public space and do something that benefits that company, it shouldn’t be solely for the company’s benefit. And so like an example of, of one way that we’ve seen this done is in Vancouver, for example, if you’re gonna build a building, you have to include a certain portion of that building that is affordable housing, because they’re worried that if people come in and just build luxury condos,

[00:16:31] Jason: it’s

[00:16:31] Jason: gonna ruin the city

[00:16:33] Jason: because there won’t, you know, it won’t be possible for people to live there.

[00:16:35] Jason: You know,

[00:16:35] Jason: look at San Francisco for example. so , the people building. Can either put in that percentage of, of affordable housing or they can fund public works like a public park, a public library, something like that. So in some way, the company has to allocate some of its profit toward benefiting the community

[00:16:54] Jason: that it’s going to benefit from. Right. And so one of the things I would love to see, and this is where I think the, [00:17:00] like why they’re fighting so hard against regulation. I think that, , they should be taxed at a higher rate and that that should go back into funding, art, education, funding, actually paying for these programs that they benefit from.

[00:17:11] Jason: if they need that to exist, if art is so important that if we made them pay for it, the company folds,

[00:17:17] Jason: kind of

[00:17:18] Jason: sounds like,

[00:17:18] Jason: they need to build that into their profit

[00:17:20] Jason: model. Right? because

[00:17:21] Jason: otherwise,

[00:17:22] Jason: I mean, the other, the other outcome is like, if we don’t do this, then they’re gonna continue to use this stuff for free.

[00:17:27] Jason: Which is gonna disincentivize anybody from doing it because they know their work’s gonna get stolen, which means the input

[00:17:32] Jason: suffer, which

[00:17:33] Jason: means that eventually

[00:17:33] Jason: this

[00:17:34] Jason: dries up

[00:17:34] Jason: and everybody’s far worse off for it.

[00:17:36] Jason: So

[00:17:37] Jason: this is

[00:17:37] Jason: one of those things where, well, and

[00:17:39] Jason: I

[00:17:39] Jason: mean this is sort of the thing I’m worried about is that we, we’re very bad as an industry, as a country, as a, as a species at thinking about second and third order effects of things.

[00:17:49] Jason: And the first order effect of AI is that everybody gets access to all this great information really fast. The second order effect is that it disincentivizes literally everybody else from creating because [00:18:00] they know that their work is gonna get chewed up by the AI and they won’t get compensated for it.

[00:18:04] Jason: So the third order effect is we stop getting good information and the AI’s are frozen at whatever level they were at,

[00:18:10] Jason: if the companies are smart, then putting 10% of their profit into sustaining the creativity that makes their product good is a really wise investment. But I don’t

[00:18:20] Jason: think

[00:18:20] Jason: they’re smart.

[00:18:21] Jason: I think they’re greedy

[00:18:22] Jason: and I think

[00:18:22] Jason: they’re,

[00:18:23] Jason: not going

[00:18:23] Jason: to do it. And

[00:18:24] Jason: I think

[00:18:24] Jason: it’s gonna cost

[00:18:25] Jason: us a lot in the long run Unless we get regulation.

[00:18:28] Robbie Wagner: when they first started, Sam Altman was all,

[00:18:30] Robbie Wagner: oh

[00:18:30] Robbie Wagner: yeah. Like this is

[00:18:31] Robbie Wagner: a non-profit and like

[00:18:33] Robbie Wagner: all

[00:18:33] Robbie Wagner: this

[00:18:33] Robbie Wagner: bullshit

[00:18:34] Jason: I mean between, between like Sam Alton and Peter Thiel and Mark Andrees, and I think

[00:18:38] Jason: we’ve realized

[00:18:39] Jason: that the people in

[00:18:39] Jason: charge are

[00:18:40] Jason: not

[00:18:40] Jason: good people.

[00:18:41] Robbie Wagner: Yeah.

[00:18:41] Robbie Wagner: Yes.

[00:18:42] Robbie Wagner: Yeah,

[00:18:42] Robbie Wagner: ‘cause I think if you did that and you took like all the money made and you put it in funds for like, if you put us all out of work, we get some of that money.

[00:18:49] Jason: I, that’s,

[00:18:51] Jason: the, I

[00:18:51] Jason: think

[00:18:51] Jason: this is,

[00:18:52] Jason: sorry, this

[00:18:52] Jason: is your

[00:18:52] Jason: episode. I’m gonna rant.

[00:18:53] Angie Jones: no, go.

[00:18:55] Jason: the the thing that makes me the most mad is when you see an interview with these folks and they [00:19:00] say something like, well, yeah, so AI is gonna make it so that people don’t have to work. we are gonna make it so that you live these lives of leisure and it’s gonna drive the prices down.

[00:19:08] Jason: And I’m like, motherfucker, have you ever, ever

[00:19:11] Jason: seen

[00:19:11] Jason: a

[00:19:11] Jason: company

[00:19:12] Jason: voluntarily, Lower prices? Have you ever seen a

[00:19:17] Jason: society make it possible for somebody to

[00:19:19] Jason: exist

[00:19:20] Jason: without having to make money?

[00:19:21] Angie Jones: And the same people who are saying this

[00:19:23] Angie Jones: are the

[00:19:23] Angie Jones: same

[00:19:23] Angie Jones: people

[00:19:24] Angie Jones: that

[00:19:25] Angie Jones: you

[00:19:25] Angie Jones: know

[00:19:25] Angie Jones: vote

[00:19:25] Angie Jones: against.

[00:19:27] Jason: right?

[00:19:28] Angie Jones: The types of programs that help

[00:19:30] Angie Jones: people

[00:19:30] Angie Jones: in

[00:19:30] Angie Jones: need. So

[00:19:31] Angie Jones: now

[00:19:31] Angie Jones: all

[00:19:31] Angie Jones: of

[00:19:31] Angie Jones: a

[00:19:31] Angie Jones: sudden we’re all,

[00:19:33] Angie Jones: in need and we think

[00:19:34] Angie Jones: that these

[00:19:35] Angie Jones: billionaires are going to say,

[00:19:37] Angie Jones: oh,

[00:19:37] Angie Jones: you

[00:19:37] Angie Jones: know what?

[00:19:38] Angie Jones: Here’s a

[00:19:38] Angie Jones: couple of

[00:19:39] Angie Jones: million

[00:19:39] Angie Jones: dollars,

[00:19:40] Angie Jones: Jason, go live

[00:19:40] Angie Jones: your

[00:19:40] Angie Jones: best life.

[00:19:41] Jason: Yeah.

[00:19:42] Jason: Like we’ve, we’ve literally never seen Peter

[00:19:46] Jason: Thiel part

[00:19:46] Jason: with anything to help somebody

[00:19:48] Jason: else out. Like he is

[00:19:49] Jason: out to amass the

[00:19:50] Jason: most he can.

[00:19:51] Jason: And if he wins the anti-regulation stuff and he, he becomes one of the, you know, the prime investors who has all the AI bucks coming in and he becomes [00:20:00] the, you know, one of the world’s first trillionaires.

[00:20:02] Jason: He’s not

[00:20:02] Jason: gonna turn around

[00:20:03] Jason: and pay for me

[00:20:04] Jason: to go to art

[00:20:04] Jason: school.

[00:20:05] Jason: Yeah.

[00:20:05] Jason: Right.

[00:20:06] Jason: He’s gonna find a

[00:20:07] Jason: way to monetize

[00:20:08] Jason: my therapist.

[00:20:09] Jason: Like,

[00:20:09] Jason: you know what

[00:20:10] Jason: I mean?

[00:20:10] Jason: Like, he’s gonna

[00:20:11] Jason: make it

[00:20:11] Jason: so I

[00:20:11] Jason: gotta

[00:20:11] Jason: pay

[00:20:12] Jason: to

[00:20:12] Jason: go

[00:20:12] Jason: outside.

[00:20:13] Jason: Like,

[00:20:14] Robbie Wagner: Yeah.

[00:20:14] Jason: it’s, it’s, it’s just very frustrating that we’re, we’re saying like, oh no, don’t, don’t regulate innovation. Don’t regulate innovation. And then the promise is if we have unbounded regulation or unbounded innovation,

[00:20:26] Jason: it’s

[00:20:26] Jason: gonna

[00:20:26] Jason: benefit

[00:20:27] Jason: society.

[00:20:28] Jason: We have. Zero proof, zero precedent, no plan, no promise on how they’re actually going to make anybody’s lives better. So the, end result most likely is that wealth disparity.

[00:20:40] Jason: increases. I

[00:20:41] Jason: don’t even

[00:20:41] Jason: know

[00:20:41] Jason: what

[00:20:41] Jason: happens

[00:20:42] Jason: next,

[00:20:42] Jason: because

[00:20:43] Jason: if we, if we don’t, well, I mean , the

[00:20:45] Jason: last time we had

[00:20:46] Jason: wealth

[00:20:46] Jason: disparity

[00:20:47] Jason: this bad,

[00:20:47] Jason: right?

[00:20:48] Jason: We

[00:20:48] Jason: had, it was like the Great Depression, the end of the gilded age. The last

[00:20:52] Jason: time

[00:20:52] Jason: we saw that

[00:20:53] Jason: in Europe,

[00:20:53] Jason: they started cutting people’s heads off like it’s

[00:20:56] Jason: historically,

[00:20:56] Jason: this

[00:20:56] Jason: does

[00:20:57] Jason: not

[00:20:57] Jason: end

[00:20:57] Jason: well

[00:20:57] Jason: for the very, very rich people.

[00:20:59] Jason: Yeah. Right. [00:21:00] And So interest, again, lack

[00:21:02] Jason: of

[00:21:03] Jason: understanding,

[00:21:03] Jason: of second

[00:21:04] Jason: and third

[00:21:04] Jason: order

[00:21:04] Jason: effects. Yeah.

[00:21:05] CTA: This just in! Whiskey.fund is now open for all your merch needs. That’s right, Robbie. We’re hearing reports of hats, sweaters, and T-shirts, as well as a link to join our Discord server. What’s a Discord server? Just read the prompter, man. Hit subscribe. Leave us a review on your favorite podcast app and tell your friends about our broadcast. It really does help us reach more people and keeps the show growing. All right, back to your regularly scheduled programming.

[00:21:38] Angie Jones: I

[00:21:38] Angie Jones: almost feel like people

[00:21:41] Angie Jones: think,

[00:21:42] Angie Jones: companies

[00:21:42] Angie Jones: think

[00:21:43] Angie Jones: that

[00:21:43] Angie Jones: they can’t even

[00:21:44] Angie Jones: afford

[00:21:45] Angie Jones: to

[00:21:45] Angie Jones: think

[00:21:46] Angie Jones: about that.

[00:21:47] Angie Jones: Like

[00:21:47] Angie Jones: the

[00:21:47] Angie Jones: race

[00:21:48] Angie Jones: is so

[00:21:48] Angie Jones: tight

[00:21:49] Angie Jones: on

[00:21:49] Angie Jones: a global scale

[00:21:51] Angie Jones: of.

[00:21:52] Angie Jones: we

[00:21:52] Angie Jones: all know we are in a

[00:21:53] Angie Jones: bubble. It’ll burst.

[00:21:55] Angie Jones: Some

[00:21:55] Angie Jones: will

[00:21:55] Angie Jones: fall, some will stand.

[00:21:57] Angie Jones: So everybody’s racing [00:22:00] to be

[00:22:00] Angie Jones: the one that stands

[00:22:01] Angie Jones: in morals,

[00:22:03] Angie Jones: ethics,

[00:22:03] Angie Jones: everything

[00:22:04] Angie Jones: is

[00:22:04] Angie Jones: like,

[00:22:05] Angie Jones: I have

[00:22:05] Angie Jones: no time

[00:22:06] Angie Jones: to think about that.

[00:22:07] Angie Jones: I

[00:22:07] Angie Jones: just gotta

[00:22:07] Angie Jones: win the

[00:22:08] Angie Jones: race.

[00:22:08] Angie Jones: Yeah.

[00:22:08] Angie Jones: You

[00:22:08] Angie Jones: know,

[00:22:09] Angie Jones: that’s

[00:22:09] Angie Jones: what

[00:22:09] Angie Jones: I

[00:22:09] Angie Jones: feel

[00:22:09] Angie Jones: like,

[00:22:10] Angie Jones: that’s

[00:22:10] Angie Jones: where

[00:22:11] Angie Jones: we are.

[00:22:11] Jason: ,

[00:22:11] Jason: And

[00:22:11] Jason: honestly,

[00:22:12] Jason: this is to,

[00:22:12] Jason: to

[00:22:13] Jason: bring this

[00:22:13] Jason: away

[00:22:13] Jason: from the precipice of

[00:22:14] Jason: a,

[00:22:15] Jason: of

[00:22:15] Jason: like

[00:22:15] Jason: the most depressing episode of Whiskey Web and whatnot ever made. I

[00:22:19] Jason: I I do wanna say this is one of the things that I really admire about you, specifically, Angie, is that

[00:22:25] Jason: when

[00:22:25] Jason: I saw

[00:22:25] Jason: this coming up, my instinct was to back away.

[00:22:29] Jason: I was like, I don’t want to be involved in this, because this is gonna be exactly what

[00:22:33] Jason: you just.

[00:22:33] Jason: Said,

[00:22:35] Jason: and

[00:22:35] Jason: you

[00:22:36] Jason: dove

[00:22:36] Jason: right in.

[00:22:36] Jason: I looked at this

[00:22:37] Jason: and I was like,

[00:22:38] Jason: this is gonna be exhausting. These are not the people that I want to be surrounded with.

[00:22:41] Jason: This is not the culture that I want to be a part of. And you looked at it and you said, i’m not gonna

[00:22:46] Jason: not

[00:22:46] Jason: be in that

[00:22:46] Jason: room.

[00:22:47] Jason: Like, I’m not gonna

[00:22:47] Jason: let them make

[00:22:48] Jason: decisions

[00:22:48] Jason: without us

[00:22:49] Angie Jones: they will.

[00:22:49] Jason: I

[00:22:50] Jason: admire

[00:22:50] Jason: you.

[00:22:50] Jason: because I don’t,

[00:22:51] Jason: I don’t have the, whatever it is that, makes you strong enough to do that.

[00:22:54] Jason: ‘cause I, I’m

[00:22:56] Jason: like,

[00:22:56] Jason: whatever, just

[00:22:57] Jason: put me

[00:22:58] Jason: in

[00:22:58] Jason: the,

[00:22:58] Jason: put

[00:22:58] Jason: me in

[00:22:58] Jason: the

[00:22:58] Jason: data

[00:22:59] Jason: mine, I

[00:22:59] Jason: guess.

[00:22:59] Jason: [00:23:00] I’ll just work away when, when all the jobs are gone.

[00:23:02] Robbie Wagner: Yeah. Let’s, let’s pivot back a little. Um,

[00:23:07] Robbie Wagner: let’s

[00:23:08] Robbie Wagner: talk about MCP in general. Still ai, but a little lighter. What is

[00:23:11] Robbie Wagner: MCP.

[00:23:13] Angie Jones: Okay,

[00:23:13] Angie Jones: so MCP stands for Model Context Protocol. It’s a open standard that was developed by anthropic. It’s pretty

[00:23:20] Angie Jones: new,

[00:23:21] Angie Jones: less

[00:23:21] Angie Jones: than a

[00:23:21] Angie Jones: year old.

[00:23:22] Angie Jones: It

[00:23:22] Angie Jones: was

[00:23:22] Angie Jones: released in November, 2024.

[00:23:24] Angie Jones: So what

[00:23:25] Angie Jones: MCP does

[00:23:27] Angie Jones: . All the stuff we complained about in the early days of, , using AI where they’re hallucinating a lot and just kind of making things up and stuff like that.

[00:23:38] Angie Jones: The reason they do that is ‘cause they don’t have context. So I mean, it’s literally they’re not failing. That’s how they were designed, right, is to generate a response, predict what should be the next word, like that. Is what they do, right? And

[00:23:53] Angie Jones: so

[00:23:53] Angie Jones: when

[00:23:53] Angie Jones: you

[00:23:53] Angie Jones: don’t

[00:23:53] Angie Jones: have context

[00:23:54] Angie Jones: in front

[00:23:55] Angie Jones: of you.

[00:23:56] Angie Jones: Yes,

[00:23:56] Angie Jones: you maybe pick the wrong thing.

[00:23:58] Angie Jones: , MCP

[00:23:59] Angie Jones: [00:24:00] provides

[00:24:00] Angie Jones: a

[00:24:01] Angie Jones: way

[00:24:01] Angie Jones: to

[00:24:02] Angie Jones: get

[00:24:02] Angie Jones: your

[00:24:03] Angie Jones: models

[00:24:04] Angie Jones: context.

[00:24:05] Angie Jones: And

[00:24:05] Angie Jones: with that,

[00:24:06] Angie Jones: the

[00:24:06] Angie Jones: models now

[00:24:07] Angie Jones: also

[00:24:07] Angie Jones: have function calling abilities.

[00:24:09] Angie Jones: Couple

[00:24:10] Angie Jones: those two.

[00:24:11] Angie Jones: And

[00:24:11] Angie Jones: now

[00:24:11] Angie Jones: you get to

[00:24:13] Angie Jones: agents,

[00:24:14] Angie Jones: right?

[00:24:14] Angie Jones: Ag agentic ai,

[00:24:16] Angie Jones: ,

[00:24:16] Angie Jones: Where

[00:24:17] Angie Jones: you can actually

[00:24:18] Angie Jones: build

[00:24:18] Angie Jones: software that can

[00:24:19] Angie Jones: talk

[00:24:20] Angie Jones: to

[00:24:20] Angie Jones: these models.

[00:24:21] Angie Jones: And then take actions on your behalf.

[00:24:23] Angie Jones: And

[00:24:23] Angie Jones: so

[00:24:24] Angie Jones: in order for

[00:24:25] Angie Jones: an agent to take action on

[00:24:26] Angie Jones: your behalf, one, they need to

[00:24:27] Angie Jones: be connected

[00:24:29] Angie Jones: to

[00:24:29] Angie Jones: your systems

[00:24:30] Angie Jones: and

[00:24:30] Angie Jones: they

[00:24:30] Angie Jones: need

[00:24:31] Angie Jones: data and

[00:24:31] Angie Jones: context.

[00:24:32] Angie Jones: So

[00:24:32] Angie Jones: MCP is

[00:24:34] Angie Jones: a

[00:24:34] Angie Jones: standard

[00:24:34] Angie Jones: that

[00:24:34] Angie Jones: provides

[00:24:36] Angie Jones: a

[00:24:36] Angie Jones: way

[00:24:37] Angie Jones: for

[00:24:37] Angie Jones: the

[00:24:37] Angie Jones: agents to get that context right. And.

[00:24:40] Angie Jones: It’s, a nice, clean way so that you don’t have to do integrations with every single

[00:24:45] Angie Jones: API

[00:24:46] Angie Jones: that you might want your AI to talk to.

[00:24:48] Angie Jones: Instead, if that

[00:24:50] Angie Jones: API, is exposed via an MCP server,

[00:24:55] Angie Jones: for example,

[00:24:56] Angie Jones: you

[00:24:56] Angie Jones: can just

[00:24:56] Angie Jones: plug that into

[00:24:57] Angie Jones: any agent. And MCP is,

[00:24:59] Angie Jones: , [00:25:00] LLM agnostic. It’s agent agnostic, so it truly is, this open

[00:25:04] Angie Jones: standard and

[00:25:05] Angie Jones: it’s

[00:25:05] Angie Jones: been great

[00:25:06] Angie Jones: for.

[00:25:07] Angie Jones: us

[00:25:07] Angie Jones: getting value

[00:25:09] Angie Jones: out of ai.

[00:25:10] Robbie Wagner: I’m

[00:25:10] Robbie Wagner: trying to equate this to, so like in Ember, what I know, you used to have like serializers for your data, right? Or in anything where you need to munch some data, you’ll have a serializer.

[00:25:21] Robbie Wagner: And if anyone didn’t quite get the, , standard right, the spec, right, they didn’t quite follow the spec. They have a lot of problems. So I’m wondering if that is a problem with MCP, if like some people are doing a little bit of their own flavor, not following the spec, like, and it doesn’t work everywhere or like what kind of challenges are you seeing around that?

[00:25:41] Robbie Wagner: Or is it

[00:25:41] Robbie Wagner: a challenge? I

[00:25:42] Robbie Wagner: don’t know.

[00:25:42] Angie Jones: It’s

[00:25:42] Angie Jones: pretty simple. Um, , the spec is wide and so you don’t have to implement like every part of the spec, but

[00:25:48] Angie Jones: there’s

[00:25:49] Angie Jones: like certain parts you definitely do if you’re gonna. Like work

[00:25:52] Angie Jones: at all. I guess most common part

[00:25:55] Angie Jones: of that

[00:25:55] Angie Jones: is

[00:25:55] Angie Jones: the

[00:25:55] Angie Jones: tools part of

[00:25:56] Angie Jones: the spec. So

[00:25:57] Angie Jones: as

[00:25:57] Angie Jones: long as you follow

[00:25:58] Angie Jones: that, you should be [00:26:00] good.

[00:26:00] Angie Jones: So

[00:26:00] Angie Jones: your server might not have,

[00:26:02] Angie Jones: all

[00:26:03] Angie Jones: of

[00:26:03] Angie Jones: the other

[00:26:03] Angie Jones: pieces, but

[00:26:04] Angie Jones: the tools part is critical in

[00:26:07] Angie Jones: order

[00:26:07] Angie Jones: for

[00:26:07] Angie Jones: it

[00:26:08] Angie Jones: to

[00:26:08] Angie Jones: work. So as long as

[00:26:09] Angie Jones: you

[00:26:09] Angie Jones: follow

[00:26:09] Angie Jones: that

[00:26:10] Angie Jones: part,

[00:26:10] Angie Jones: and

[00:26:10] Angie Jones: it’s

[00:26:10] Angie Jones: not like really hard,

[00:26:12] Angie Jones: it’s

[00:26:12] Angie Jones: like.

[00:26:13] Angie Jones: Okay,

[00:26:14] Angie Jones: describe

[00:26:14] Angie Jones: the

[00:26:15] Angie Jones: name like this, the description, and then what

[00:26:17] Angie Jones: do you wanna do in the body?

[00:26:18] Angie Jones: So

[00:26:18] Angie Jones: very much like a regular function. So there’s

[00:26:21] Angie Jones: syntax

[00:26:22] Angie Jones: there of course,

[00:26:23] Angie Jones: but

[00:26:23] Angie Jones: , Other than

[00:26:23] Angie Jones: that,

[00:26:24] Angie Jones: yeah,

[00:26:24] Angie Jones: it should be good to go.

[00:26:25] Jason: I think I saw you, you post about this recently where you were saying that people are, are going out there saying, oh, this is our MCP agent for x.

[00:26:32] Jason: Our agent four y are, are you seeing that, is that marketing or is that, are, are people trying to build

[00:26:39] Jason: like little

[00:26:39] Jason: walled gardens

[00:26:40] Jason: inside of

[00:26:40] Jason: MCP?

[00:26:41] Angie Jones: Okay,

[00:26:41] Angie Jones: so

[00:26:42] Angie Jones: it, it’s the servers that they’re seeing that for. So they build a MCP server

[00:26:46] Angie Jones: and a MCP server.

[00:26:47] Angie Jones: Let’s say you make a MCP server

[00:26:48] Angie Jones: for,

[00:26:50] Angie Jones: let’s

[00:26:50] Angie Jones: just

[00:26:50] Angie Jones: say YouTube. All right.

[00:26:52] Angie Jones: So I got MTP server for YouTube,

[00:26:53] Angie Jones: which means if I

[00:26:54] Angie Jones: plug this

[00:26:55] Angie Jones: into,

[00:26:56] Angie Jones: ,

[00:26:56] Angie Jones: Any agent.

[00:26:57] Angie Jones: Then it should be able to [00:27:00] interact with YouTube

[00:27:01] Angie Jones: on

[00:27:01] Angie Jones: my

[00:27:01] Angie Jones: behalf, meaning logged

[00:27:03] Angie Jones: in

[00:27:04] Angie Jones: as me, Angie, and

[00:27:05] Angie Jones: do

[00:27:05] Angie Jones: whatever I needed to do, right? So I can say something

[00:27:08] Angie Jones: like,

[00:27:08] Angie Jones: oh, find y’all the videos on

[00:27:10] Angie Jones: MCP and make

[00:27:11] Angie Jones: me

[00:27:11] Angie Jones: like,

[00:27:12] Angie Jones: , A playlist or something like that, right?

[00:27:14] Angie Jones: Anyway,

[00:27:15] Angie Jones: so

[00:27:15] Angie Jones: if I

[00:27:16] Angie Jones: were to make that server

[00:27:17] Angie Jones: and

[00:27:17] Angie Jones: I

[00:27:17] Angie Jones: said, Hey.

[00:27:19] Angie Jones: I

[00:27:19] Angie Jones: made a

[00:27:19] Angie Jones: new YouTube MCP server

[00:27:22] Angie Jones: for

[00:27:22] Angie Jones: goose,

[00:27:22] Angie Jones: or

[00:27:23] Angie Jones: for claw

[00:27:23] Angie Jones: code,

[00:27:24] Angie Jones: or

[00:27:24] Angie Jones: something like

[00:27:25] Angie Jones: that. Sounds silly.

[00:27:26] Angie Jones: ,

[00:27:26] Angie Jones: And the reason

[00:27:27] Angie Jones: it

[00:27:27] Angie Jones: sounds

[00:27:27] Angie Jones: silly

[00:27:28] Angie Jones: is because

[00:27:29] Angie Jones: the

[00:27:29] Angie Jones: MCP servers are supposed to

[00:27:30] Angie Jones: be

[00:27:31] Angie Jones: agent

[00:27:32] Angie Jones: agnostic,

[00:27:33] Angie Jones: meaning

[00:27:34] Angie Jones: like,

[00:27:35] Angie Jones: as

[00:27:35] Angie Jones: long as

[00:27:36] Angie Jones: it, the agent adheres to the spec, your

[00:27:38] Angie Jones: MCP server

[00:27:39] Angie Jones: works

[00:27:40] Angie Jones: with all

[00:27:40] Angie Jones: of

[00:27:40] Angie Jones: them.

[00:27:41] Angie Jones: So

[00:27:41] Angie Jones: can’t see DODs, uh.

[00:27:42] Jason: the, that’s

[00:27:43] Jason: sort of

[00:27:43] Jason: the

[00:27:43] Jason: underlying question is

[00:27:44] Jason: like,

[00:27:45] Jason: are you

[00:27:45] Jason: seeing,

[00:27:46] Angie Jones: people say

[00:27:46] Angie Jones: that I don’t.

[00:27:47] Angie Jones: know

[00:27:47] Angie Jones: if it’s marketing

[00:27:48] Angie Jones: or

[00:27:49] Angie Jones: just a misunderstanding.

[00:27:51] Angie Jones: So for example,

[00:27:52] Angie Jones: If

[00:27:52] Angie Jones: you use claw code,

[00:27:53] Angie Jones: right?

[00:27:54] Angie Jones: You

[00:27:54] Angie Jones: might

[00:27:55] Angie Jones: make

[00:27:55] Angie Jones: an MCP server, you tried it

[00:27:57] Angie Jones: with

[00:27:57] Angie Jones: claw code and you say, yeah, I’m

[00:27:59] Angie Jones: just

[00:27:59] Angie Jones: [00:28:00] gonna

[00:28:00] Angie Jones: advertise

[00:28:01] Angie Jones: it

[00:28:01] Angie Jones: as this

[00:28:01] Angie Jones: ‘cause I

[00:28:01] Angie Jones: haven’t even tried

[00:28:02] Angie Jones: it with the

[00:28:02] Angie Jones: rest of the agents.

[00:28:03] Angie Jones: I don’t know if it

[00:28:03] Angie Jones: works or

[00:28:04] Angie Jones: not,

[00:28:05] Angie Jones: or,

[00:28:05] Angie Jones: you

[00:28:05] Angie Jones: know, call code is popular.

[00:28:07] Angie Jones: you tag that

[00:28:08] Angie Jones: onto yours for SEO value.

[00:28:10] Jason: Yeah, know Why

[00:28:11] Angie Jones: they do

[00:28:12] Angie Jones: it, but it upsets me because, uh, Kenzie dos, he, he quote tweeted that in, in that

[00:28:18] Angie Jones: my

[00:28:18] Angie Jones: tweet

[00:28:19] Angie Jones: and

[00:28:19] Angie Jones: said,

[00:28:20] Angie Jones: that’s like

[00:28:20] Angie Jones: saying I

[00:28:21] Angie Jones: made a website for

[00:28:22] Angie Jones: Google

[00:28:22] Angie Jones: Chrome.

[00:28:23] Angie Jones: And

[00:28:23] Angie Jones: that’s

[00:28:23] Angie Jones: exactly

[00:28:24] Angie Jones: what

[00:28:24] Robbie Wagner: it, like website

[00:28:26] Angie Jones: works

[00:28:26] Angie Jones: on

[00:28:26] Angie Jones: any

[00:28:26] Angie Jones: browser.

[00:28:27] Angie Jones: Who well, and, and this

[00:28:28] Jason: is, this

[00:28:29] Jason: is

[00:28:29] Jason: the

[00:28:29] Jason: part that

[00:28:29] Jason: always had

[00:28:30] Jason: me worried is because

[00:28:31] Jason: in the

[00:28:32] Jason: old

[00:28:32] Jason: days,

[00:28:32] Jason: right, there

[00:28:33] Jason: was like internet

[00:28:33] Jason: Explorer and Netscape, and you

[00:28:35] Jason: would

[00:28:36] Jason: run

[00:28:36] Jason: into the

[00:28:36] Jason: websites

[00:28:37] Jason: that were like,

[00:28:37] Jason: oh, you’re on Netscape.

[00:28:38] Jason: You need to open

[00:28:39] Jason: Internet

[00:28:39] Jason: Explorer

[00:28:39] Jason: to

[00:28:39] Jason: see

[00:28:40] Jason: this

[00:28:40] Jason: one. Yeah.

[00:28:41] Jason: Right.

[00:28:41] Jason: And so,

[00:28:42] Jason: That was my That’s kind of true to see the same

[00:28:45] Angie Jones: thing

[00:28:45] Angie Jones: happen.

[00:28:45] Angie Jones: Okay.

[00:28:45] Angie Jones: Well that’s

[00:28:46] Angie Jones: kind

[00:28:46] Angie Jones: of true.

[00:28:47] Angie Jones: ,

[00:28:47] Angie Jones: Like I was talking about with the spec. So if I implement tools, yes. I work in like pretty much any.

[00:28:53] Angie Jones: these agents that adhere to the spec are called MCP clients, right? So

[00:28:59] Angie Jones: I

[00:28:59] Angie Jones: work [00:29:00] with any client if I support tools.

[00:29:02] Angie Jones: Now,

[00:29:02] Angie Jones: there’s other features within the spec that you can add to your MCP server, but

[00:29:10] Angie Jones: that

[00:29:10] Angie Jones: doesn’t mean

[00:29:11] Angie Jones: all of the agents support those yet, right?

[00:29:14] Angie Jones: For example,

[00:29:15] Angie Jones: MCP

[00:29:16] Angie Jones: UI is something

[00:29:17] Angie Jones: that’s, relatively new, is

[00:29:18] Angie Jones: getting A lot

[00:29:19] Angie Jones: of community,

[00:29:20] Angie Jones: Interest in it,

[00:29:21] Angie Jones: but

[00:29:22] Angie Jones: it’s where

[00:29:22] Angie Jones: you

[00:29:23] Angie Jones: know how

[00:29:23] Angie Jones: you’re talking to your agent and it’s just text-based. Right? And maybe they even ask you a question saying like, do you want me to do option one, option two, or option three?

[00:29:35] Angie Jones: And you have to type

[00:29:36] Angie Jones: that in, right?

[00:29:37] Angie Jones: That would be

[00:29:37] Angie Jones: better

[00:29:38] Angie Jones: as

[00:29:38] Angie Jones: like

[00:29:38] Angie Jones: a radio, a

[00:29:39] Angie Jones: set of

[00:29:40] Angie Jones: radio button chat by something like that. Right? So something you can interact with. So that’s one of, the features that’s being proposed to the spec. And of course it’s so new that a lot of agents have not adopted that yet.

[00:29:52] Angie Jones: So if you MCP server has that, then yeah, you might.

[00:29:56] Angie Jones: Say this does not work with this particular agent. In fact, goose [00:30:00] is like the only one that has implemented that. Again, because it’s open

[00:30:04] Angie Jones: source. A community member added that,

[00:30:06] Angie Jones: not

[00:30:06] Angie Jones: The core team. Right.

[00:30:08] Angie Jones: And so,

[00:30:08] Jason: So

[00:30:09] Jason: it’s, it’s

[00:30:09] Jason: early

[00:30:09] Jason: browser days. We’re,

[00:30:10] Jason: we’re inventing things. The features are,

[00:30:13] Jason: We

[00:30:13] Jason: haven’t, we haven’t unified on like a a W three C for, for MCP oversight.

[00:30:19] Angie Jones: Okay.

[00:30:20] Jason: Well,

[00:30:20] Jason: that’s

[00:30:20] Jason: what I’m, oh, that’s,

[00:30:21] Jason: kind of what

[00:30:21] Jason: I’m asking. ‘cause like, you know, right now the browsers have the, the

[00:30:25] Jason: sort of like

[00:30:25] Jason: core group that’s like, these are the

[00:30:27] Jason: features.

[00:30:28] Jason: We’ve, we’ve as a group decided these are gonna ship and then all the browsers will, will

[00:30:32] Jason: put an

[00:30:33] Jason: intent

[00:30:33] Jason: to ship. Yeah. Yeah.

[00:30:34] Jason: And that’s the signal that like, yeah, it’s coming so you can safely use this.

[00:30:38] Jason: Whereas other ones are like, well, only Google is gonna ship this, so, you know, safari’s not gonna

[00:30:44] Angie Jones: this. Yeah. don’t

[00:30:44] Angie Jones: use this in

[00:30:45] Angie Jones: your

[00:30:45] Jason: website

[00:30:45] Jason: unless you’re

[00:30:45] Jason: comfortable

[00:30:46] Jason: with

[00:30:46] Jason: non-standard stuff.

[00:30:47] Angie Jones: I

[00:30:48] Angie Jones: think we’re,

[00:30:48] Angie Jones: we’re kind of there. I would say that it is adopted

[00:30:51] Angie Jones: and

[00:30:51] Angie Jones: everybody

[00:30:52] Angie Jones: has done

[00:30:53] Angie Jones: the whole

[00:30:53] Angie Jones: intent to ship

[00:30:54] Angie Jones: thing.

[00:30:55] Jason: Okay. haven’t gotten to it

[00:30:56] Angie Jones: yet. Right.

[00:30:57] Angie Jones: Okay. well, no,

[00:30:57] Angie Jones: that’s, that’s

[00:30:57] Angie Jones: actually great to hear. Yeah. Yeah, yeah. [00:31:00] Oh yeah.

[00:31:00] Angie Jones: I think it’s pretty mature for, to be

[00:31:02] Angie Jones: such

[00:31:02] Angie Jones: a.

[00:31:03] Angie Jones: A

[00:31:03] Angie Jones: young model.

[00:31:04] Angie Jones: There’s, , so

[00:31:04] Angie Jones: much

[00:31:05] Angie Jones: energy around

[00:31:05] Angie Jones: it. There’s

[00:31:06] Angie Jones: like all of these working groups and things that are like really focused on,

[00:31:11] Angie Jones: ,

[00:31:11] Angie Jones: On making

[00:31:12] Angie Jones: sure

[00:31:12] Angie Jones: that this

[00:31:13] Angie Jones: is,

[00:31:13] Angie Jones: a big

[00:31:13] Angie Jones: boy standard.

[00:31:14] Angie Jones: You know?

[00:31:16] Jason: Is

[00:31:16] Jason: it my question?

[00:31:18] Robbie Wagner: Oh, it can be. Yours

[00:31:19] Jason: Because I feel like It’s

[00:31:20] Jason: a good

[00:31:20] Jason: follow up

[00:31:20] Jason: here. one of the things I was really curious about is, because you’ve wade into this space that is brand new and you’re working in, enablement, you’re running the Derel team for Goose, , you’re doing a lot of the outreach stuff. How are you building a, , educational and advocacy program around

[00:31:39] Jason: concepts that

[00:31:39] Jason: like didn’t exist

[00:31:41] Jason: last month?

[00:31:41] Jason: because, you know, like Dere, it feels like took many years to mature to the point. there

[00:31:45] Jason: was

[00:31:45] Jason: anything

[00:31:46] Jason: resembling like

[00:31:47] Jason: a

[00:31:47] Jason: standard or a plan

[00:31:48] Jason: that you could follow. So how have you approached this and, and how are you looking at this space and with how quickly it’s moving to build a program that is

[00:31:57] Jason: resilient in the face of how

[00:31:59] Jason: fast

[00:31:59] Jason: [00:32:00] everything

[00:32:00] Angie Jones: You know, I get a lot of kudos

[00:32:02] Angie Jones: about

[00:32:03] Angie Jones: my team and how

[00:32:04] Angie Jones: they are. Essentially teaching the masses about this brand new technology, and it goes far beyond our product, right? So we’re like teaching concepts that are applicable to our competitor, like any, product. And that’s totally fine, right? I think that’s how it should be done.

[00:32:21] Angie Jones: but I’ve always been one to kind of work on the cutting edge and then bring everybody along with me. I feel like that.

[00:32:29] Angie Jones: My purpose in tech. I’m pretty good at like figuring out new complex stuff and then breaking it down so that we all understand together. I shouldn’t be the only one who gets this, so we’re, we’re building.

[00:32:42] Angie Jones: Out loud

[00:32:42] Angie Jones: and learning

[00:32:43] Angie Jones: together. So it’s very obvious. This is new. We’re not experts. We’re very clear about that. , And we say, but hey, I tried it out. This is what I’ve learned. This is what I learned, doesn’t work so great. And just sharing those lessons. And because, , we work in [00:33:00] DeVere, we have. The privilege of working with this stuff day in and day out.

[00:33:04] Angie Jones: Whereas other people who are working on like production software, engineering teams, like may not be able to dive that deep ‘cause they have other deliverables they need to meet. Right. the other part of my role is, , internally with our engineering org. And so I work with them. To, they use all sorts of tools, goose claw cursor, they use ‘em all.

[00:33:27] Angie Jones: So I, I’m very aware of everything that’s out there and what works and what doesn’t work in real enterprise environments. Right. And so, ,

[00:33:37] Angie Jones: my

[00:33:37] Angie Jones: job is to

[00:33:37] Angie Jones: help them go beyond just using like code generation, but to embed,

[00:33:45] Angie Jones: ,

[00:33:45] Angie Jones: AI

[00:33:46] Angie Jones: and agents into

[00:33:47] Angie Jones: like.

[00:33:49] Angie Jones: Their repos into ci, into like all the things, right? And so, I see

[00:33:54] Angie Jones: a

[00:33:54] Angie Jones: lot,

[00:33:55] Angie Jones: I learn a lot, , on real,

[00:33:57] Angie Jones: production, software development.

[00:33:59] Angie Jones: And [00:34:00] so I feel it’s my duty

[00:34:01] Angie Jones: to

[00:34:02] Angie Jones: like

[00:34:02] Angie Jones: share

[00:34:02] Angie Jones: those

[00:34:03] Angie Jones: lessons,

[00:34:04] Angie Jones: ,

[00:34:04] Angie Jones: More

[00:34:04] Angie Jones: broadly

[00:34:05] Angie Jones: externally.

[00:34:06] Jason: And so

[00:34:06] Jason: so

[00:34:06] Jason: your

[00:34:07] Jason: strategy

[00:34:07] Jason: is

[00:34:07] Jason: kind of

[00:34:07] Jason: just

[00:34:08] Jason: go all in on

[00:34:09] Jason: learning in

[00:34:09] Jason: public. Oh yeah.

[00:34:10] Angie Jones: Go

[00:34:10] Angie Jones: all

[00:34:10] Angie Jones: in

[00:34:10] Angie Jones: on learning probably. I like,

[00:34:11] Angie Jones: I don’t know any of this and you

[00:34:12] Angie Jones: don’t either.

[00:34:13] Robbie Wagner: You gotta

[00:34:14] Robbie Wagner: learn.

[00:34:15] Robbie Wagner: I’m one for

[00:34:15] Angie Jones: the team.

[00:34:16] Angie Jones: here’s what I learned,

[00:34:17] Angie Jones: kind of thing. Yeah,

[00:34:18] Robbie Wagner: Yeah, I think that’s a great way to do it because something you’ve just learned, you’re gonna be able to explain

[00:34:24] Robbie Wagner: better ‘cause

[00:34:24] Robbie Wagner: that person’s

[00:34:25] Robbie Wagner: in the same exact situation you were in a minute ago.

[00:34:28] Robbie Wagner: Like. They wanna learn it. You just learned it.

[00:34:31] Robbie Wagner: Perfect.

[00:34:31] Jason: And it’s, it’s

[00:34:32] Jason: kind of the only way to get out of, , what I think the major hangup for me with a lot of the AI stuff for so long was that every

[00:34:38] Jason: discussion, every

[00:34:39] Jason: demo was theoretical. People

[00:34:41] Jason: were just telling me

[00:34:42] Jason: what they

[00:34:42] Jason: thought it would do or, or what they

[00:34:44] Jason: think it could

[00:34:44] Jason: solve. And I was like.

[00:34:45] Jason: Build it.

[00:34:46] Jason: Show me, like, show me anything.

[00:34:48] Jason: Like, I don’t, I don’t, believe you because you

[00:34:50] Jason: keep telling

[00:34:50] Jason: me

[00:34:51] Jason: and

[00:34:51] Jason: nobody’s

[00:34:51] Jason: showing me and

[00:34:52] Jason: it

[00:34:52] Jason: doesn’t

[00:34:52] Jason: seem real.

[00:34:53] Angie Jones: I did, uh, the Dere Khan. ,

[00:34:56] Angie Jones: So

[00:34:56] Angie Jones: it’s funny.

[00:34:57] Angie Jones: All my friends, Jason

[00:34:58] Angie Jones: included.

[00:34:59] Angie Jones: Laugh [00:35:00] about

[00:35:00] Angie Jones: Dere Kahan, and

[00:35:01] Angie Jones: they’re like,

[00:35:01] Angie Jones: what is

[00:35:02] Angie Jones: that?

[00:35:02] Angie Jones: Like

[00:35:02] Angie Jones: y’all just a

[00:35:02] Angie Jones: bunch of dere

[00:35:03] Angie Jones: like

[00:35:04] Angie Jones: selling

[00:35:04] Angie Jones: your products to

[00:35:05] Angie Jones: each other. But it’s,

[00:35:07] Angie Jones: it’s,

[00:35:07] Angie Jones: not

[00:35:08] Angie Jones: that

[00:35:08] Angie Jones: at all

[00:35:09] Angie Jones: Dere, Kahan is very much about the craft of developer relations and like how to do these sorts of things, right?

[00:35:15] Angie Jones: And so I did the keynote there and I talked about how Dere is now on its biggest stage yet. And I talk about like, this is a new movement where. All engineers, no matter, like what they’re doing, have like a mandate from like their CEOs that they have to learn these tools and these concepts and these software engineering patterns.

[00:35:38] Angie Jones: and

[00:35:38] Angie Jones: so

[00:35:39] Angie Jones: this

[00:35:39] Angie Jones: just goes way beyond

[00:35:40] Angie Jones: your

[00:35:41] Angie Jones: product or

[00:35:41] Angie Jones: your tool.

[00:35:42] Angie Jones: Like

[00:35:42] Angie Jones: your,

[00:35:43] Angie Jones: everything

[00:35:43] Angie Jones: that you’re doing is uplifting the entire software engineering community. You know what I mean? And so,

[00:35:49] Angie Jones: ,

[00:35:49] Angie Jones: Y’all should

[00:35:49] Angie Jones: check that

[00:35:50] Angie Jones: talk out.

[00:35:51] Angie Jones: If you have a, have some time. And

[00:35:53] Jason: And just

[00:35:53] Jason: to

[00:35:53] Jason: be

[00:35:53] Jason: clear,

[00:35:54] Jason: I don’t

[00:35:54] Jason: think

[00:35:54] Jason: DeVere Con is

[00:35:55] Jason: Devereux

[00:35:55] Jason: selling

[00:35:56] Jason: other

[00:35:56] Jason: DeVere sinks. Oh, Okay.

[00:35:57] Jason: Okay. That’s what I think

[00:35:57] Jason: every other

[00:35:58] Angie Jones: Oh,

[00:35:58] Angie Jones: Oh,

[00:35:59] Angie Jones: yes.[00:36:00]

[00:36:00] Robbie Wagner: You’re not

[00:36:01] Robbie Wagner: wrong.

[00:36:02] Robbie Wagner: Speak.

[00:36:04] Angie Jones: Shame. Shame.

[00:36:06] Robbie Wagner: Oh. Speaking of

[00:36:08] Robbie Wagner: other

[00:36:08] Robbie Wagner: conferences, you’ve been, uh, at a few and we’ll be at a few more,

[00:36:12] Jason: one

[00:36:12] Jason: or two.

[00:36:14] Robbie Wagner: yeah. I wanted to get your take on like, how do we solve this problem that every single conference is like, you know, when’s a good time,

[00:36:20] Robbie Wagner: October,

[00:36:22] Jason: For,

[00:36:23] Robbie Wagner: like,

[00:36:23] Robbie Wagner: please, My, my my sleep

[00:36:25] Jason: schedule

[00:36:26] Jason: is

[00:36:26] Jason: begging for

[00:36:26] Jason: an

[00:36:26] Jason: answer to this question.

[00:36:28] Angie Jones: yeah.

[00:36:29] Angie Jones: Yeah.

[00:36:29] Angie Jones: And it’s draining. I’m on tour

[00:36:31] Angie Jones: right now. ,

[00:36:32] Angie Jones: I

[00:36:33] Angie Jones: literally will

[00:36:33] Angie Jones: not see

[00:36:34] Angie Jones: my house

[00:36:34] Angie Jones: in

[00:36:35] Angie Jones: the month of October.

[00:36:36] Angie Jones: Um, so it’s

[00:36:37] Angie Jones: just like back to back trips. The part that gets me is, , people don’t realize like how much it goes into

[00:36:44] Angie Jones: Speaking at a conference, like the major

[00:36:47] Angie Jones: part, of course

[00:36:47] Angie Jones: is like preparing my talk and

[00:36:49] Angie Jones: all

[00:36:49] Angie Jones: of that.

[00:36:51] Angie Jones: But I mean, each conference is like, oh, can we jump on a call? Oh, can I see your slides? Oh, can we meet, can we do? And it’s like, I have too

[00:36:59] Angie Jones: many

[00:36:59] Angie Jones: conferences [00:37:00] to

[00:37:00] Angie Jones: do this. Like, I’m gonna

[00:37:01] Angie Jones: show

[00:37:01] Angie Jones: up,

[00:37:01] Angie Jones: gonna do a

[00:37:02] Angie Jones: great

[00:37:02] Angie Jones: job,

[00:37:04] Angie Jones: And

[00:37:05] Angie Jones: then,

[00:37:05] Angie Jones: and

[00:37:05] Angie Jones: then

[00:37:06] Angie Jones: let’s

[00:37:06] Angie Jones: just call

[00:37:06] Angie Jones: it

[00:37:06] Angie Jones: a day. You

[00:37:07] Angie Jones: know,

[00:37:08] Jason: I hit my breaking point

[00:37:09] Jason: with this because I,

[00:37:10] Jason: I, you

[00:37:10] Jason: and

[00:37:10] Jason: I are on,

[00:37:11] Jason: on tour together

[00:37:11] Jason: here for a little while. I think we

[00:37:12] Jason: got like

[00:37:13] Jason: five

[00:37:13] Jason: events

[00:37:14] Jason: over the next few weeks that we’re gonna both be at.

[00:37:16] Jason: I was getting those same emails and I,

[00:37:17] Jason: kind

[00:37:18] Jason: of

[00:37:18] Jason: hit my breaking point

[00:37:19] Jason: and I just

[00:37:20] Jason: sent an

[00:37:20] Jason: email that was like,

[00:37:21] Jason: listen,

[00:37:22] Jason: I’m so

[00:37:22] Jason: flattered that you wanted me to be part of this. I’m not doing any of that. Uh. I understand if you’re uncomfortable with that, I will happily yield my

[00:37:31] Jason: spot. but

[00:37:32] Jason: like, I can’t. I

[00:37:32] Jason: can’t,

[00:37:33] Jason: I can’t

[00:37:33] Jason: do it.

[00:37:34] Jason: I’m

[00:37:34] Jason: gonna

[00:37:34] Jason: show

[00:37:34] Jason: up. I’m gonna do

[00:37:35] Jason: a

[00:37:35] Jason: great

[00:37:35] Jason: job.

[00:37:35] Jason: I’m

[00:37:35] Jason: gonna

[00:37:36] Jason: bring

[00:37:36] Jason: my

[00:37:36] Jason: computer

[00:37:37] Jason: and

[00:37:37] Jason: I’m gonna

[00:37:37] Jason: plug

[00:37:37] Jason: it in.

[00:37:38] Jason: And

[00:37:38] Jason: that’s all it is gonna

[00:37:39] Jason: be

[00:37:39] Jason: like, I’m not

[00:37:40] Jason: sending you slides

[00:37:40] Jason: ahead

[00:37:40] Jason: of time.

[00:37:41] Jason: We’re

[00:37:41] Jason: not

[00:37:41] Jason: doing

[00:37:41] Jason: a content

[00:37:42] Jason: review.

[00:37:42] Jason: We’re

[00:37:42] Jason: not

[00:37:43] Jason: doing,

[00:37:43] Jason: I

[00:37:43] Jason: don’t

[00:37:44] Jason: need

[00:37:44] Jason: a speaker

[00:37:44] Jason: coach. Like,

[00:37:45] Jason: I

[00:37:45] Jason: like,

[00:37:45] Jason: I, I

[00:37:46] Jason: appreciate

[00:37:47] Jason: all of these resources.

[00:37:48] Jason: I’m

[00:37:48] Jason: not doing it

[00:37:49] Angie Jones: Yeah.

[00:37:50] Angie Jones: yeah, that’s

[00:37:50] Angie Jones: true. I mean, and right

[00:37:52] Angie Jones: now, I mean,

[00:37:53] Angie Jones: developer

[00:37:55] Angie Jones: advocates

[00:37:55] Angie Jones: Are

[00:37:56] Angie Jones: mostly

[00:37:58] Angie Jones: the ones that people are [00:38:00] paying to come to this,

[00:38:01] Angie Jones: right? Yeah.

[00:38:01] Angie Jones: Like a lot of these

[00:38:02] Angie Jones: conferences. They’re community driven or whatever. They

[00:38:05] Angie Jones: don’t

[00:38:05] Angie Jones: have the budget

[00:38:06] Angie Jones: to like

[00:38:06] Angie Jones: fly everybody

[00:38:08] Angie Jones: in

[00:38:08] Angie Jones: and pay. You know,

[00:38:09] Angie Jones: so companies

[00:38:09] Angie Jones: are sponsoring

[00:38:10] Angie Jones: that,

[00:38:11] Angie Jones: which

[00:38:11] Angie Jones: means

[00:38:13] Angie Jones: that

[00:38:13] Angie Jones: those people

[00:38:14] Angie Jones: are overbooked.

[00:38:15] Angie Jones: right?

[00:38:16] Angie Jones: And

[00:38:16] Angie Jones: so

[00:38:16] Angie Jones: they

[00:38:16] Angie Jones: don’t, like

[00:38:17] Angie Jones: someone

[00:38:17] Angie Jones: asked

[00:38:18] Angie Jones: for

[00:38:18] Angie Jones: my

[00:38:18] Angie Jones: slides. It’s like

[00:38:19] Angie Jones: I

[00:38:19] Angie Jones: got five

[00:38:20] Angie Jones: conferences

[00:38:20] Angie Jones: before

[00:38:21] Angie Jones: I get to your conference.

[00:38:22] Angie Jones: Like,

[00:38:22] Angie Jones: I

[00:38:22] Angie Jones: do not have,

[00:38:23] Angie Jones: You’re,

[00:38:24] Angie Jones: I

[00:38:24] Jason: can’t

[00:38:24] Jason: think your

[00:38:25] Jason: slides will

[00:38:26] Jason: exist

[00:38:26] Jason: roughly 36 hours before your yeah. phenomenal,

[00:38:29] Angie Jones: promise you that, you know?

[00:38:33] Robbie Wagner: Yeah. Yeah. that’s tough. I do think it is helpful on the flip side, if you’re like speaking at one conference and you haven’t spoken before, you might want those resources. So I

[00:38:41] Jason: Well, why they do it, that’s

[00:38:43] Jason: exactly

[00:38:43] Jason: what it is.

[00:38:44] Jason: And I

[00:38:44] Jason: I, think

[00:38:44] Jason: the part

[00:38:44] Jason: that’s,

[00:38:45] Jason: that’s tricky

[00:38:45] Jason: is like

[00:38:46] Jason: if I’m running

[00:38:47] Jason: the

[00:38:47] Jason: event.

[00:38:48] Jason: I

[00:38:48] Jason: wanna

[00:38:48] Jason: make

[00:38:48] Jason: sure

[00:38:49] Jason: that the speakers

[00:38:49] Jason: are,

[00:38:50] Jason: are ready. I

[00:38:51] Jason: wanna make sure that that,

[00:38:52] Jason: you know, they’re

[00:38:52] Jason: not gonna

[00:38:53] Jason: show

[00:38:53] Jason: up

[00:38:54] Jason: and do something that violates the code of conduct. If they’re

[00:38:56] Jason: just gonna stand up

[00:38:56] Jason: there

[00:38:57] Jason: and like do a 30 minute ad for their company.

[00:38:58] Jason: I want to have a talk with them [00:39:00] beforehand. So I, I know from the, conference organizer’s perspective

[00:39:03] Jason: why

[00:39:04] Jason: every

[00:39:04] Jason: single one

[00:39:05] Jason: of those steps

[00:39:05] Jason: exist. it is no judgment on the conference organizers themselves. and with Angie it’s like, it’s Angie’s job.

[00:39:12] Jason: I

[00:39:12] Jason: don’t get

[00:39:12] Jason: paid

[00:39:13] Jason: to speak.

[00:39:14] Jason: Right? Like I get paid when I work on code TV stuff. So this for me is,

[00:39:18] Jason: is because

[00:39:18] Jason: I really like to speak

[00:39:20] Jason: and

[00:39:20] Jason: there’s

[00:39:20] Jason: networking opportunities, but like,

[00:39:22] Jason: it’s kind

[00:39:22] Jason: of

[00:39:23] Jason: a cost center

[00:39:23] Jason: for

[00:39:24] Robbie Wagner: yeah.

[00:39:24] Jason: Like it’s

[00:39:24] Jason: almost a marketing

[00:39:25] Jason: expense

[00:39:25] Jason: for me. So

[00:39:26] Jason: if you add

[00:39:26] Jason: six hours of

[00:39:27] Jason: meetings,

[00:39:28] Jason: I

[00:39:28] Jason: just

[00:39:28] Jason: can’t, I

[00:39:29] Jason: can’t afford

[00:39:29] Jason: to do it.

[00:39:30] Jason: Right.

[00:39:30] Robbie Wagner: they need speaker pre-check. Like if you’re on the list, you don’t have to do the meetings.

[00:39:34] Robbie Wagner: Oh

[00:39:35] Robbie Wagner: my God,

[00:39:35] Robbie Wagner: that’s a great

[00:39:36] Robbie Wagner: idea.

[00:39:36] Angie Jones: I love that

[00:39:37] Jason: I love

[00:39:37] Angie Jones: idea.

[00:39:37] Jason: a,

[00:39:38] Jason: We

[00:39:38] Jason: should make

[00:39:39] Angie Jones: Yeah, yeah,

[00:39:40] Angie Jones: yeah.

[00:39:40] Angie Jones: yeah.

[00:39:41] Robbie Wagner: Okay,

[00:39:42] Robbie Wagner: I think that’s about all we had. Uh, what would you like to plug or where can people find you, et cetera?

[00:39:47] Angie Jones: yeah,

[00:39:48] Angie Jones: so

[00:39:49] Angie Jones: check me out. , My website is Angie jones.tech.

[00:39:53] Angie Jones: All my social channels are

[00:39:55] Angie Jones: there.

[00:39:55] Angie Jones: I hang

[00:39:56] Angie Jones: out

[00:39:56] Angie Jones: mostly

[00:39:57] Angie Jones: on

[00:39:57] Angie Jones: LinkedIn

[00:39:58] Angie Jones: these days,

[00:39:59] Angie Jones: ,

[00:39:59] Angie Jones: As

[00:39:59] Angie Jones: well

[00:39:59] Angie Jones: as [00:40:00] Twitter.

[00:40:00] Angie Jones: I’m gonna call it Twitter for life.

[00:40:01] Angie Jones: Hmm. cesspool,

[00:40:02] Angie Jones: but

[00:40:02] Angie Jones: hey, you

[00:40:03] Angie Jones: know,

[00:40:03] Angie Jones: um,

[00:40:04] Angie Jones: I can, it, it’s my cesspool. I can I can find some good content there, but yeah,

[00:40:09] Angie Jones: I really highly encourage if you are a software engineer right now, you are, find yourself in the boat that I’m talking about where you’re being kind of pushed to learn how to use these tools effectively.

[00:40:21] Angie Jones: Definitely come outside of your company. There’s so many other people who

[00:40:25] Angie Jones: are doing this.

[00:40:26] Angie Jones: Who

[00:40:27] Angie Jones: are learning out

[00:40:27] Angie Jones: loud and

[00:40:28] Angie Jones: sharing

[00:40:29] Angie Jones: the

[00:40:29] Angie Jones: things

[00:40:29] Angie Jones: that

[00:40:29] Angie Jones: they’re

[00:40:29] Angie Jones: learning. So you wanna

[00:40:31] Angie Jones: kind

[00:40:31] Angie Jones: of

[00:40:31] Angie Jones: tap into the community right

[00:40:33] Angie Jones: now. It’s a good time to do that.

[00:40:35] Robbie Wagner: All

[00:40:35] Robbie Wagner: right. Uh,

[00:40:36] Robbie Wagner: thanks for coming on Angie. Thanks everyone for listening. If you’d like to please subscribe, leave us some ratings and reviews. We appreciate it, and we will catch you next time.

[00:40:43] Outro: You’ve been watching Whiskey Web and Whatnot. Recorded in front of a live studio audience. What the fuck are you talking about, Chuck? Enjoyed the show? Subscribe. You know, people don’t pay attention to these, right? Head to whiskey.fund for [00:41:00] merchant to join our Discord server. I’m serious, it’s like 2% of people who actually click these links. And don’t forget to leave us a five star review and tell your friends about the show. All right, dude, I’m outta here. Still got it.