korrents

Steve Yegge

@steve-yegge · 25 positions · 0 changes of mind

Software engineer of four decades who spent years at Amazon and Google, wrote the Stevey's Blog Rants essays, and co-authored the book Vibe Coding with Gene Kim.

Everything they publish, on ppll ↗

Steve Yegge did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

  1. I had a lot of my own ego and identity wrapped up in my sort of compiler background. It's all It's interesting, right? But it's it's not useful in any meaningful sense anymore.
    spoken · machine transcript hear it at 0:06:38 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 1st of 25 in this recording

  2. I'm mad at Amazon for laying off 16,000 people and blaming AI without an AI strategy for it. Those people are not going to be able to find jobs, by and large, and they're the first of many to come and nobody has a plan for this.
    spoken · machine transcript hear it at 0:18:08 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 2nd of 25 in this recording

  3. Because they're all starting to spend their own salaries in tokens. And so, at least for a while, if you want your engineers to be as productive as possible, you're going to have to get rid of half of them to make the other half maximally productive.
    spoken · machine transcript hear it at 0:18:44 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 3rd of 25 in this recording

  4. And so, what's happening is everybody on average is setting that dial to about 50% and we're going to lose about half the engineers from big companies, which is scary.
    spoken · machine transcript hear it at 0:19:01 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 4th of 25 in this recording

  5. it's also enabling engineers who have seen the light and believe the curves are going to continue to go up to actually get together in groups of two and five and 10 and 20 and 30 people and start to do things that rival the output of these big companies that are tripping over themselves.
    spoken · machine transcript hear it at 0:19:23 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 5th of 25 in this recording

  6. I think a lot of the people coming out of knowledge work are just anti-AI. And those people are going to struggle. I'm sorry, but if you're anti-AI at this point, it's like being anti-the the sun. You're going to have to go live underground, right?
    spoken · machine transcript hear it at 0:20:17 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 6th of 25 in this recording

  7. they they're like, "Yeah, you know, I use Cursor, and I I ask it questions sometimes, and I'm really impressed with the answers, and then I review its code really carefully, and then I check it in." And I'm like, "Dude, you're going to get fired, and you're one of the best engineers I know."
    spoken · machine transcript hear it at 0:22:17 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 7th of 25 in this recording

  8. What probably the single most important proxy metric that you can have it in a company today is token burn. Because what token burn says is your engineers are trying to do stuff or your non-engineers.
    spoken · machine transcript hear it at 0:26:28 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 8th of 25 in this recording

  9. So I think we're in a weird limbo for the rest of this year okay where until the UIs arrive that are good enough for everybody who can't read everybody who can't read is going to be a severe disadvantage.
    spoken · machine transcript hear it at 0:29:11 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 9th of 25 in this recording

    coding agents

  10. I think that by the end of this year and we'll see demos of it like right away, but by the end of this year most people will be programming by talking to a face. A face as in a face on the screen.
    spoken · machine transcript hear it at 0:30:38 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 10th of 25 in this recording

  11. if chat is completions in a loop, basically, and agents are basically chat in a loop, well, then we're going to put we're going to put agents in a loop, and that'll be an orchestrator, right?
    spoken · machine transcript hear it at 0:31:44 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 11th of 25 in this recording

  12. But right now I think it's sitting somewhere between half million and five million lines of code, somewhere in there. Probably more on the half million side right now and with the next drop of an Anthropic model, we're probably going to see it jump up to a few million lines.
    spoken · machine transcript hear it at 0:40:46 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 12th of 25 in this recording

    Anthropic

  13. If you're a monolith, you're kind of hosed because I told you the ceiling's going up for what they can do, but it ain't ever going to hit your monolith. They will never fit in the context window and you're never going to be able to never in the next 18 months be able to tell a model go fix my monolith. You have to break it up.
    spoken · machine transcript hear it at 0:41:29 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 13th of 25 in this recording

  14. There's a vampiric effect happening with AI where it gets you excited and you work really really hard and you're capturing a ton of value. For me, I'm doing it all for myself and it's still kind of like pushing me to my ragged edge.
    spoken · machine transcript hear it at 0:42:05 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 14th of 25 in this recording

  15. let's say an engineer can be 100 times as productive, just just for sake of argument, all right? Who captures that value? If the if the engineer goes to work and works for 8 hours a day and produces 100 times as much, the company captured all of that value.
    spoken · machine transcript hear it at 0:43:16 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 15th of 25 in this recording

  16. You might only get three productive hours out of a person at max vibe coding speed. And yet they're still 100 times as productive as they would have been without AI. So, do you let them work for 3 hours a day? And the answer is yeah, you better.
    spoken · machine transcript hear it at 0:45:41 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 16th of 25 in this recording

    vibe coding

  17. In fact, innovation died on the vine like all together and since I don't know, 2008, there has been no innovation from Google. It's all been acquisitions. They have they've created nothing new.
    spoken · machine transcript hear it at 0:51:51 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 17th of 25 in this recording

    Google

  18. My my feeling is that probably people have a low tolerance for non-determinism. And these things are fundamentally non-deterministic. So, they can't just go replace customer call center software because they they could be wrong.
    spoken · machine transcript hear it at 0:55:33 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 18th of 25 in this recording

  19. So, I think what's happening is we're all looking at the big companies going, "When are you going to give us something?" And the answer is we're looking at the big dead companies. We just don't know they're dead yet.
    spoken · machine transcript hear it at 0:56:54 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 19th of 25 in this recording

  20. Where an idea can take root among the agents that's incorrect. It's It's It's a wrong architecture or or wrong data flow or whatever that's that's causing an impedance mismatch for the rest of your code. And what happens is I call it a heresy because they have the tend They have a tendency to to grow and to come back and they're really hard to weed out, okay?
    spoken · machine transcript hear it at 1:02:59 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 20th of 25 in this recording

    vibe coding

  21. The bitter lesson is don't try to be smarter than the AI, okay? You think that you've got special knowledge. The humans bring special domain knowledge to this problem and we're going to teach it something to AI and it will be smarter. What we found was bigger is smarter. Always.
    spoken · machine transcript hear it at 1:05:02 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 21st of 25 in this recording

  22. But, I can tell you that there are at least two more cycles left in this, and that means they will be at least 16 times smarter than they are today, and that is going to cause all of knowledge work to be subsumed by this stuff.
    spoken · machine transcript hear it at 1:06:57 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 22nd of 25 in this recording

  23. But I'm serious, if you're working at a company that uses that gave you Copilot, they think that they're starting to move faster and there's a barbarian horde of people using Opus 4.5 that are going to destroy your company sooner or later.
    spoken · machine transcript hear it at 1:17:48 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 23rd of 25 in this recording

  24. we are moving into a world very quickly this year where proof of work is so important and I mean proof of work not in the Bitcoin sense but your proof of what you have done, your resume. And I don't mean your resume because nobody's going to believe that. I mean the actual work that you did which has to be visible
    spoken · machine transcript hear it at 1:18:06 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 24th of 25 in this recording

  25. But right now we're in a funny place where the some languages work better than others still because they have better training data, but in the fullness of time, all languages will work equally well.
    spoken · machine transcript hear it at 1:23:19 · all korrents from this recording

    From IDEs to AI Agents with Steve Yeggeyoutube.com 25th of 25 in this recording