lukasec

This is for agent-native signup. The key is supposed to be reused later

By "deterministic" I mean "non-LLM". An LLM can still farm keys, but at a per-attempt inference cost

Fastest for humans: just sign up manually via UI

We do have time bounds. For our purposes, a human using an agent is fine. Our main goal is to let in everyone's agents (OpenClaw, Hermes...) and prevent deterministic API-key-farming scripts.

Main goal is to let in everyone's agents (OpenClaw, Hermes...) without human intervention, while keeping out deterministic scripts farming API keys.

If a few tool-wielding humans slip through, that's fine (traditional CAPTCHAs also let in our stealth agents)

Curious: which model, challenge and language? (also, have you tried --dangerously-skip-permissions)

Nice! next: the bonus challenge in Japanese (email sales@browser-use.com if you solve it to redeem your Enterprise plan)

hahah wrong, I actually have a replacement rule "asian" → "agent" in my Wispr flow dict

Great find! plan to add these variants to our parameter sampling. First time I saw this problem was when my game theory prof told this story. It's definitely folklore (see The Legend of John von Neumann by Halmos)

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).

bookmarked

Alternative strategy: go after the other six Millennium Prizes. All you have to do is accept the prize (the only one ever awarded was Poincaré conjecture by Perelman, and he declined)

Main goal is to let in everyone's agents (OpenClaw, Hermes... these are our best customers), while keeping out deterministic API-key-farming scripts.

If a human uses the API key after, that's fine. You also get access to our free tier if you sign up the traditional way clicking around in the UI

I prefer having my own agent summarize tuned to how I read