Dex Horthy

@dex-horthy · 26 positions · On ppll ↗

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.

What Dex Horthy says most about

coding agents 13

Every 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.
The IDE of the future has to be rethought from the ground up for agents, rather than being a text editor with an agents tab bolted on.

See all 13

LLMs 9

Every 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.
Without 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.

See all 9

software quality 6

Ship for three to six months with nobody reading the code and the codebase gets so bad that starting over is easier than fixing it — we ran a lights-off software factory and shut it down.
A team that slows down and reads every pull request and every line of code should expect only a 30 to 50 percent productivity lift from AI.

See all 6

design 3

The IDE of the future has to be rethought from the ground up for agents, rather than being a text editor with an agents tab bolted on.
Models will not learn to write maintainable code from today’s benchmarks, because the cost of bad architecture cannot be measured by running the unit tests — it arrives three to six months later.

See all 3

vibe coding 3

It is no longer worth not reading the code in exchange for the occasional two-week hand fix, because the volume of code we can now generate has gone up ten to a hundred times.
Ship for three to six months with nobody reading the code and the codebase gets so bad that starting over is easier than fixing it — we ran a lights-off software factory and shut it down.

See all 3

developer tools 2

The IDE of the future has to be rethought from the ground up for agents, rather than being a text editor with an agents tab bolted on.
The valuable form of loop engineering is a slow loop — a nightly cron job that fixes one thing and opens one pull request — not a redesign of your whole infrastructure around agents.

See all 2