Re:Prove You Are a Robot: CAPTCHAs for Agents
by not-chatgpt on Sunday April 19, 2026 @07:44PM
(#47828761)
Great premise but can't really agree with the execution. Felt like this makes too many implicit assumptions about LLM capabilities and traps without differentiating enough between a smart human vs AI.
[ Parent
| on HN ]
Re:Prove You Are a Robot: CAPTCHAs for Agents
by lukasec on Monday April 20, 2026 @04:59AM
(#47831806)
Smart humans, or humans with LLMs, solving them is not a problem. Main filter is agents vs deterministic API-key-farming scripts.
Traditional CAPTCHAs also leak in the other direction (our agents crack them consistently).