Had a great time presenting at the music workshop, thanks @zacknovack.bsky.social and @hermandong.bsky.social for putting it together!

Presenting a poster with some independent work on dynamic neural audio at 3pm at the AI for Music workshop (room 27)! bostromk.net/ASURA

As our main result, we find that when a token is in a model’s vocabulary—i.e., when its characters are tokenised as a single symbol—the model may assign it up to 17x more probability than if it had been split into two tokens instead

Finally found it!

power's back, now I can resume flailing ("running ICLR rebuttal experiments")

another starter pack, this time for folks (past & current) from Ai2 (@ai2.bsky.social) 😍 go.bsky.app/Qjyc97J

EMNLP was so fun miami is interesting