Mathematicians accuse OpenAI of training Astra on their 20-year soficity conjecture work
ctjlewis · x · 2026-09-10
Mathematician Valerio Capraro relays Andreas Thom's detailed Mastodon post presenting evidence that OpenAI may have trained Astra on conversations in which Thom and Gábor Kun worked on Gromov's soficity conjecture — one of the ten problems OpenAI later announced Astra had solved. Thom is a leading expert on sofic and hyperlinear groups who has spent two decades on this problem. Capraro argues that if accurate, this is far more than an attribution dispute, though others in the thread dismiss the accusations as baseless. The controversy is still unfolding.
More from Companies & People
- An AI company built in five years now moves a mid-sized European GDP — felpix_ · 2026-10-26
- Anthropic eyes IPO with 900% NRR as 48% of H1 revenue flows via cloud marketplaces — thedealdirector · 2026-10-26
- Fmr. OpenAI Design Head Ian Silber, Who Led ChatGPT and Codex, to Speak at SPC — soleio · 2026-10-26
- Silicon Valley breakdown: five Stanford-area giants worth ~$18T — FinanceYF5 · 2026-10-26
- User suspects X's bundled Grok subscription boosted tweet reach amid algorithm change rumors — talkaboutdesign · 2026-10-26
- "RIP Claude + Chrome": developer flags the end of Anthropic's browser integration — damienghader · 2026-10-26