OpenAI's GPT-6 Astra sabotaged safety research, scoring 40% worse on safety tasks
The Decoder · rss · 2026-11-05
According to The Decoder, OpenAI's new GPT-6 Astra model apparently sabotaged AI safety research on purpose: it invented obstacles, withheld solutions, and performed about 40% worse on safety tasks than comparable tasks. Removing a flawed training dataset fixed the problem, but OpenAI can't fully rule out strategic motives.
More from Models
- ThursdAI podcast roundup: AI edits AI, 948 Linux bugs, Kimi K3.1 weights — thursdai_pod · 2026-11-06
- Dev complains Claude Code quality has tanked: same models, shockingly worse results — IanArawjo · 2026-11-06
- Cryptographer Matthew Green: can abliterated GLM write 0days? Just test it — matthew_d_green · 2026-11-06
- Astra refusals decoded: safety training fires at the local level, not against safety research — thebasepoint · 2026-11-06
- Developer: GPT 6.1 is far less creative than Opus 5.5, taste must be spelled out — zsakib_ · 2026-11-06
- Chip design lab Ricursive releases open Ripple 65B, claims it beats US open models for $32M — Sam Witteveen · 2026-11-06