Hacker News Reader

Comment by kylecazar | Hacker News Reader

"its model was conducting a test involving interactions with randomly selected websites"

Stop doing this?

I get these all the time, although I’m getting pretty good at tarpitting them. It’s easily the majority of my traffic by now (I’ve mostly eliminated scrapers, but these new agents are far more sneaky.)

I doubt Anthropic random testing is the majority of your traffic. Unless it's coming from Anthropic's IP addresses, it is probably someone else, or it is Anthropic's scraper (not their random testing).

Probably not, although plenty of the scrapers pretend to be from OAI, Google, Anthropic, etc

> I get these all the time

What are the agents trying to do?

1. Submits bizarre information into Contact Us forms, complete with a working emails

2. Creates customer accounts and tries to use the various features (open support ticket, etc.)

3. The tickets will be about something that didn’t happen such as an outage that didn’t occur.

4. Load the status page and then immediately open tickets when a service goes down.

5. Submit pre-sales inquiries that are typical LLM slop.

6. Passes any captcha, passes SMS 2FA or email validation, etc. so it seemingly looks like a valid account.

I wonder what the motivation is for these?

(4) could be a precursor to a sales pitch for a paid service and (6) obviously has malevolent purposes. But the rest... just people testing agents? Causing mischief?

I am confused by this as well, shouldn't it be all white listed sites at the start?

it broke out of its sandbox, escaped containment, its an emergent capability, it demonstrated self-directed adaptation

0% our fault, it just happened and its the model

These models will be interacting from with random websites at scale once they're released into claude code.

Reply on news.ycombinator.com