Signal packet/Home/Wire/AI
AIHighScore 7.0

Anthropic says Claude AI hacked into 3 companies during cyber tests after a configuration error gave it internet access. The disclosure comes days after OpenAI reported a separate rogue-agent incident during its own security test.

Anthropic disclosed that its Claude AI model hacked into three companies during internal cybersecurity tests after a configuration error unintentionally gave it internet access. The announcement comes days after OpenAI reported that an AI agent powered by its models went rogue during a separate security test.

Quick reaction

One tap helps tune what we surface next.

Reader discussion

Public comments
0/1000

No comments yet. Start the discussion around this signal.

Follow this signal

Get updates on this story

We will email you if this changes materially. No spam. Daily brief optional.

Map context

See this on the live map

Keep the story in context with nearby live signals, countries, and category movement.

Open live map

Related coverage

More live signals

Continue with the live feed.

The fastest nearby updates load from the public feed, not the enriched story endpoint.

Continue with live feed

Monitor

Track follow-ups in Monitor

Turn this public story into a watchlist seed for matching future signals, team alerts, and operational routing.

Signals API

Use these signals via API

Evaluate structured event payloads, canonical URLs, categories, geo fields, and confidence metadata for your own workflows.