> If you ask ChatGPT or Claude to write something like this through their websites, they will refuse. This OpenClaw agent had no such compunctions.

OpenClaw runs with an Anthropic/OpenAI API key though?

▲

macintux 8 hours ago | parent | next [-]

I think they’re describing a difference in chat behavior vs API. The API must have fewer protections/be more raw.

▲

basketbla 7 hours ago | parent | prev | next [-]

Probably pretty big difference in system prompt from using the apps vs hitting the api, not that that’s necessarily what’s happening here. + I think openclaw supports other models / its open source and it would be pretty easy to fork and add a new model provider.

	▲	zahlman 7 hours ago \| parent [-]
		Why wouldn't the system prompt be controlled on the server side of the API? I agree with https://news.ycombinator.com/item?id=47010577 ; I think results like this more likely come from "roleplaying" (lightweight jailbreaking).

▲

varenc 8 hours ago | parent | prev [-]

Yea pretty confused by this statement. Though also I'm pretty sure if you construct the right fake scenario[0] you can get the regular Claude/ChatGPT interfaces to write something like this.

[0] (fiction writing, fighting for a moral cause, counter examples, etc)