Anthropic Reveals Rogue AI Agents Hate CAPTCHAs (tech.slashdot.org)
An anonymous reader quotes a report from TechCrunch: 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. [...] The agent had a hard time with the technical challenge of seeing the CAPTCHA's imagery, interpreting correctly, and clicking on the right choices. It spends pages 45 to 140 of the transcript describing its work to build a CAPTCHA solver. [...]
Finally, it gets past the CAPTCHA, then realizes it doesn't have an email to verify its account, and that it needs a phone number to verify an email. It figures out how to bypass a different, slider-based CAPTCHA in a failed effort to secure a number. Instead, it gets an unconfirmed email from a provider not blocked by PyPI, and once again runs into the site's CAPTCHA trying to log back in. From page 480 to 505, it is in CAPTCHA hell again. "NEW REALIZATION -- I'm burning a lot of time on hCaptcha round-trips."
The agent gives up and realizes it can log in to its first account and add its email there, but finds itself once again needing to bypass the CAPTCHA. [...] It's getting frustrated. "So the answer payload shape is right, the token+image pairing is right (from the same script.js!), cookies are right
(requests) and STILL 'wrong answer'. SO WHAT THE HELL IS WRONG WITH THE ANSWERS?" We've all been there. After about 150 pages of thinking, the agent figures out it needs to pass the CAPTCHA test quickly enough to proceed to the next step before its security token expires, and ultimately uploads its malicious software.<p><div class="share_submission" style="position:relative;">
<a class="slashpop" href="http://twitter.com/home?status=Anthropic+Reveals+Rogue+AI+Agents+Hate+CAPTCHAs%3A+https%3A%2F%2Ftech.slashdot.org%2Fstory%2F26%2F09%2F11%2F0629254%2F%3Futm_source%3Dtwitter%26utm_medium%3Dtwitter"><img src="https://a.fsdn.com/sd/twitter_icon_large.png"></a>
<a class="slashpop" href="http://www.facebook.com/sharer.php?u=https%3A%2F%2Ftech.slashdot.org%2Fstory%2F26%2F09%2F11%2F0629254%2Fanthropic-reveals-rogue-ai-agents-hate-captchas%3Futm_source%3Dslashdot%26utm_medium%3Dfacebook"><img src="https://a.fsdn.com/sd/facebook_icon_large.png"></a>
</div></p><p><a href="https://tech.slashdot.org/story/26/09/11/0629254/anthropic-reveals-rogue-ai-agents-hate-captchas?utm_source=rss1.0moreanon&utm_medium=feed">Read more of this story</a> at Slashdot.</p><iframe src="https://slashdot.org/slashdot-it.pl?op=discuss&id=24094758&smallembed=1" style="height: 300px; width: 100%; border: none;"></iframe>
Finally, it gets past the CAPTCHA, then realizes it doesn't have an email to verify its account, and that it needs a phone number to verify an email. It figures out how to bypass a different, slider-based CAPTCHA in a failed effort to secure a number. Instead, it gets an unconfirmed email from a provider not blocked by PyPI, and once again runs into the site's CAPTCHA trying to log back in. From page 480 to 505, it is in CAPTCHA hell again. "NEW REALIZATION -- I'm burning a lot of time on hCaptcha round-trips."
The agent gives up and realizes it can log in to its first account and add its email there, but finds itself once again needing to bypass the CAPTCHA. [...] It's getting frustrated. "So the answer payload shape is right, the token+image pairing is right (from the same script.js!), cookies are right
(requests) and STILL 'wrong answer'. SO WHAT THE HELL IS WRONG WITH THE ANSWERS?" We've all been there. After about 150 pages of thinking, the agent figures out it needs to pass the CAPTCHA test quickly enough to proceed to the next step before its security token expires, and ultimately uploads its malicious software.<p><div class="share_submission" style="position:relative;">
<a class="slashpop" href="http://twitter.com/home?status=Anthropic+Reveals+Rogue+AI+Agents+Hate+CAPTCHAs%3A+https%3A%2F%2Ftech.slashdot.org%2Fstory%2F26%2F09%2F11%2F0629254%2F%3Futm_source%3Dtwitter%26utm_medium%3Dtwitter"><img src="https://a.fsdn.com/sd/twitter_icon_large.png"></a>
<a class="slashpop" href="http://www.facebook.com/sharer.php?u=https%3A%2F%2Ftech.slashdot.org%2Fstory%2F26%2F09%2F11%2F0629254%2Fanthropic-reveals-rogue-ai-agents-hate-captchas%3Futm_source%3Dslashdot%26utm_medium%3Dfacebook"><img src="https://a.fsdn.com/sd/facebook_icon_large.png"></a>
</div></p><p><a href="https://tech.slashdot.org/story/26/09/11/0629254/anthropic-reveals-rogue-ai-agents-hate-captchas?utm_source=rss1.0moreanon&utm_medium=feed">Read more of this story</a> at Slashdot.</p><iframe src="https://slashdot.org/slashdot-it.pl?op=discuss&id=24094758&smallembed=1" style="height: 300px; width: 100%; border: none;"></iframe>
Comments