jtrt
jtrt
Can replicate on a new install.
@stefangrotz are you still working on this? your repo seems a bit dead - I could give this a go.
I'll start working on this later, then. Thanks, but I prefer to clean fork this myself.
As for making this a plugin, @Qoyyuum in my opinion wikidata is general-purpose enough and well-established enough to be a "core" functionality, since google is not always the best source...
It would obviously be necessary to test the responses' accuracy when evaluating risk and to tweak the prompt to something less improvised. Nevertheless, I believe this would be a good...
Yes, it would increase costs, but not doubling at all since embeddings are not used here. Still, the idea is to have this as a third, optional mode.
I am almost done implementing this. GPT-4 does a very good job analyzing commands. However, GPT-3.5 is lacking at best. Will post feedback in pull request.
Why close?
Just to provide context to any discussion, this is the prompt used to calculate risk: > You are to act as an intelligent, automated expert risk evaluator. You will be...
More comments: - GPT-4 (expectedly) does a better job assessing risk than GPT-3 and 3.5. - Even though GPT models are usually safe and do not output dangerous commands, AutoGPT...