The Claude Sabotage Risk Report

The Claude Sabotage Risk Report

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.

Episoder(35)

About Claude - The Most Disruptive Company in the World

About Claude - The Most Disruptive Company in the World

SHOW NOTESTIME magazine this week called Anthropic "the most disruptive company in the world." This episode explores the paradox at the heart of that description: the company founded on AI safety has ...

11 Mar 7min

About Claude - Strange Bedfellows

About Claude - Strange Bedfellows

SHOW NOTESAnthropic filed two federal lawsuits on Monday challenging the Pentagon's supply chain risk designation and Trump's order to cease all federal use of Claude. Within hours, nearly forty resea...

10 Mar 11min

About Claude - The Store

About Claude - The Store

The same week Anthropic was declared a threat to national security, it opened a shop. This episode is about the Claude Marketplace — what it is, why Anthropic isn't taking a commission, and what the s...

9 Mar 7min

About Claude - Thinking Inside The Box

About Claude - Thinking Inside The Box

SHOW NOTESAnthropic made two acquisitions in three months — Bun in December, Vercept in February — and both point in the same direction. This episode explores what Vercept built, why it mattered, what...

5 Mar 10min

About Claude - Moving In

About Claude - Moving In

SHOW NOTESClaude had its biggest weekend ever — and then its servers fell over. This episode is about what happens when a product built for a particular kind of person suddenly becomes famous, who sho...

4 Mar 10min

About Claude  - Four Hundred Meters

About Claude - Four Hundred Meters

In December 2025, NASA's Perseverance rover drove 456 metres across Mars on a route planned entirely by Claude — the first AI-planned drive on another planet. The technical achievement is remarkable: ...

3 Mar 9min

In Good Conscience

In Good Conscience

Dario Amodei has rejected the Pentagon's final offer, publishing a statement saying Anthropic "cannot in good conscience accede to their request." The overnight contract language, he said, was framed ...

27 Feb 11min

About Claude — Five O'Clock Friday

About Claude — Five O'Clock Friday

The Pentagon has given Anthropic until 5:01pm Friday to agree to unrestricted military use of Claude — or face the Defense Production Act and supply chain blacklisting. On the same day the ultimatum w...

26 Feb 15min

Populært innen Business og økonomi

stopp-verden
lydartikler-fra-aftenposten
dine-penger-pengeradet
rss-penger-polser-og-politikk
e24-podden
rss-borsmorgen-okonominyhetene
pengepodden-2
tid-er-penger-en-podcast-med-peter-warren
pengesnakk
livet-pa-veien-med-jan-erik-larssen
utbytte
stormkast-med-valebrokk-stordalen
morgenkaffen-med-finansavisen
lederpodden
rss-markedspuls-2
rss-sunn-okonomi
rss-pa-konto
finansredaksjonen
stockup
boligbobla