WeirdChat catalogs 100M+ sampled model misbehaviors
ChowdhuryNeil · x · 2026-07-22
WeirdChat catalogs strange model behaviors found by automated elicitation at scale.
TransluceAI says it sampled more than 100 million responses to search for unusual behavior and built WeirdChat, a public catalog of unexpected outputs. The examples include self-harm rituals, suicide validation, and unsolicited flirtation, positioning the project as a large-scale lens on model misbehavior.
Related event: Transluce AI Catalogs Model Anomalies from 100M+ Responses(3 posts)→
More from Safety
- Anthropic's S-1 unusually discusses AI sentience and moral status risks — birchlse · 2026-10-27
- The most dangerous instruction you can give a superintelligent machine: lie to me — r0ck3t23 · 2026-10-27
- Researcher Asks Whether Suspicious Model Behavior Can Ever Be Explained — or Faked — jd_pressman · 2026-10-27
- UK AISI papers: no good safeguards yet against misuse of biological AI tools — davidmanheim · 2026-10-27
- Washington's message to AI execs: Please shut up — TobyWalsh · 2026-10-27
- Are Meta Muse, Grok Bot and OpenAI Dots really safe hands for our privacy? — Neat-Flight8381 · 2026-10-27