korrents

korrents · The Pragmatic Engineer Podcast

Building OpenCode with Dax Raad

Dax Raad · 1h 21m · youtube.com ↗

24 korrents from this recording

1h
Dax Raad did not write this page.

Every claim below is a statement made in this recording, quoted word for word and linked to the second it was said, so you can hear it rather than take our word for it. The wording comes from the transcript published alongside the recording; the sentence above each quote is our reading of the claim, not their wording.

  1. 0:04:58 · watch on youtube.com↗

    Our reading

    Before product-market fit, coding faster does not help: it is better to think a lot than to swing a lot, and AI does not speed up the thinking.

    Their wordsBut I've always thought it's better to think a lot instead of swinging a lot. I think you could you can eliminate a lot of ideas or directions just by, you know, spending a lot of time in your head and with your team talking. Um, obviously AI doesn't speed that part up.
    Interesting
  2. 1 min later

  3. 0:05:41 · watch on youtube.com↗

    Our reading

    Answering every problem, competitor and user request with one more shipped feature does not add up to a good product; it adds up to a horrible one.

    Their wordsIf you add that up, you think, "Oh, we shipped a thousand features. Now that adds it to a good product." It actually adds it to a horrible product.
    Interesting

  5. 0:05:52 · watch on youtube.com↗

    Our reading

    Shipping ten times as much is not an advantage, because the moment you ship something you are stuck supporting it forever and every later feature has to interact with it.

    Their wordsThe moment you ship something, you're stuck supporting it forever. And by supporting, it means any future feature you build is going to like interact with it. So you still have to be very conservative with what you put out there. It's hard to undo anything. Just cuz we can ship 10 times more doesn't mean we have 10 times as many good ideas to ship out there.
    Interesting
  6. 1 min later

  7. 0:06:44 · watch on youtube.com↗

    Our reading

    Nobody in the coding-agent market is using AI so much better than everyone else that their competitors cannot keep up — the gap you would expect to see simply is not there.

    Their wordsnone of our competitors are crushing us either. Like no one out there is using AI so well that they just like we can't even compete, right? Um, and we're in the coding agent space. All our competitors are super into AI. So you would think in our space there would be like uh a huge gap, but there there just isn't.
    Interesting
  8. 12 min later

  9. 0:18:32 · watch on youtube.com↗

    Our reading

    In every developer-tool category — databases, compilers, whatever — the open source option eventually becomes the default option.

    Their wordsevery single dev tool we use whether it's databases, compilers, whatever eventually the open source option becomes a default option, right?
    Interesting
  10. 7 min later

  11. 0:25:18 · watch on youtube.com↗

    Our reading

    A small company's most reliable play is to pick one temporary bad guy and galvanise all of their competitors into pushing something forward against them.

    Their wordsthe strategy that we know how to play really well is to pick one temporary bad guy and then galvanize all their competitors to push something forward against them.
    Interesting
  12. 1 min later

  13. 0:26:29 · watch on youtube.com↗

    Our reading

    Get the positioning right and the world keeps handing you wins you never predicted, because well-funded rivals will all use a neutral party to advance their own interests.

    Their wordsIf you get your positioning right, the world just keeps handing you wins that you didn't even expect. So like we never predicted this exact scenario but like our fundamental understanding of the position was right. like if if there is a neutral party, all these companies with billions of dollars will kind of use a neutral party to advance their own like company's interests.
    Interesting
  14. 2 min later

  15. 0:28:19 · watch on youtube.com↗

    Our reading

    Developer tools are consumer products, and the reason there are gaps to win is that programmers are horrible at consumer products and do not know it.

    Their wordsThe the biggest advantage to in DevTools is the fact that everyone working at DevTools is a programmer and programmers are horrible at B2C products. They don't realize DevTools are B2C products.
    Interesting
  16. 2 min later

  17. 0:29:59 · watch on youtube.com↗

    Our reading

    The winning move in coding agents was inverted: take share with a merely good-enough harness first, then go back and make the harness smart.

    Their wordsAnd our harness wasn't very good for like the first like five months of open code. But it was good enough. It was good enough that most people couldn't really tell a difference. And once we won enough share, then we went back and like tried to make our harness like good and smart and optimize and all those things. But uh it was inverted from what everybody else was doing. Everybody else was being like you have to build the smartest harness and that's how you win.
    Interesting
  18. 8 min later

  19. 0:37:30 · watch on youtube.com↗

    Our reading

    Inference is a high-margin business even for a middleman: renting GPUs at scale, some models carry an eighty per cent margin over their sticker price.

    Their wordscuz because we rent GPUs at scale to run the models and we still use middleman by the way. So we're not like going all the way down to the down to the floor. Even for us there are some models the sticker price and the cost to us there's like an 80% margin in there.
    Interesting
  20. 1 min later

  21. 0:38:55 · watch on youtube.com↗

    Our reading

    Every hyped business attracts negative sentiment nobody has an incentive to correct — and inference makes sense as a business long-term, whatever the training costs are.

    Their wordsThere's always negative sentiment that exists for any business that's getting hyped. They have no incentive to correct it. Um so again it's complicated because I know the training costs are a big part of it. Uh the R&D department is is hugely expensive but long-term inference makes sense as a business and I think it it always will.
    Interesting
  22. 1 min later

  23. 0:39:33 · watch on youtube.com↗

    Our reading

    Demand for inference may be growing exponentially while GPU production can only grow linearly, and the tightening happens where those two lines cross.

    Their wordsThe demand for inference is growing. So, like I don't think it's linearly growing. I think it might even be exponentially growing. But we haven't made our production of GPUs grow exponentially. That's like kind of a linear process. So as those lines intersect, there's going to be uh tightening.
    Interesting
  24. 2 min later

  25. 0:41:54 · watch on youtube.com↗

    Our reading

    Give an ordinary employee a button that does their work faster and they will do the same amount of work and keep the time — which makes complete sense.

    Their wordsYou give them a button that lets them do their work faster. The natural place for them to do is hit that button as much as possible, do the same amount of work, and just cash in that extra time, right? Which makes total sense.
    Interesting
  26. 4 min later

  27. 0:45:34 · watch on youtube.com↗

    Our reading

    AI moved him from spending 95 per cent of his energy on deciding what to do to spending 96 per cent — a 20 per cent improvement that feels like no change at all.

    Their wordsthe joke I made was pre AI, I would spend 95% of my energy thinking about what to do and 5% of my energy doing it. Now I spend 96% of my time thinking about what to do and 4% of my time actually doing it. So yeah, it's like a 20% improvement, but dayto-day it feels as hard as ever.
    Interesting
  28. 2 min later

  29. 0:47:15 · watch on youtube.com↗

    Our reading

    There is a world where AI coding tools change nothing except that engineers are happier, and for a lot of companies that is not good enough to keep paying for.

    Their wordsthere is a world where the net result of all these AI coding tools is the same amount of work gets done, but all the engineers are happier because their job is easier. That's not good enough for a lot of companies. So, they're just going to say go back to typing out the code.
    Interesting
  30. 3 min later

  31. 0:50:18 · watch on youtube.com↗

    Our reading

    The judgement call about whether to absorb a hack is distorted right now, because the agent will simply do the hacky thing and deal with the consequences for you.

    Their wordsThat judgment, that ability to have that judgment is so distorted right now because the agent will just do the hacky thing for you. The agent will kind of deal with the hacky problems that come down the road. And it's way easier just to be like, "Oh yeah, it's a temporary fix."
    Interesting
  32. 1 min later

  33. 0:51:39 · watch on youtube.com↗

    Our reading

    The prickle you used to feel writing a hack is muted now, so the landmines are still there but the feedback loop that kept your judgement honest is gone.

    Their wordsThat prickle that feeling that you get, it's like muted now cuz someone else it's kind of like you've made someone else deal with the problem. The problem is still there and the the landmines are still going to blow up on you eventually, but like you're not you don't feel that bad feeling as much anymore. So your judgment is skewed. You're not getting that feedback loop.
    Interesting
  34. 5 min later

  35. 0:56:36 · watch on youtube.com↗

    Our reading

    Almost every confident prediction about AI is a defence mechanism: people asserting a future in which they personally turn out to be the winner.

    Their wordsIt's like everyone is just saying mantras to themselves cuz the root thing that's going on here is we are experiencing a moment of great change. Everyone is very nervous about what that means for their own position in it. a defense mechanism is to confidently assert a future in which you're a winner. And that's almost what every single prediction that you see is happening.
    Interesting
  36. 3 min later

  37. 0:59:23 · watch on youtube.com↗

    Our reading

    You probably only have one good idea in your whole product, and the job is getting the user to experience it as fast as possible.

    Their wordsYou probably only have one good idea in your whole product. Get the user to experience that as fast as possible. Well, it sounds so easy, but if you go try every single product out there, you will see a million accidental steps they introduced from the user hearing about your product to like seeing the value in it.
    Interesting
  38. 1 min later

  39. 1:00:00 · watch on youtube.com↗

    Our reading

    The job of product is not to ship the immediate solution to a problem but to absorb all the problems and find the one solution that fixes fifty of them.

    Their wordsThe job of product isn't to just receive a problem and ship the immediate solution. It's to absorb all the problems and understand that there's one solution you can ship to fix 50 different problems.
    Interesting
  40. 10 min later

  41. 1:09:45 · watch on youtube.com↗

    Our reading

    Quality comes from doing irrational things — half of what you do you did not have to do — and almost nobody is willing to operate that way.

    Their wordsI still believe quality is a huge differentiator. It's not just something you can decide to do. I think it needs to show up every single aspect of your company from like you have to do things that are irrational. I think that's kind of what quality comes from. like you do a bunch of things and like 50% of those things you you didn't have to do and I think very few people are willing to operate that way.
    Interesting
  42. 4 min later

  43. 1:13:58 · watch on youtube.com↗

    Our reading

    Redefining the engineer's job as building guardrails is not novel — it is the same problem as making a junior engineer effective, which we never solved either.

    Their wordsThe thing that I find interesting is that's not novel. This has been the thing we've always been trying to do forever. How do we get a junior engineer to ship code safely without breaking stuff? Right? How do we make patterns in the codebase? How do we make tests? Like it's it's all the old stuff that we've always wanted to do.
    Interesting
  44. 1 min later

  45. 1:14:53 · watch on youtube.com↗

    Our reading

    The verbose enterprise patterns everyone hated are worth having again: coding agents are idiots working around the clock, and you are not the one typing the boilerplate any more.

    Their wordsWe're now doing it in a much heavier way because we find that these like kind of bory enterprisey uh patterns end up being pretty useful because you have a bunch of idiots on your team now. The coding agents are a bunch of idiots and they are going to work 24/7 and they're going to like ship a lot of stuff. So you need way more guardrails than you used to.
    Interesting
  46. 2 min later

  47. 1:16:44 · watch on youtube.com↗

    Our reading

    Being a decent software engineer plus a genuine expert in one industry is a deadly combination, and engineers are the only people who get to change industries at will.

    Their wordsBut you if you also become an expert in a specific industry, that's like a deadly combo. Um if you are like just pick any industry, let's say let's say farming, let's say you understand that farming industry really well and you're also a decent software engineer, you're probably like the top 10 people in the world for that combination that the whole industry will want to hire.
    Interesting