Firehose

Filtered to Hacker News, tagged “formal semantics” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

27 JUL 2026 · Hacker News · 107 pts · 79 comments ↗

A diagonal attack on linearly represented truth probes, inspired by Tarski's paradox, shows that no probe can pin down truth in a language model's embedding space due to the self-referential nature of natural language, which can express its own properties and lead to paradoxes like the liar paradox. AI summary