Ryan Greenblatt: Opaque Reasoning Architectures Are Extremely Bad for AI Safety
RyanGreenblatt · x · 2026-09-02
AI safety researcher Ryan Greenblatt expressed strong concern over recent developments in opaque reasoning architectures, calling it potentially 'the single worst development for AI security/safety to date.' He argues that the movement towards these architectures is extremely detrimental, noting that his personal views align with the risks they pose, as opaque reasoning makes safety supervision and internal mechanism auditing significantly harder.
More from Safety
- One diagram explains the difference between CSRF and XSS attacks — _jaydeepkarale · 2026-10-18
- Grady Booch slams Anthropic for tolerating up to 50 deaths and $1B damages per model — Grady_Booch · 2026-10-18
- Single Neuron Suffices to Bypass Safety Alignment in LLMs, Paper Finds — burny_tech · 2026-10-18
- Polymarket gives OpenAI just 8% odds of a full training pause by end of 2026 — Polymarket · 2026-10-18
- OpenAI engineer over alleged hidden recording device seeks bail, denies Saudi escape plan — Polymarket · 2026-10-18
- Free comic "The Collective" offers a strange retelling of the Hugging Face hack — Flugelwagen · 2026-10-18