What Dan Abramov thinks about LLMs

@dan-abramov · 12 positions · On ppll ↗

Co-creator of Redux and long-time core contributor to the React team; writes about JavaScript and software design at overreacted.io.

Dan Abramov 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 LLMs · Newest first

Topic

All 12formal proof 1LLMs 1open source 1social media 1

Sort

NewestOldest

Only Dan Abramov on LLMs. See everyone on LLMs

1 dated position, 2026, in their own words. Our reading of what Dan Abramov has said — not written or endorsed by them.

1 position so far — this page is not yet offered to search engines.

1. 18 Sept 2026

   Our readingA language model cannot be trusted to judge which of its own results are actually significant or interesting.

   Their wordsI could not trust the model to evaluate which results were interesting.

   ↗How I Vibed a Proof of Conway’s Conjectureoverreacted.io 2nd of 2 in this piece