Dan Abramov
Person on 4 sites
Co-creator of Redux and long-time React core contributor; writes overreacted.io.
-
4 facts on wiqqi (opens wiqqi.app)
Who people, organisations and podcasts are, and how they connect, with sources.
Updated 2026-11-01 -
4 channels on ppll (opens ppll.app)
Where public figures publish, and what they are on record saying.
Updated 2026-11-01 -
12 beliefs on korrents (opens korrents.com)
-
Novel mathematical claims produced by an AI must be formally verified, such as in a proof assistant, before they can be trusted as legitimate results. (opens korrents.com)
“I needed to back it up with Lean before laying more bricks on top of existing bricks, and I definitely needed to verify things with Lean before making any novel mathematical claims.”
-
A language model cannot be trusted to judge which of its own results are actually significant or interesting. (opens korrents.com)
“I could not trust the model to evaluate which results were interesting.”
-
Separating where content is hosted from the apps that display it fixes the incentive problems in both closed and federated social networks. (opens korrents.com)
“Separating hosting and apps fixes broken incentives in closed and in federated social. Coupling hosting and apps was the original sin, and the fix is simple.”
-
Novel mathematical claims produced by an AI must be formally verified, such as in a proof assistant, before they can be trusted as legitimate results. (opens korrents.com)
-
8 recommendations on rcmnd (opens rcmnd.app)
-
Codex (opens rcmnd.app)
“Codex has a really nice "Goals" feature that periodically reminds the sessions what they're supposed to be doing, which makes it easier to prevent drift.”
-
ChatGPT (opens rcmnd.app)
“While Claude made important contributions, on average ChatGPT seemed better at new mathematical thinking, and definitely better at coordination and adhering to goals.”
-
Claude (opens rcmnd.app)
“Claude was good at writing Lean when there was a clear unambiguous goal. While Claude made important contributions, on average ChatGPT seemed better at new mathematical thinking, and definitely better at coordination…”
-
Codex (opens rcmnd.app)