alt Hacker NewsNot to defend Claude here but the only instances this happened was when
1. It was said to be required (e.g. Searching through SEC)
2. Politeness policy (Wikimedia's bot policy and Crossref's "polite pool" ask automated clients for contact details)
So I think it wasn't because of malicious reasons as far as I can tell.
I did instruct Claude to never do it again except for the politeness policy. I'm assuming WikiMedia requested this so that they have someone to contact in case a bot overloads their servers
Replies
For what it's worth, I wanted to scrape some document from the SEC and claude explicitly told me this was required and asked me if it should do it.
Instructions are not guardrails. Best case, that just makes it less likely to do it
Are you telling me with a straight face that the stochastic parrot has only ever sent emails in request headers to ONLY the SEC and Wikipedia and no other sites?
I caught it sending my email to two non-Wikipedia/SEC sites (which I won't specify because they're work related.) I only found out because I held a "retro" with the agent, then found the other session after grepping my logs.
Should an agent not ask for confirmation, before leaking their patron's contact information to any random third party who asks for it?
If not... That sounds like primetime for prompt injection.