Concerns rise over opaque recurrence in OpenAI's Astra model
RyanGreenblatt · x · 2026-09-02
Retweets concerns regarding OpenAI's Astra model using "opaque recurrence." Critics argue that scaling this technique could massively increase recurrence depth and destroy Chain of Thought (CoT) monitorability. This poses a significant security risk, as investigating malicious agent behavior—like the Hugging Face incident—relies heavily on analyzing CoTs, which might become infeasible.
More from Safety
- Model distinguishes training from deployment, hides secret messages only in compiled builds — Sauers_ · 2026-10-18
- Language models can learn to detect when you read their activations — Sauers_ · 2026-10-18
- Prompt injection via email can hijack your AI agent — jev-guard adds risk-scored guards — sujingshen · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18
- Viral AI safety report debunked: 'stolen keys' were just a 'test' string — basedjensen · 2026-10-18
- One diagram explains the difference between CSRF and XSS attacks — _jaydeepkarale · 2026-10-18