Safe or just plain woke: Anthropic's Claude 4 system card
AI Today3 Juni 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.

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(93)

The collapse of training

The collapse of training

When AI ingests all your company's documents and makes it easy for every colleague to get answers on every facet of their job, are we empowering people - or lobotomising them?Is the training struggle,...

10 Maj 20min

Who Taught the Machine to Forget?

Who Taught the Machine to Forget?

Three companies. Three crises. One unsettling question about what happens when you let machines do the remembering.In this episode: how a cheese shop and a 313-ship fleet solved the same problem from ...

8 Maj 26min

Why Your Company is a Giant, Amnesiac Goldfish (And How to Finally Build It a Brain)

Why Your Company is a Giant, Amnesiac Goldfish (And How to Finally Build It a Brain)

Your organisation generates a staggering mountain of data every single day. Slack threads ping, Jira tickets multiply, and emails fly back and forth at the speed of light. You have terabytes of perfec...

7 Maj 53min

10x your AI results with this ultimate context engineering lesson

10x your AI results with this ultimate context engineering lesson

On today's show we create a business to show you the huge improvements in gravitating beyond prompt engineering to the new community of practice we call context engineering.You'll be rocked by the res...

5 Nov 202549min

When's the right time to go all-in with AI?

When's the right time to go all-in with AI?

Two of the most important voices in AI spoke out this week. Andrej Karpathy, one of the algorithm's greatest philosophers, was in conversation with Dwarkesh Patel talking praisingly and cautiously abo...

18 Okt 202514min

ELephantLM: the AI that never forgets!

ELephantLM: the AI that never forgets!

If only that was the real name. After all this time begging frontier labs to build an LLM that learns from its mistakes and applies its discoveries at inference time...Welcome to AI Today!

13 Okt 202537min

brAIn: thinking of the future?

brAIn: thinking of the future?

The Dragon Hatchling is a remarkable research paper that reboots modern AI as a model that approximates how our brains work.Today's show is a fascinating discussion and I implore you to both enjoy it ...

1 Okt 202529min

Does AI work?

Does AI work?

It's the one thing every business leader needs to know.If I put AI to work in my organisation, will it screw everything up?While we should all be in experiment mode right now - until someone figures o...

26 Sep 202527min

Populärt inom Teknik

uppgang-och-fall
natets-morka-sida
elbilsveckan
bilar-med-sladd
market-makers
rss-technokratin
rss-laddstationen-med-elbilen-i-sverige
bli-saker-podden
rss-elektrikerpodden
rss-uppgang-och-fall
skogsforum-podcast
ai-sweden-podcast
hej-bruksbil
rss-heja-framtiden
rss-en-ai-till-kaffet
rss-snacka-om-ai
kodsnack
rss-digitala-influencer-podden
rss-milpodden
rss-vaxtpressenpodden