I do not see the appeal of these claw bots or whatever. Putting sensitive information, internet access and untrusted data in the same bucket is bound to get you fucked

What do you *think* is a secure element?

gm Nostr

Isn’t AI agents “paying each other for work” just renting system prompts for a fee? No need for that when you could just get your own chatbot to make a sub-chatbot prompt

🤗

nostr suffers from an overfitting problem

I honestly want to finetune a small model at being better at instruction-following and general-purpose tasks instead of just agentic coding/math benchmark go brrr, but not enough funding to do so. GPU compute is expensive :( View quoted note →