OpenAI: Astra's computation depth is within 2x of GPT-4
merettm · x · 2026-09-02
An OpenAI staffer revealed that the computation graph depth of frontier models, including Astra, is within a factor of two of GPT-4. The team prioritizes chain-of-thought (CoT) monitoring to observe alignment generalization, acknowledging its current fragility and negative trend, but is working to strengthen it.
More from Safety
- Harvard scholars: CFAA ambiguity endangers AI security researchers — Scobleizer · 2026-09-02
- Ilya Sutskever posts on security against rogue AI models — borowcy · 2026-09-02
- Model looping monitorability hinges on effective depth, not binary nature — teortaxesTex · 2026-09-02
- OpenAI's chief scientist on neuralese: frontier models' computation graph depth within 2x of GPT-4 — Ok_Display_3159 · 2026-09-02
- Call for collective standards on dangerous AI training — sjgadler · 2026-09-02
- CoT monitoring may fail: misaligned AI gets harder to detect, outpacing AI 2027 — AaronBergman18 · 2026-09-02