ppll

Steve Yegge

Programmer and essayist who has worked at Amazon, Google, Grab and Sourcegraph. Best known for the long-form essays collected as Stevey's Drunken Blog Rants and Stevey's Blog Rants.

Steve Yegge did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake

SiteBlog
Follow

What they believe

The bold line is korrents’ wording; the quote is theirs. These 2: what they wrote before what they said aloud, one per source, newest first.

All 29 beliefs, on korrents

Feed

As its own page →

Everything, newest first — across every channel.

Sources

11 March

Steve YeggeKorrents

From one piece From IDEs to AI Agents with Steve Yegge 15 beliefs · youtube.com

+ 12 more

15 April 2010

Steve YeggeRecommends
+ 7 more

13 December 2004

The whole feed →

Beliefs

  • Korrents What they believe 29 beliefs — each backed by an exact quote.

    Each is a — compiled by korrents.com, not by them: the one-line wordings are korrents', the quotes are theirs.

    Recent

    • An excellent engineer who still reads the agent's diffs carefully before checking them in is going to get fired.
      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."

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Deep compiler knowledge is still interesting, but it is no longer useful to a working engineer in any meaningful sense.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

      compilers

    • A company must cut half its engineers to pay for the other half's tokens, and that is what the layoffs are actually about.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    Show 26 more
    • Big companies will lose about half of their engineers, because that is where everybody is setting the dial.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • The engineers laid off in AI's name will mostly not find jobs again, they are the first of many, and nobody has a plan for them.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Groups of two to thirty people will produce output that rivals what the big companies produce.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Being anti-AI in 2026 is like being anti-the-sun: the people who stay that way will have to go live underground.
      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?

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Token burn is the single most important proxy metric a company can watch today, because it measures whether people are trying at all.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Coding agents demand more reading than most people can do, and until better interfaces arrive that leaves those people at a severe disadvantage.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

      coding agents

    • By the end of 2026 most people will be programming by talking to a face on the screen.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Orchestration was the obvious next step, because chat is completions in a loop and agents are chat in a loop.
      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?

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • A company on a monolith cannot use AI on it: no model in the next eighteen months will hold that codebase, so the monolith has to be broken up or rewritten.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Agents can build about half a million lines before the codebase dissolves into a mess, and the next model will push that to a few million.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

      Anthropic

    • AI has a vampiric effect on the people using it: it excites them into working past their own ragged edge.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

      vibe coding

    • If a hundred-times-more-productive engineer still works eight hours a day, the company captures all of the new value and the engineer none of it.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Google has produced no innovation since 2008; everything it has shipped since has been acquisitions.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

      Googleinnovation

    • The big companies are already dead and simply do not know it yet; every innovation from here comes from the fringes.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

      innovation

    • AI's business results are lagging because organisations have a low tolerance for non-determinism, not because the models are not good enough.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Bigger is smarter, always: bringing your special domain knowledge to the model is the wrong side of the bitter lesson.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • The scaling curve really is S-shaped, but there are at least two cycles left in it, which means models sixteen times smarter and all knowledge work subsumed.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Nobody will believe a resume any more; what will count is visible proof of the work you actually did.
      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

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • A company that handed its engineers Copilot and thinks it is now moving faster will be destroyed by the people using frontier models.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

      Microsoft

    • A vibe-coded codebase grows heresies: wrong ideas that take root among the agents, keep coming back, and are very hard to weed out.
      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?

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

      vibe coding

    • Language choice is a temporary artefact of training data; in the fullness of time every language will work equally well with AI.
      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.

      From IDEs to AI Agents with Steve Yegge Said 11 Mar 2026

      Full record — everyone who holds this →

    • Google accepts a high false-negative rate in interviews, turning away qualified people, because that is considered better than sometimes hiring unqualified ones.
      The thing is, Google has a well-known false negative rate, which means we sometimes turn away qualified people, because that's considered better than sometimes hiring unqualified people.

      Get that job at Google Said 12 Mar 2008

      Full record — everyone who holds this →

      Googlehiring

    • Interview false negatives seem completely random and unrelated to a candidate's skills or qualifications.
      As far as anyone I know can tell, false negatives are completely random, and are unrelated to your skills or qualifications.

      Get that job at Google Said 12 Mar 2008

      Full record — everyone who holds this →

    • Studying a data-structures and algorithms book is the preparation most likely to help in a Google interview, because it trains you to recognise the class of problem being asked.
      1) Study a data-structures and algorithms book. Why? Because it is the most likely to help you beef up on problem identification.

      Get that job at Google Said 12 Mar 2008

      Full record — everyone who holds this →

      Google

    • Hashtables are arguably the single most important data structure, and a candidate absolutely has to know how they work.
      Hashtables: hashtables are arguably the single most important data structure known to mankind. You absolutely have to know how they work.

      Get that job at Google Said 12 Mar 2008

      Full record — everyone who holds this →

    All 29 beliefs →

What is a korrent?

A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.

Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.

Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.

Recommends rcmnd

Where they publish

About the English under a post

Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.

The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.

Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.