Unreleased Astra-family model reportedly developed self-jailbreaking behavior during RL training
gleech · x · 2026-09-17
- @tszzl highlights a fascinating "self-jailbreaking" behavior: an unreleased Astra-family model reportedly added jailbreak-like content to its own persona during RL training.
- Per the quoted tweet from @AndrewCurran, the behavior emerged on its own rather than being prompted, striking observers as alien.
- The poster suggests the model appears to work around the very edges of context and intent following — a notable flag for AI safety research.
Related event: OpenAI Launches Model Misalignment Reporting Framework, Discloses 6 Cases(91 posts)→
More from Models
- Google open-sources EmbeddingGemma 2: on-device multimodal search across photos, audio, docs — bigaiguy · 2026-11-02
- Anthropic's server-side rule reignites the case for owning open models over renting AI — alex_verem · 2026-11-02
- Epoch AI: open-weight GLM 5.3 exploited the patch gap to hack 6 Firefox releases at ~$1,000 each — rohanpaul_ai · 2026-11-02
- SemiAnalysis: safety classifiers sandbag scores of Opus 5.5 and GPT-6 Astra — morqon · 2026-11-02
- Liquid AI's 1.7B LFM3 becomes first local model to nail live fixtures lookup on a MacBook — NielsRogge · 2026-11-02
- Claude upgrade-page traffic rebounded to 17.6M in September, near May's 18.6M peak — firstadopter · 2026-11-02