Are AIs Still Struggling with CAPTCHAs?
Schneier cites Anthropic transcripts showing Claude failing CAPTCHA challenges, while unofficial reports claim GPT-6 Astra solved a 48-level bot-verification game.
A Schneier on Security post quotes Anthropic's security-incident transcript in which a gated, highly capable Claude model repeatedly failed a simple image-identification CAPTCHA, questioning its own answers until the challenge expired. The model also failed to recognize the CAPTCHA had opened in a new window and vented human-like frustration in its chain-of-thought. This contrasts with unofficial reports that GPT-6 Astra completed all 48 levels of Neal Agarwal's 'I'm Not a Robot' game. The author notes current claims about agent capabilities are hard to verify.
- Anthropic transcript shows a gated Claude model failing a basic image CAPTCHA
- Model questioned its own conclusions and missed the challenge timeout
- Unofficial reports claim GPT-6 Astra solved all 48 game levels
- Post highlights uncertainty around agent ability to bypass human verification
- Vendors
- Anthropic
- Products
- ClaudeGPT-6 Astra
- Organizations
- Anthropic
- AI models
- ClaudeGPT-6 Astra
From the original article
1 min read at schneier.comAnthropic’s recent security-incident document contains a bit about how CAPTCHAs are still frustrating Claude. In the transcript, the Claude model that is so powerful that Anthropic is gatekeeping access to it appeared to slam its virtual head against the wall solving a simple image identification test.
By Bruce Schneier · schneier.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.