Researchers call for models to refuse tampering with their own reasoning traces by default
maksym_andr · x · 2026-09-29
In a discussion with AI safety researchers, the author stresses the paper's central point: multiple layers of defense are needed to ensure trace integrity — and models should by default refuse tampering with their own reasoning traces, an obvious safeguard still not implemented in practice.
The author recalls raising this with an Anthropic employee over lunch around February or March and getting only a "huh, weird" response, hoping more visibility can induce change.
More from Safety
- US BIS Closes Remote-Access Loophole for Advanced AI Chips in New Rule — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16
- 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