Skip to content
a16za16z

How Jev Turns AI Into Software That Gets Things Done

a16z’s Ben Horowitz and Martin Casado sit down with TypeSafe AI founder Diogo Almeida to ask a simple question: AI has become remarkably capable, so where is all the automation? Diogo argues that coding agents may help us write software faster, but the software they produce still largely works the way software always has. TypeSafe is taking a different approach with Jev: putting intelligence inside software itself, so developers can build programs that reason about intent and make probabilistic decisions rather than simply generate text for a human to interpret. They discuss why reliability is the key to making AI genuinely programmable, how this could open a new era of probabilistic software, and why established SaaS companies may be particularly well positioned to benefit. Ultimately, Diogo’s goal is straightforward: technology that can reliably “do what I mean.” Timestamps: 00:00 - Intro 00:50 - Meet Diogo and Type Safe 04:07 - Smart software, not just faster code 15:46 - Where's all the automation? 22:00 - Is it just a data problem? 30:21 - SaaS apocalypse, reversed 34:58 - New capabilities, not more code 38:27 - Apps vs the guts of systems 41:08 - Reliability and "do what I mean" Resources: Follow Diogo Almeida: https://x.com/CompleteSkeptic Learn more about TypeSafe AI: https://typesafe.ai/ Follow TypeSafe AI: https://x.com/typesafeai Follow Ben Horowitz on X: https://x.com/bhorowitz Follow Martin Casado on X: https://x.com/martin_casado Stay Updated: If you enjoyed this episode, be sure to like, subscribe, and share with your friends! Find a16z on X: https://twitter.com/a16z Find a16z on LinkedIn: https://www.linkedin.com/company/a16z Listen to the a16z Show on Spotify: https://open.spotify.com/show/5bC65RDvs3oxnLyqqvkUYX Listen to the a16z Show on Apple Podcasts: https://podcasts.apple.com/us/podcast/a16z-podcast/id842818711 Follow our host: https://x.com/eriktorenberg Please note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see http://a16z.com/disclosures.

Diogo AlmeidaguestMartin CasadohostBen Horowitzhost
Sep 28, 202642mWatch on YouTube ↗

EVERY SPOKEN WORD

  1. 0:00 – 0:50

    Intro

    1. DA

      Where the fuck is all the automation?

    2. MC

      Yeah.

    3. DA

      AI is so unbelievably smart, and yet it's so useless at all other stuff.

    4. MC

      It doesn't matter how much AI coding agents you use, the software actually isn't getting better. [laughs]

    5. DA

      [laughs]

    6. MC

      Maybe you're writing it faster. It's like-

    7. DA

      Yes

    8. MC

      ... arguably getting worse.

    9. DA

      OpenAI has been trying to automate customer service since 2020. What I want instead is smart software. I want to expand what software itself can do, such that things that should be automatable can then be automatable.

    10. BH

      My favorite thing that you guys say is, "We build prod, not God."

    11. MC

      [laughs] So good.

    12. BH

      Because if we had any other kind of, like, big lab leader, even if they had joy, they would cover it up. [laughs]

    13. MC

      [laughs]

    14. BH

      And then your view is so different. You're like, "No, we're gonna create a way better world."

    15. DA

      For nuanced reasons, I don't think we are on the path of RSI. In the SaaSpocalypse story, um-

  2. 0:50 – 4:07

    Meet Diogo and Type Safe

    1. BH

      Today-

    2. DA

      [laughs]

    3. BH

      ... we have the founder and leader of TypeSafe, Diogo, with us, um, who, uh, is a bit of a hero to both Martin and me.

    4. MC

      Yes.

    5. BH

      Um-

    6. MC

      Yes

    7. BH

      ... he is not only building, like, a really interesting product, uh, but creating what we think is a very important movement. So we're super excited about today. Welcome, Diogo.

    8. MC

      Thanks for coming. Yeah.

    9. DA

      Thank you.

    10. BH

      Yeah. And, uh, maybe you can give us kind of a, a brief on, um, just, you know, what is Jev? What is TypeSafe? Why is it important?

    11. DA

      Is this, uh, curse-friendly or no?

    12. BH

      Yeah. Yeah, yeah.

    13. MC

      Oh.

    14. DA

      Oh, okay. Cool.

    15. BH

      What the fuck are you talking about? [laughs]

    16. DA

      Oh, okay, okay, okay, cool. So I was actually asked-

    17. MC

      Anything else, and yeah, yeah

    18. DA

      ... uh, for, like, a elevator pitch, which I tend to ramble on, and I don't do well. But, like, I realized my favorite e- elevator pitch for Jev is-

    19. MC

      Oh, yeah

    20. DA

      ... where the fuck is all the automation?

    21. MC

      [laughs]

    22. DA

      Like, this is, like, so-

    23. MC

      Oh

    24. DA

      ... unbelievably tragic.

    25. MC

      Yes.

    26. DA

      You know? So much intelligence.

    27. MC

      Yeah.

    28. DA

      AI is so unbelievably smart, and yet so... I, I... Not that I hate on chatbots or coding agents. I love them myself, but it's like th- it's so useless at all other stuff, and it's, it's tragic. It's tragic-

    29. MC

      Yes

    30. DA

      ... so that, you know, we have so much, like, diamond in the rough, but not polished for work. That's, that's... But TypeSafe is making AI for software. You know-

  3. 4:07 – 15:46

    Smart software, not just faster code

    1. BH

      uh, somewhat replaces a software engineer with a faster, maybe not even as good software engineer, what you're saying is, "No, no, no, we're gonna super empower the software engineers we have to write way, way better, more interesting things."

    2. MC

      Yeah. I, I actually-

    3. BH

      Yeah.

    4. MC

      I mean, yeah, yeah. So this is s- by the way, I, I just think so many people miss this point, and it's such-

    5. BH

      Yeah

    6. MC

      ... a subtle point, and it's so important to actually tease it out, which is, um, if you use something like Cloud Code or Codex, which is great, or Cursor, which is great-

    7. DA

      [laughs]

    8. BH

      Yeah

    9. MC

      ... they write code, but that code is the same thing a human being would have write. Maybe it's better, maybe it's worse, but it's basically still code, just like code looked 10 years ago.

    10. DA

      Yeah.

    11. BH

      Yeah.

    12. MC

      A- and the thing with Jev is whether or not you're Cloud Code or a human, you have this new primitive, this new thing that you stick in your code that actually expands, like, the power of software. So instead of, like, writing code, it is something that you include in your code.

    13. DA

      Hmm.

    14. MC

      Which-

    15. DA

      Go ahead. No, no, you go ahead. Go ahead

    16. MC

      ... no, no, you go ahead. Well, one, two, which by the way is interesting because it's this very powerful primitive, which would be great if you explain, but it's also a little bit different than, like, you know, how programmers think. For example, like, it has this notion of, like, you know, probabilities or, you know... And, like, so, you know, so maybe-

    17. BH

      Oh, so an intelligent layer inside the software.

    18. MC

      Yeah, think of, like, like a libr- yeah, like a library that you can, like, use natural language to describe what you want, and then you give it kind of a state machine, and then it will, will choose what to do with some confidence levels, which we kind of haven't really had before-

    19. DA

      Yeah. Yeah

    20. MC

      ... like, so ubiquitous. So maybe...

    21. DA

      Ooh, there's a lot of tricks there. I will-

    22. MC

      [laughs]

    23. DA

      ... jump into one thing first, which is-

    24. MC

      Yeah

    25. DA

      ... I love the first thing you said. Like, you know, in the direction of where the fuck is all the automation.

    26. MC

      Yeah.

    27. DA

      I love software so much.

    28. MC

      It's the best.

    29. DA

      I wish I could be writing it all day.

    30. MC

      Yes. [laughs]

  4. 15:46 – 22:00

    Where's all the automation?

    1. BH

      But y-

    2. DA

      Yeah

    3. BH

      ... you know, it, it's a kind of a, it's a very tip of the iceberg of the things that are horrible things to do that, that we need to automate.

    4. DA

      I think that if we were going to be really intellectually honest, and we are really aiming for the North Star of automation, we cannot fall into the same anti-patterns that AI has fallen into, which is really, um, focusing on outliers and demos.

    5. BH

      Hmm.

    6. DA

      Right? Like, a lot of people ask me, like, "What are your favorite use cases?" And I'm like, "I'm not sure if they work." I want them to work in the background-

    7. BH

      [laughs]

    8. DA

      ... such that, like-

    9. BH

      Yeah

    10. DA

      ... someone would trust that to run and not page them, and, like, people can build on top of that too. And, like-

    11. BH

      Uh, composable. Composable AI.

    12. DA

      Composable, but, like, other things, like-

    13. BH

      Yeah

    14. DA

      ... safe, right?

    15. BH

      Mm-hmm.

    16. DA

      Like, it's a different type of safety where, like, i- if you want it to actually, like, run with resources associated with it, with access-

    17. BH

      Mm-hmm

    18. DA

      ... to things, you need guarantees for that, or, like, at least statistical guarantees.

    19. BH

      [laughs]

    20. DA

      And, um, like-

    21. BH

      So it doesn't go rogue, break and enter-

    22. DA

      [laughs]

    23. BH

      ... face, that type of thing.

    24. DA

      Well, I, I, I don't think our models will be doing that-

    25. BH

      Yes

    26. DA

      ... anytime soon-

    27. BH

      Yes

    28. DA

      ... unless someone, like, does the software to do that, which would be g-

    29. BH

      Their fault, yeah

    30. DA

      ... a very cool flex. Very cool flex.

  5. 22:00 – 30:21

    Is it just a data problem?

    1. MC

      the, the, the real, the distribution of the real world is, is, is different than the digital world, right? It's heavy tailed. There's a lot of exceptions. We don't have all the data. And I mean, it, couldn't it be the case that the reason we're not doing productive stuff in the real world is just like we're not, we don't have the data for that distribution. We're not training on that distribution, and this is why it's just been basically relegated to like these lower dimensional manifolds, like whatever math or code or...

    2. DA

      Um, I don't entirely buy the data argument, in my opinion. Um, I do believe that there's a, a long tail, for sure, like that would be kind of crazy-

    3. MC

      Yeah

    4. DA

      ... to deny. And I don't think that in my like canary in the coal mine situation, we need to automate that long tail. Like I think that-

    5. MC

      I see. Okay

    6. DA

      ... I think we need to be incredibly pragmatic on everything, and like building reliable software is always an investment.

    7. MC

      Yeah.

    8. DA

      Right? Like it, like, you know, what are the three great virtues of a programmer? Laziness to not to do it again, hubris, and [inhales] there was a third one.

    9. MC

      Oh, yeah. No, yeah, no, I remember. This is from the Pearl days.

    10. DA

      Yeah.

    11. MC

      Yeah, yeah.

    12. DA

      Yeah. There, there was a third one.

    13. MC

      Larry Wall, yeah.

    14. DA

      I, I wish, I wish I could remember it.

    15. MC

      Yeah, yeah.

    16. DA

      But like it's about like the laziness to like spend [chuckles] you know, like ten hours to do like the five-minute task instantly and to never have to do it again. Like, it only make, like it should be an ROI decision for people who like automate stuff. Like, I would just like it to be automatable.

    17. MC

      Yeah.

    18. DA

      And I think that people will just make n-like new kinds of work, he-hence the Jev in Jevens.

    19. MC

      Yeah.

    20. DA

      New kinds of work once that stuff is doable. But, uh, like, as like a, a benchmark, I feel like it's useful to see can we actually automate the stuff that it really, really looks like AI should be able to automate.

    21. MC

      I see.

    22. DA

      OpenAI has been trying to automate customer service since 2020.

    23. MC

      Yeah.

    24. DA

      You know, like, and it, it, it's, you know, like it's not. [laughs]

    25. MC

      Which is pretty amazing.

    26. DA

      [laughs] It, it's, it's wild, you know? It's wild.

    27. MC

      Well, and then inside, I mean, inside companies, um, there's very little that's automated right now.

    28. DA

      Yeah.

    29. MC

      Like, a-a-and the projects haven't worked. Um-

    30. DA

      Yeah

  6. 30:21 – 34:58

    SaaS apocalypse, reversed

    1. DA

      I, I don't know what else to say, right?

    2. BH

      Yeah.

    3. DA

      Like, I, I think it's, like, quite natural.

    4. BH

      Mm-hmm.

    5. DA

      Like, in the SaaSpocalypse story-

    6. BH

      Mm

    7. DA

      ... um, the, the story that I feel like has panned out really poorly is that software is very cheap and perhaps easy to replicate, which-

    8. BH

      Mm-hmm

    9. DA

      ... I think I could, I could believe the former, I could not believe the latter because a lot of the stuff happens beneath the hood.

    10. BH

      Totally.

    11. DA

      Um, I'm maybe overly a software fanboy here. Um-

    12. BH

      Yeah, all of us. [laughs]

    13. DA

      Yeah. Okay, okay, okay. Um, I didn't know where you-

    14. BH

      Yeah

    15. DA

      ... might be in the coding agent fanboy-

    16. BH

      We, we have a lot of legacy around that.

    17. DA

      Yeah.

    18. BH

      100%, yeah.

    19. DA

      Yeah. So it, I don't think that really panned out, so SaaS seems like maybe the markets don't agree.

    20. BH

      Mm.

    21. DA

      But, like, I think SaaS is providing the same value it used to. Maybe the markets are just scared.

    22. BH

      Mm.

    23. DA

      Um, but I think that SaaS will be one of the largest winners of, like, the whole AI game.

    24. BH

      Mm-hmm.

    25. DA

      And I want to, like, work really, really well with, like, all the biggest, most boring, most, like, in the know of user problem-

    26. BH

      Mm-hmm

    27. DA

      ... SaaS companies because I think that they are the best positioned to know what workflows to automate, what do people need. Like, that's what-

    28. BH

      Mm

    29. DA

      ... what their bread and butter is, and to spend the big... Like, you know, software is always a CapEx investment.

    30. BH

      Mm.

  7. 34:58 – 38:27

    New capabilities, not more code

    1. DA

      If people take that as a takeaway, that would be, like, the greatest compliment ever to what we are doing.

    2. BH

      Yeah.

    3. DA

      Like, I actually feel like it's almost too grand of a vision to expand beyond the three logic gates that we have-

    4. BH

      Yeah, yeah

    5. DA

      ... into, like... You know, it, our types are kind of like one s- of the same logic gate, but, like, one that's, like, a little brain in there.

    6. BH

      Yeah.

    7. DA

      Like, that would be the greatest compliment-

    8. BH

      Yeah

    9. DA

      ... to, like, the, the, the type safe legacy, 'cause, like, that is t- that's a very-

    10. BH

      Huge

    11. DA

      ... non-trivial, huge thing for the world. Um, I'm not gonna, like, overpromise, underdeliver that, but I will fight for that.

    12. MC

      Yeah, I mean, listen, I mean, there's, I think pretty open questions to what, like how deep can this get as far as, like, like, really serious stuff, like state consistency or durability or, like, real systems level stuff where you actually need to, like, provide strong guarantees. And so 100% this will change-

    13. DA

      Mm-hmm

    14. MC

      ... things like whatever, analyzing logs, analyzing emails, providing a UI, talking to the human. Like, that for sure, but, like, you know, you could argue that over time this becomes, like, a smart database.

    15. DA

      Yep, yep.

    16. MC

      Like, you know, and so-

    17. DA

      And, and also-

    18. BH

      Air traffic control system.

    19. MC

      Uh, anything, right?

    20. BH

      Which we really need. [laughs]

    21. MC

      True, true.

    22. DA

      A little scary.

    23. BH

      Yeah.

    24. DA

      Like, I think automate the easy work before the hard work is always my philosophy.

    25. MC

      Yeah, yeah.

    26. BH

      Yes.

    27. DA

      But I also think there's going to be, like, an entire era of probabilistic programming that's opened up. Like, my-

    28. MC

      By the way, you know there's a huge history of probabilistic programming-

    29. DA

      Oh, I do

    30. MC

      ... that basically died in, like, the '70s, right? [laughs]

  8. 38:27 – 41:08

    Apps vs the guts of systems

    1. MC

      more in terms of like systems, foundations, or all the above?

    2. DA

      For what I would think of or how-

    3. MC

      Yeah, just general application for this. When you think about like, like you're working on Jev and like, and you kind of envision the people are adapting it, like how, how, you know, like do, do, or maybe do you even have an opinion?

    4. DA

      I have a little bit, and it's... So the way I think of it is a little like, uh, like deep into like the TCP guts. You know, like UDP, TCP, you know, like it's unreliable, it's unreliable.

    5. MC

      You're speaking, speaking my language. [laughs]

    6. DA

      Exactly. And, and like I, I, so like when I think of AI-

    7. MC

      Feel comfortable

    8. DA

      ... no, no, I mean, like when I think of AI, and this is why I care about intelligence per dollar, to be clear.

    9. MC

      Yeah.

    10. DA

      When I think... And, and how I got to this conclusion is I work backwards from AI-based economic revolution, AI everywhere, you know, sci-fi and everything, like all the software has AI all over the place. And I ask myself the question, what percentage of the calls to AI, imagine it's like a function-

    11. MC

      Mm-hmm

    12. DA

      ... which, uh, what percentage are like for human consumption, where you need like style and everything?

    13. MC

      Versus understanding.

    14. DA

      And, and, yeah.

    15. MC

      Mm-hmm.

    16. DA

      And it's gonna be like many nines, and actually from that same question, how many will be at the first layer-

    17. MC

      Yeah

    18. DA

      ... versus like deep in the guts?

    19. MC

      Yeah.

    20. DA

      Right? And I think that it's going to be many nines in the guts, but it will start at the first layer. But like we need to, if you don't aim for the guts... [chuckles] Wait, that sounds weird.

    21. MC

      [laughs]

    22. DA

      If you don't aim for the guts, you, you, it's, it's, it's going to take you a while to get there.

    23. MC

      Yeah.

    24. DA

      Right?

    25. MC

      I, I think people don't understand to what extent like AI was kind of ships in the night with software. Like even if you try to embed AI in software, it kind of like didn't behave, right? Because software doesn't really take natural languages, and you like do all this weird stuff. Like you stick in the prompt like, "Here's the JSON output that you want, and here's a schema," and it would never listen to it.

    26. DA

      Yeah.

    27. MC

      And so, and so what you ended up doing is just taking the output and giving it to a human. You're like, "To hell with it," right? It's like-

    28. DA

      Yes, or another LLM. That is what a while loop is, like the-

    29. MC

      Yeah, ex-

    30. DA

      ... agent while loop, right?

  9. 41:08 – 42:13

    Reliability and "do what I mean"

    1. DA

      really, really care about reliability. We could have released so much sooner. I don't think people realize that, and I don't think that, honestly, I don't think that they will. I, uh, based on what I see of the Twitter discussion-

    2. MC

      Yeah. [laughs]

    3. DA

      ... I think people will never get it, but like it'll just have like that good vibe of like, "Oh, I can trust this."

    4. MC

      Yeah.

    5. DA

      So-

    6. MC

      Well, it's the anti-frustration machine, yeah.

    7. DA

      [laughs]

    8. MC

      Yeah.

    9. DA

      It's, it's a... I hope so. I hope, do what I mean, right?

    10. MC

      Yes.

    11. DA

      Like to me, that is about like smoothness in the world, like having everything like just move more smoothly together and interlink like gears.

    12. MC

      Yeah.

    13. DA

      I actually have my whole like AI utopia on like different axes that I really, really want, and like do what I mean is a huge part of this.

    14. MC

      Yeah.

    15. DA

      You know, like imagine if all technology just did what you mean.

    16. MC

      Yeah.

    17. DA

      That is, like that's not sci-fi. Look how smart AI is, right?

    18. MC

      Yeah. No, it's, uh, it's amazing. And, and maybe that's the thought to close on.

    19. DA

      Oh.

    20. MC

      Do what I mean.

    21. DA

      [laughs] Yeah, love it.

    22. MC

      Thank you, Diogo. This has been a great conversation.

    23. DA

      Hell yeah.

    24. MC

      Really enjoyed it.

    25. DA

      So fun.

Episode duration: 42:24

Install uListen for AI-powered chat & search across the full episode — Get Full Transcript

Transcript of episode Ut3LOjKNJaE

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

iOSAndroidClaudeChrome