Viewing profile — rcarmo

Even the fixed version is less of a coder than Qwen.

I have a feeling we're all working towards the same thing, but with different frameworks and infra. The Cloudflare OS experience looks, to me, very much like what I created for mys…

It's pretty much what I do as well, piclaw has had selective tool activation since... March, I think.

It already is, to the point I’ve forked it https://rcarmo.github.io/projects/tau-prime and am playing with bolting on my “standard” web UI onto it.

I added that in https://rcarmo.github.io/projects/piclaw a few weeks back. The reason it’s not in pi-ai is that server-side OpenAI compaction is encrypted/opaque and (at least in m…

I’ve been using both families of models inside pi/piclaw ( https://rcarmo.github.io/projects/piclaw/ ) and I assure you they work _better_ in that environment than in the originals…

I built https://rcarmo.github.io/projects/piclaw/ on top of pi largely leveraging its extension philosophy (I extended the contract to UI extensions, basically) and am very happy w…

They follow the tropes I get when I ask AI to do docs or summaries. Very Opus style, this one.

Would be awesome if it ran Qwen (the MoE probably won't squeeze that low, but...). This because I have hardly been able to use Gemma for any sort of useful coding.

[flagged]

Good. I have been poking at rcarmo/go-264 but was hesitant to tackle encoding :)

Depends on what you are using. I have been experimenting with various compaction techniques in piclaw ( https://github.com/rcarmo/piclaw/blob/main/docs/pipelined-co... ) and Codex …

I do hope they provide optimized A3B quants--that's been the sweet spot for usable local inference for me, at least.

Yeah, diarization is the real feature these days. STT needs uniformization, but quality of diarization is what is setting personal solutions apart in this field.

And yet, downvoting is still working within seconds of my commenting! Rock on HN, never change.