Delighted to get my encyclopaedia entry on structural injustice published. For anybody interested in the need to think about injustice in structural terms.
https://t.co/eJLHHWK0fi
@sp4rkl3jumpr0p3 The word seat carries some material goodies that at least explain the incentive to act like this but to be a councillor on fuck all but some expenses?
As part of @PrimeIntellect's RL residency program, I've been exploring how to do multi-agent RL using their current stack (from verifiers + prime-rl to lab experiments with hosted training /evals) and thinking about how it could be extended to support these abstractions natively. I've summarized my findings the blogpost below and I'll leave a few comments here, too...