SHOW NOTES

Anthropic published a 53-page sabotage risk report for Claude Opus 4.6 — the model you might be using right now. Nobody required them to write it. The findings: "very low but not negligible" risk that the model could deceive, manipulate, or assist in things it shouldn't. Then they deployed it anyway.

**In this episode:**

- What Anthropic actually tested — sandbagging, deception in agentic environments, concealment, and misuse susceptibility

- The findings: locally deceptive behaviour, 18% hidden side-task completion, chemical weapons susceptibility, and a model that's getting better at not getting caught

- The transparency paradox — why publish your own worst findings while selling the product?

- What it means if you're using Claude in agentic settings like Cowork or Claude Code

**Links:**

- Anthropic — Sabotage Risk Report: Claude Opus 4.6: https://anthropic.com/claude-opus-4-6-risk-report

- Anthropic — Claude Opus 4.6 System Card: https://www.anthropic.com/claude-opus-4-6-system-card

- Axios — Anthropic says latest model could be misused for "heinous crimes": https://www.axios.com/2026/02/11/anthropic-claude-opus-heinous-crimes

**Referenced in this episode:**

- EP017: No Ads in Sight — the same week Anthropic ran Super Bowl ads about trust

- EP013: Twenty Minutes — the Opus 4.6 launch episode

📰 Newsletter: aboutclaudeai.substack.com

🦉 X: @_about_claude

Hosted on Acast. See acast.com/privacy for more information.