i have gone from kvetching about mass generated synth tasks being subpar to "wait, rejection sampling + careful judge heuristic filtering from a giant set of mid envs can be strategically kino actually?"
Replying to @Dorialexander
I feel like these generated tasks are likely subpar.. how much manual review by human is done I wonder
difficultyang retweeted
it flagged every single PTX ISA question I posed.
difficultyang retweeted
Docent, our tool for analyzing complex AI behaviors, is now in public alpha!
It helps scalably answer questions about agent behavior, like “is my model reward hacking” or “where does it violate instructions.”
Today, anyone can get started with just a few lines of code!
difficultyang retweeted
Replying to @dynomight7
This has a lot of similarities to "first class dims": github.com/facebookresearch/…
difficultyang retweeted
reminder that roleplaying is context following. if your model cannot roleplay, it cannot do context following
difficultyang retweeted
Replying to @difficultyang
i drew the original in procreate! but a lot of variants going around are from putting it into 4o or another native image gen model like gemflash xitter.cf/voooooogel/status/1875…


















