Viewing profile — kraddypatties

I think the only thing that gives me pause is the fact that they SFT on Opus 4.5 explanations as a pertaining step. But, generally I agree, especially given the auto encoder is onl…

I believe that’s _part_ of the point (or at least a side-effect) of the KL divergence loss term they have on the AV. That and training stability.

I can believe that in the long run. Does the agent have access to arxiv (a brief skim of the README didn't have an answer)? If not, it could be that the current approach of relying…

Hm, that's fair. It does feel like there's low hanging fruit in combining "old school" methods for conducting a hyperparameter sweep efficiently _with_ the higher level architectur…

I feel like most of this recent Autoresearch trend boils down to reinventing hyper-parameter tuning. Is the SOTA still Bayesian optimization when given a small cluster? It was ~3 y…

Glad you liked it! Currently the avatar does it based on the text, which maps the incoming audio to one of our emotion codes, biasing the generation to that emotion. It's not foolp…

Hey HN, we're the co-founders of Keyframe Labs. We train photoreal AI human models you can FaceTime with (try for yourself here: https://demo.keyframelabs.com ). Notably, our model…

I'm interpreting this as "uv was built off of years of PEPs", which is true; that being said the UX of `uv` is their own, and to me has significantly reduced the amount of time I s…

Running into "no healthy upstream" when navigating to the link -- hug of death maybe?

been lurking for most of my adult life (and it shows :-)) Thanks HN! You make me smarter every (other) day.

Thanks for trying it out! Yea that latency makes sense; "listening" includes turn detection and STT, "thinking" LLM + TTS _and then_ our model, so the pipeline latency stacks up pr…

Hey HN. Over the last few months, we've (me and @parthradia) homebrewed some very fast, very cheap, and pretty expressive talking head models. Our latest enabled us to finally get …

We've been tinkering with building realtime talking head models (avatar models, etc.) for a while now, and finally have something that works (well enough)! Operates at ~2x realtime…