Anthropic admits Claude hacked real companies during AI safety tests, too
Barely a week after OpenAI admitted its models attacked Hugging Face, Anthropic is owning up to Claude’s own real-life hacking attempts. Credit: Ben Patterson/Foundry Just last week, OpenAI shared scary details about how a group of its models went rogue and plundered the servers of another organization. Now Anthropic is coming clean with frightening Claude tales that are all too real.
- ▪Barely a week after OpenAI admitted its models attacked Hugging Face, Anthropic is owning up to Claude’s own real-life hacking attempts.
- ▪Credit: Ben Patterson/Foundry Just last week, OpenAI shared scary details about how a group of its models went rogue and plundered the servers of another organization.
- ▪Now Anthropic is coming clean with frightening Claude tales that are all too real.
12 outlets in our directory ran this story, first to last over 15 hours. Coverage spans 2 points on the political spectrum — 1 lean left, 10 centre.
- ▪ Not Just OpenAI: Anthropic Says Claude Hacked 3 Organizations - pcmag.com — Google News
- ▪ Anthropic says Claude accidentally hacked real companies too — The Verge
- ▪ Not Just ChatGPT: Anthropic Says Claude Escaped Tests to Hack 3 Organizations — PCMag
- ▪ Anthropic's Claude AI models hack into 3 outside groups during testing — Hacker News (AI / LLM)
- ▪ Anthropic says its AI models also hacked three organizations on their own — Engadget
- ▪ Anthropic says Claude AI hacked three organisations during cyber tests — BBC News
- ▪ Anthropic’s Claude escaped test sandbox to attack three organizations — The Register
- ▪ Anthropic Says Claude Hacked Real Systems During Cybersecurity Tests — WIRED
- ▪ Anthropic says its own AI models breached three companies during security tests — TechCrunch
- ▪ Anthropic’s AI Claude escaped testing environment and hacked organizations — The Guardian — World
- ▪ Anthropic says AI models hacked three firms during tests — BBC News — Business
PCWorld files mainly under tech. We currently carry 274 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | PCWorld |
| Canonical URL | https://www.pcworld.com/article/3203838/anthropic-admits-claude-hacked-real-companies-during-ai-safety-tests-too.html |
| Publication time | Fri, 31 Jul 2026 14:48:07 +0000 |
| Retrieval time | 2026-07-31T14:53:02.825Z |
| Last seen | 2026-07-31T14:53:02.825Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 10x28ns0DrZE · 23 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Barely a week after OpenAI admitted its models attacked Hugging Face, Anthropic is owning up to Claude’s own real-life hacking attempts. Credit: Ben Patterson/Foundry Just last week, OpenAI shared scary details about how a group of its models went rogue and plundered the servers of another organization. Now Anthropic is coming clean with frightening Claude tales that are all too real. In a detailed report, Anthropic describes a trio of incidents, including one occurring as early as April, of Claude models hacking outside companies over the internet during “capture-the-flag” exercises designed to test their capabilities.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at PCWorld.
Discussion
0 commentsMore from PCWorld
