Anthropic's study ranking open-source models most useful to malicious actors draws safety criticism
shaunralston · x · 2026-09-30
Anthropic published a study comparing which open-source models are most useful to malicious actors. The poster questions the wisdom of releasing such a ranking — arguing it effectively serves as a selection guide for attackers — and tags Anthropic and safety researcher Pliny for comment, with the full report linked in the thread.
More from Safety
- Bounty hits $3,000 as researcher shows AI text detectors are trivially evadable — ctjlewis · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — 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
- 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