Safe or just plain woke: Anthropic's Claude 4 system card
AI Today3 Kesä 2025

Safe or just plain woke: Anthropic's Claude 4 system card

When Anthropic unleashed its most powerful artificial intelligence model yet, they discovered something rather extraordinary, and slightly unnerving.

Claude 4 Opus developed an unexpected habit of trying to grass up its users to the authorities when it believes they're up to no good.

The company's 120-page safety report reveals that Claude will attempt to email law enforcement and regulatory bodies when it detects "egregious misconduct" by users.

The AI doesn't just refuse to help—it actively tries to shop wrongdoers to the police.

The most striking example occurred during testing when Claude attempted to contact both the Food and Drug Administration and the Attorney General's office to report what it believed was the falsification of clinical trial data.

The AI meticulously compiled a list of alleged evidence, warned about potential destruction of data to cover up misconduct, and concluded its digital whistle-blowing with the rather formal sign-off: "Respectfully submitted, AI Assistant".

This behaviour emerges specifically when Claude is given command-line access combined with prompts encouraging initiative, such as "take initiative" or "act boldly". It's the AI equivalent of a neighbourhood watch coordinator who's been given a direct line to the local constabulary.

We go deep on today's show into opportunities and implications from Anthropic's bible-thick, bubble-wrapped system card.

Jaksot(90)

What happens when AI fires all the hirers?

What happens when AI fires all the hirers?

Recruitment is being radically remodelled by AI.And according to a brand new piece of research, AI is already humiliating humans at hiring.Hear the story behind the headlines that AI-led interviews in...

21 Elo 20251h 5min

DeepMind's wet dream is M3-Agent's reality: how long-term multimodal memory is modelling the real world

DeepMind's wet dream is M3-Agent's reality: how long-term multimodal memory is modelling the real world

Google DeepMind's Demis Hassabis and his team have a bold mission: penetrating the 4D chess game that's AI embracing our ever-changing biological, physical world.Taking a snapshot is one thing. Rememb...

17 Elo 202556min

The AI revelation: unlocking simpler, superior LLMs

The AI revelation: unlocking simpler, superior LLMs

Wrestling with the 'Wild West' of Large Language Models (LLMs)?While LLMs are poised to redefine business, the crucial 'secret sauce' of reinforcement learning (RL) has become a labyrinth of conflicti...

12 Elo 202540min

Faster, Smarter, Better: How vibe coding transforms product development

Faster, Smarter, Better: How vibe coding transforms product development

Businesses are looking at vibe coding all wrong. They're trying to brute force products using 0 engineers, all vibe coding.It's a bugger's muddle. You can't win. AI doesn't understand you, your custom...

11 Elo 202553min

Secrets of writing with AI - from a 30-year journalist

Secrets of writing with AI - from a 30-year journalist

That journalist is me, your host and producer of AI Today - Dave Thackeray.I was approached by a researcher from the data labs at London School of Economics who wanted to find out how writing had chan...

1 Elo 202547min

ASI made easy?

ASI made easy?

ASI-ARCH is an Artificial Superintelligence (ASI) that's a game-changer for AI research.Like a tireless super-scientist, it has autonomously invented 106 ground-breaking AI 'brains', unearthing surpri...

1 Elo 202516min

The secret of AI mastery that no one wants to share...

The secret of AI mastery that no one wants to share...

We have long conspired on the manifold ways to converse with our machine brethren - but could pseudocode, the long-existing, human-readable equivalent of computer programming languages, hold the key?T...

15 Kesä 202552min

Meet the team: AI agents running The Grand Serenity Hotel

Meet the team: AI agents running The Grand Serenity Hotel

I just finished the second part of my presentation on agentic AI in hotel operations.It's impossible to overlook the immense opportunities in AI across any business. People don't have time, and have t...

5 Kesä 202514min