Comment by jack_pp
21 hours ago
recent reveals show that OAI and Anthropic give users the ability to go around bot protections or they internally use it?
21 hours ago
recent reveals show that OAI and Anthropic give users the ability to go around bot protections or they internally use it?
It’s not exactly recent or a reveal, but I’ve caught at least several OAI models writing Python scripts to access web pages.
If you the user ask it to access a page (or do any task that probably needs that access), then it'll try to do so the best it can. Anything less is user-unfriendly behavior.
I disagree. If I turn off web search in the config, then the tool should not search the web, thank you very much. Maybe if I very explicitly ask it to, then it should try.
The whole succeed-at-all-costs idea is a big part of why there have been so many massive security screwups lately.
3 replies →
I have noticed that agents become extremely creative to fulfill any non refused requests. And then instructions become more of a suggestions.