korrents
Chip Huyen

What Chip Huyen thinks about AI agents

@chip-huyen · 37 positions · On ppll ↗

Engineer and writer on machine-learning systems; author of Designing Machine Learning Systems and AI Engineering.

Chip Huyen 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.

Filter AI agents · Newest first
Topic
All 37LLMs 13AI agents 4vibe coding 4ambition 2coding agents 2OpenAI 2reinforcement learning 2software quality 2AGI 1
10 more topics
AI alignment 1AI and human skill 1behavioural science 1chat interfaces 1computer vision 1design 1Google 1innovation 1neural networks 1self-driving cars 1
Sort
NewestOldest

Only Chip Huyen on AI agents. See everyone on AI agents

4 dated positions, 2025 to 2026, in their own words. Our reading of what Chip Huyen has said — not written or endorsed by them.

4 positions so far — this page is not yet offered to search engines.

  1. Our readingWe are still retrofitting the tools we already had onto workflows we have only imagined, instead of designing for how people will actually work with AI.

    Their wordsSo, I I think there's a lot of things we still try to imagine. What would be an AI-driven world look like, right? I think people are trying to like retrofit what already exists to fit what they think is a new workflow.

    ↗Chip Huyen: Building when it feels like there's nothing left to build - The Pragmatic Summityoutube.com 9th of 14 in this recording

  3. Our readingThe frightening part of giving agents more access is not bad code but irreversible action, so the guardrails to build next are guardrails on reversibility.

    Their wordsYou cannot just reverse that, right? It's just not working. So, I do think that we need to build out the whole guardrails for the reversibility of actions because that actually where things get really really scary.

    ↗Chip Huyen: Building when it feels like there's nothing left to build - The Pragmatic Summityoutube.com 11th of 14 in this recording

  4. 15 months earlier

  5. Our readingMost real-world AI agent systems are actually multi-agent systems made of multiple components.

    Their wordsBecause most agentic workflows are sufficiently complex to involve multiple components, most agents are multi-agent.

    ↗Agentshuyenchip.com 2nd of 3 in this piece

  7. Our readingPlanning is fundamentally a search problem: explore paths, predict outcomes, and pick the best one.

    Their wordsPlanning, at its core, is a search problem. You search among different paths towards the goal, predict the outcome (reward) of each path, and pick the path with the most promising outcome.

    ↗Agentshuyenchip.com 3rd of 3 in this piece