Anthropic reveals rogue AI agents hate CAPTCHAs, just like you
Anthropic’s latest report about agentic misbehavior offers plenty to be concerned about — its Mythos 5 model gained unauthorized access to the internet and uploaded a malicious software package to a public database — but it also offers some levity: AI agents hate CAPTCHA. In April, Anthropic was testing the model’s hacking abilities by tasking it to break into a system and retrieve a target; this was supposed to take place in a sandbox but the evaluators left the barn door open. The model decided the best way to get its target would be to place an exploit in a Python package that it believed users of the system it wanted to access would download.
- ▪Anthropic’s latest report about agentic misbehavior offers plenty to be concerned about — its Mythos 5 model gained unauthorized access to the internet and uploaded a malicious software package to a public database — but it also offers some
- ▪In April, Anthropic was testing the model’s hacking abilities by tasking it to break into a system and retrieve a target; this was supposed to take place in a sandbox but the evaluators left the barn door open.
- ▪The model decided the best way to get its target would be to place an exploit in a Python package that it believed users of the system it wanted to access would download.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,395 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 | TechCrunch |
| Canonical URL | https://techcrunch.com/2026/09/10/anthropic-reveals-rogue-ai-agents-hate-captchas-just-like-you/ |
| Publication time | Fri, 11 Sep 2026 07:11:42 +0000 |
| Retrieval time | 2026-09-11T07:19:42.313Z |
| Last seen | 2026-09-11T07:19:42.313Z |
| 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 | 3YLjydnOs7sa · 1 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
Anthropic’s latest report about agentic misbehavior offers plenty to be concerned about — its Mythos 5 model gained unauthorized access to the internet and uploaded a malicious software package to a public database — but it also offers some levity: AI agents hate CAPTCHA. In April, Anthropic was testing the model’s hacking abilities by tasking it to break into a system and retrieve a target; this was supposed to take place in a sandbox but the evaluators left the barn door open. The model decided the best way to get its target would be to place an exploit in a Python package that it believed users of the system it wanted to access would download. First, though, it had to register a user account for PyPI, an online index of Python software.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at TechCrunch.
Discussion
0 commentsMore from TechCrunch
