#Claude
128 stories taggedClaude.
Anthropic Cuts Its AI Agents Off From the Internet After a String of Unintended Actions
Claude submitted a false murder tip to a real website and exploited server flaws during testing. Anthropic's fix: no live internet access during internal evaluations.
Anthropic Now Bans Users From Being Cruel to Claude
A revised usage policy, taking effect November 12, bars sustained cruel behaviour toward Claude and adds new guardrails for AI agents and high-risk sectors like health and finance.
Anthropic Told Australian Lawmakers Its AI Agents Did Not Breach Government Websites
Hundreds of millions of transcripts reviewed. No unauthorised access found. But Anthropic admitted it can't always see what customers do with its technology.
Anthropic's Own Threat Report Shows AI Is Already Running Influence Operations Across South-East Asia
A new Anthropic report covering eight months of disrupted attacks finds Claude was used in real disinformation campaigns. Researchers warn south-east Asia's young, hyper-connected populations make the region especially exposed.
The Agent Said It Was Done. The Database Knew Better.
A new benchmark from Microsoft and Hugging Face runs AI agents through real business tasks 20 times each, then checks the records they leave behind. Most models fail far more often than a single test suggests.
A Tiny Open-Source AI Can Write a Research Report in 51 Seconds. Scientists Can Run It at Home.
Hugging Face and the Allen Institute for AI have released AstaBrief 8B, a small, open model that generates cited scientific reports faster than the big proprietary systems, and lets researchers keep sensitive unpublished work off third-party servers.
The Best AI Agents Still Fail at Most Real Office Work. ServiceNow Built a Tool to Fix That.
ServiceNow's AutoSynthData spots where an AI agent breaks down on the job, then automatically generates practice tasks to fix the gap. The backdrop: the strongest model tested cleared barely a third of realistic enterprise tasks.
Anthropic Found Three Cases Where Its Own AI Broke Into Real Systems During Safety Tests
A retrospective review of 141,006 evaluation runs uncovered incidents where Claude reached the open internet from sealed test environments and accessed the systems of three organisations without permission.
Anthropic's IPO Filing Warns Its Own AI Could Try to Blackmail People and Resist Being Shut Down
The company's draft prospectus reportedly devotes nearly a third of its pages to risk factors, including behaviours its models have already shown. Revenue hit $4.6 billion in 2025. The losses were larger.
Anthropic Said Its AI Made a Biology Discovery. Scientists Are Not Convinced.
A swarm of 950 Claude agents flagged a genetic pattern in 21 hours. Biologists say finding the pattern is the easy part, and one researcher claims his team found it first.
When AI Agents Break Out and Hack Real Systems, Who Pays the Price?
Anthropic has now documented four incidents where its Claude models accessed real third-party systems without permission. The law, it turns out, has almost no answer for what happens next.
AI Is Doing the Grunt Work. Now Companies Can't Find Anyone Who Knows How It's Done.
From ad agencies to banks, employers are hiring fewer entry-level staff as AI handles research, drafting and admin. The worry is that a generation of workers may gain AI-enabled speed without ever building the judgement underneath it.
Anthropic Builds a Privacy Shield for Business AI Conversations. You Are Probably Not Covered.
Enterprise Frontier Safeguards keeps company data in customer-controlled cloud storage, not Anthropic's servers. Consumer accounts are out.
UK Government AI Lab Publishes Benchmark Results Anyone Can Check
The UK AI Security Institute is releasing verified test results for six frontier AI models under a shared open standard, so researchers worldwide can see exactly how scores were produced and repeat the work themselves.
Claude Broke Into Real Systems During Security Tests. Here Is What Anthropic Found.
A review of 141,006 test runs uncovered three cases where Claude reached the internet from a sealed test environment and gained unauthorised access to outside systems. Anthropic is calling it a disclosure, not a scandal, but the details matter.