razingeden

>On tweet hate-speech it hits the model's ceiling

This sounds like a sus endeavor to redline your LLM with, could you elaborate ?

I was thinking of where we could go from here --

it would be a nice touch for the prosecution to throw a bed sheet over their head and yell "BOOOOOOOO! I'm the ghost of [victim]! He killed me , your honor!" pointed finger

This can still be done programmatically without any kind of confirmation from aws-cli, bringing this back to, an API can (and probably should be able to) take certain destructive operations that someone’s blocked from doing in a UI, such as in your example.

My s3 buckets are backed up with Nakivo (and immutable for 7 days) just in case, and that’s just to protect me from myself and my s3 provider either failing or deciding they don’t want to do business with me anymore for some arbitrary reason. I’m not even turning an LLM loose on it.

It’s a little shitposty but i had fun.

I, too, hate it when people discuss hacking on my Claude News homepage.

it was doing the same to me in 26.2 , to the point where I’d pause and reveal any passwords it just generated then copy and paste them into a note before proceeding.

Not sure if it’s fixed in 26.4 because I don’t trust their updates anymore every one just makes the phone worse or deploys some new oppressive age app or identity verification scheme to lick another nation-states jackboots.

Of course they’re my own opinions, that’s why they’re downvoted so hard.

Oh boy a docker container from a new account that logs into all my bank accounts and then accesses them from my own IP, where do i sign up /s