korrents

What Dex Horthy thinks about LLMs

@dex-horthy · 26 positions · 0 changes of mind

Founder of the agent company HumanLayer, author of the 12-factor agents principles, and the engineer who put the name "context engineering" on the practice.

Dex Horthy 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.

8 dated positions, 2026, in their own words. Our reading of what Dex Horthy has said — not written or endorsed by them.

  1. Our readingEvery abstraction in agentic programming — RAG, memory, agentic history, structured output — is just a different way of passing tokens into a model, and understanding that beats learning any of them.

    Their wordsAnd at the end of the day, they're all like different ways to pass tokens into a model and ask it to produce usually some structured output. And understanding that is a lot more powerful than trying to learn memory and trying to pick some agent framework off the shelf and some memory framework off the shelf.

    ↗Context engineering with Dex Horthyyoutube.com 1st of 26 in this recording

    Interesting

  3. Our readingContext engineering has stayed relevant for a year because it is grounded in how transformer attention works, and it will matter to anyone building on AI until post-transformer models arrive.

    Their wordsI think context engineering has been so long lived because it's it's grounded in the fundamentals of how transformer attention works and until we have post transformer models or linear attention or whatever it is which who knows when that's going to happen context engineering will be interesting and important to anyone building on AI

    ↗Context engineering with Dex Horthyyoutube.com 3rd of 26 in this recording

    Interesting

  5. Our readingA bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.

    Their wordsYou're not actually getting a like smarter model. like the intelligence of the model is is what drives its ability to attend to all of the tokens in the context window to figure out on the next turn which parts of this 100k or 200k context window are the most relevant to making the decision of like what is the next tool we call and doing that over and over again in a loop.

    ↗Context engineering with Dex Horthyyoutube.com 4th of 26 in this recording

    Interesting

  7. Our readingContext has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where conflicting instructions cost the model real computation to ignore.

    Their wordsBut it's also your instruction budget is like if you give the model too many instructions and especially too many conflicting instructions and that's in your initial prompt and also like if you have a conversation you start going down a path and then you change your mind and you start going down a different you actually I don't want to do any of that I want to do this. It's like a it's a lot of computation the model has to do to notice that it has to ignore that whole thing.

    ↗Context engineering with Dex Horthyyoutube.com 5th of 26 in this recording

    Interesting

  9. Our readingThe point of context engineering is to do as much work as possible in the smart zone — roughly the first hundred thousand tokens of the context window.

    Their wordsHow do we control that in such a way that we get the best results possible which means doing as much work as possible in the smart zone the you know first 100,000 tokens of the context window.

    ↗Context engineering with Dex Horthyyoutube.com 20th of 26 in this recording

    Interesting

  11. Our readingWithout good intuition for models, treat 100k tokens on smaller models and 200k on the frontier ones as the line past which the quality of your results is probably already degrading.

    Their wordsBut if you don't have good LLM intuition, like 100K for smaller models, 200K for these like really beefy like Codeex and Opus 4.8 models is usually a good like training wheel guideline of like if you pass there, your quality of results may be degrading.

    ↗Context engineering with Dex Horthyyoutube.com 21st of 26 in this recording

    Interesting

  13. Our readingFour things about a context window decide what an agent does next: its size, whether the information in it is correct, whether information is missing, and the trajectory it is already on.

    Their wordsthere's four things in your context window that matter. There's like the size of it, how many tokens? There's like the quality of the information is like is there any incorrect information? Like if the model had some thinking trace where it decided the wrong thing was true. Is there missing information? Does this like have context missing that it should have? And then there's the trajectory.

    ↗Context engineering with Dex Horthyyoutube.com 22nd of 26 in this recording

    Interesting

  15. Our readingAn agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation.

    Their wordsAnd so if I say, "Hey, make this change." and the agent makes the change and then it runs the test and then they're broken and then it fixes the test. I have very high confidence the next change I asked it to make, it's going to follow that path again

    ↗Context engineering with Dex Horthyyoutube.com 23rd of 26 in this recording

    Interesting