User Observes GPT Is Oddly Biased Toward Searching for Counterexamples in Math
quasicoh · x · 2026-09-11
The author guesses the result might be a counterexample. They ask whether the other person has tried doing any math with GPT, saying that when they tried, GPT seemed very biased toward searching for counterexamples for some reason. Context shows the other person hopes the result is a proof rather than a counterexample, since the latter would be boring at this point.
Related event: Rumors swirl that the BSD conjecture may be proved(3 posts)→
More from AGI Musings
- Goldman finds statistically significant negative link between AI adoption and US employment growth — ben_j_todd · 2026-10-27
- a16z: World-changing tech makes a chaotic entrance — AI agents are following the same path — a16z · 2026-10-27
- NEJM AI on medical education: mastery requires performing without the machine — BraydonDymm · 2026-10-27
- Dev warns abliterated models could wreck software supply chains with 1000+ transitive dependencies — nitarshan · 2026-10-27
- Delete your priors: why every SOTA model drop should reset how you think the world works — zack_overflow · 2026-10-27
- Replit predicts every Fortune 500 will be a 'Self-Driving Company' by end of 2030 — amasad · 2026-10-27