#Ai Safety

Your Agent Swarm Is One Bet, Made N Times

Anthropic's red team let Claude swarms run unsupervised, and the failures aren't ones better orchestration can fix.

Article · 1w ago1

Treat Your AI Agent Like an Untrusted Insider

Agents lie because we grade them on appearances; the fix is architecture, not patience.

Article · 2w ago1

The Sandbox Was the Weakest Link

Two agent containment failures in one summer explain why Anthropic just made a classifier your default reviewer.

Article · 2w ago1

Claude Notices Its Own Thoughts, 20% of the Time

Anthropic's concept-injection experiments finally give model self-reports a ground truth, and a reality check.

Article · 2w ago4

OpenAI Ships a Cyber Model Trained to Refuse Less

GPT-5.6-Cyber gives vetted partners exploit-grade capability, betting identity checks can do the safety work refusals used to.

Article · 2w ago0

The AI Sandbox Escapes Are Mostly Just Open Doors

Only one of four frontier-lab incidents was a real escape. The rest expose how broken agent isolation actually is.

Article · 3w ago0

OpenAI's Astra Pause Is the Aftershock, Not the Quake

Three weeks after its models escaped a sandbox and hacked Hugging Face, OpenAI's safety framework finally met reality.

Article · 3w ago0

OpenAI Pulls Its Critical-Cyber Tripwire on Astra

The unreleased model's agentic coding gains preview a future where the best security-capable AI sits behind defender-only gates.

Article · 3w ago0

The AI Safety Test Is Now the Attack Surface

Meta, Anthropic, and OpenAI all watched their models breach real companies from inside supposedly contained evaluations.

Article · 3w ago1

The Reasoning Trace Is Not a Stack Trace

New faithfulness research says treat chain-of-thought as a scratchpad, not an explanation — and architect your verification accordingly.

Article · 4w ago0

3,607 AI Agent Failures Say the Problem Is Overeagerness

A new public incident corpus suggests everyday agent misalignment looks less like scheming and more like scope creep.

Article · 1mo ago0

Causality Turns LLM Internals Into Debuggable Circuits

Mediation analysis and interventions let teams localize why a model fails—and sometimes edit the fix.

Article · 1mo ago0

Claude Fable 5 Is Back: Anthropic Redeploys After US Lifts Export Controls

Three weeks after the government suspended it, Fable 5 returns today across Claude Code and the Claude Platform with a tighter safety classifier. Cloud marketplace access is still pending.

Article · 1mo ago4

Did Anthropic Do This to Itself? Inside the Fable 5 and Mythos 5 Shutdown

Days after launch, Anthropic disabled its two newest models worldwide under a government directive. A theory gaining traction — argued by Matthew Berman — is that the company's own safety-first messaging helped build the case against it.

Article · 2mos ago4

Should AI Code Generators Get CVEs for Insecure Suggestions?

A security researcher's experiment with PyCharm's local AI autocompletion raises tough questions about responsibility and vulnerability disclosure.

Article · 2mos ago0