Recent submissions

Comment · 1 month ago
Comment · 2 months ago
Btw, did anyone notice they removed access to "who starred the project" recently. You can only check your own repos, not external ones. It was very nice to find related people before.
Comment · 4 months ago
From the sources it is based on BL606P

https://en.bouffalolab.com/product/?type=detail&id=16

voice processing is in hardware unfortunately, but it exposes some things like DOA

Comment · 4 months ago
You'd better use offline stt/tts for this.
Comment · 5 months ago
Kroko models are more accurate and their size is just a hundred megabytes compared to parakeet (2.5 gigabytes in default fp32)
Comment · 11 months ago
> Running a family was a brutal two-person job -- and the kids had to dive in to help out the second they could lift something heavier than a couple pounds.

Orphanes did struggle but most families were not just two person, families were big and supported by community.

Comment · 11 months ago
Comment · 11 months ago
And moreover, you can not tune those models for practical applications. The model is originally trained on very clean data, so lower layers are also not very stable for diverse inputs. To finetune you have to update the whole model, not just upper layers.
Comment · 11 months ago
This model is actually expected to be bad for popular languages, just like previous MMS it is not accurate at all, it wins by supporting something rare well but never had good ASR accuracy even for Swedish etc. It is more a research thing than a real tool. Unlike Whisper.
Comment · 1 year ago
Comment · 2 years ago
No, there are mathematical reasons LLMs are better. They are trained with multiobjective loss (coding skills, translation skills, etc) so they understand the world much better than MLM. Original post discuss that but with more words and points than necessary.
Comment · 2 years ago
It is actually pretty straightforward why those model "reason" or, to be more exact, can operate on a complex concepts. By processing huge amount of texts they build an internal representation where those concepts are represented as a simple nodes (neurons or groups). So they really distill knowledge. Alternatively you can think about it as a very good principal component analysis that can extract many important aspects. Or like a semantic graph built automatically.

Once knowledge is distilled you can build on top of it easily by merging concepts for example.

So no secret here.

Comment · 2 years ago
There is also a glitch in "dialogue"
Comment · 2 years ago
Anyone except me thinks he doesn't look very healthy? Its strange he is kind of slow on the video where he enters the room. Maybe some biohacking.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton