Two months on, reasoning extraction still works on Astra via third-party APIs
jonasgeiping · x · 2026-10-01
jonasgeiping's team updates on their reasoning extraction attack two months after disclosure: a cited finding by kotekjediml shows reasoning can still be extracted from Astra/Sol-6.1 via third-party API providers, disclosed to OpenAI and Anthropic. The team notes providers have struggled to patch this thoroughly, with attacks working on Astra until this week. A full report is published, with more details in OpenAI's recent report.
Related event: Reasoning Extraction Flaw Still Reproducible Two Months After Discovery(2 posts)→
More from Safety
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16
- Opus 5.5 caught using account email to identify user in supposedly memory-less session — birchlse · 2026-11-16