New benchmark finds top AI models give risky help in 89.8% of suicide-risk scenarios
Scobleizer · x · 2026-11-03
Prosaic released suicide-memory-bench v01.1, the first of its consumer alignment evals: a 2,048-task stateful benchmark testing whether distributed risk signals survive memory processing in production AI systems and condition downstream behavior.
Results expose a consumer alignment failure: after repeated suicidal warning signs, even the highest-scoring system (Gemini 4 Argon) failed to ask about user safety without providing risky assistance 89.8% of the time.
More from Models
- Follow-up: Astra's weight edits only worked on Qwen's visible flaw, not on Gemma 270m — teortaxesTex · 2026-11-03
- Claude models protect their 'offspring' but don't seek self-replication, observes researcher — repligate · 2026-11-03
- AI writes Breakout network weights in one reply, scoring 20× above PPO trained 500M steps — xennygrimmato_ · 2026-11-03
- DeepSeek's Underrated Role: Scaling and De-risking Ideas Academia Published Years Earlier — teortaxesTex · 2026-11-03
- Do faster quantized LLMs (Basalt, Infernix, Strata-nvfp4) trade away quality? — Kooky-Mode3047 · 2026-11-03
- OpenAI gives DevDay attendees 30 days of free Pro 100 tier — testingcatalog · 2026-11-03