dmezzetti
Joined 5 years ago
Karma
861
Submissions
552
Member since
May 22
Recent submissions
Comment · 2 months ago
As an open source maintainer, I can chime in on this.
With TxtAI, I've seen a large uptick in PRs (https://github.com/neuml/txtai/pulls?q=is%3Apr+is%3Aclosed+s...). While the extreme verbosity of Claude messages and commits is very annoying (plus the constant defending itself on why it's a bug), I do think it's a positive that more people are enabled.
It does require reviewing the PRs. Some can be tricky just like a human. For example I did merge this PR (https://github.com/neuml/txtai/pull/1136) and it would have completely broke search. But a human could also do that.
From an open source standpoint, I say the more the better. You just have to be willing to do the work to review and no not just having AI agents to review what the AI agents are submitting. There still needs to be a human in the loop, if you care about quality.
Comment · 3 months ago
Very interesting project! Are there benchmarks for the "compatibility mode" or are all the numbers for the Gigatoken API?
Comment · 3 months ago
The recent abrupt removal of the ability to see who has starred a project isn't a good move. Things like this certainly erode trust.
Comment · 3 months ago
I agree that Kokoro is a good TTS model.
If you're interested in an ONNX version and a permissively licensed TTS Tokenizer, I built a pipeline for that a while back: https://huggingface.co/NeuML/kokoro-base-onnx
Comment · 3 months ago
100% agree on this.
I've been working on small local models for years with txtai (https://github.com/neuml/txtai). I've published close to 100 models that can run local for RAG, Agents, Vector Search and more (https://huggingface.co/NeuML/collections).
Comment · 3 months ago
Interesting project. Happy to see someone who shares an interest in tiny vector embeddings models. I've worked on tiny (1MB - 4MB, 250K - 950K parameters) embeddings models called BERT Hash https://huggingface.co/blog/NeuML/bert-hash-embeddings
Keep up the great work!
Comment · 4 months ago
Why does HN let OpenAI and Anthropic basically advertise but it throws down the gauntlet at a small developer like myself when we do "self promotion"?
Top 3 posts as of this moment are all about Claude.
Comment · 4 months ago
Local models are great for a lot of things past just software development. We need to move towards solving other real world problems vs just building software. I've been focused on that with TxtAI (https://github.com/neuml/txtai) for 6 years now.
Comment · 4 months ago
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
Related paper that's a good read: https://arxiv.org/abs/1908.08962
Comment · 8 months ago
They have paid hosting - https://huggingface.co/enterprise and paid accounts. Also consulting services. Seems like a pretty good foundation to me.
Comment · 8 months ago
This is really great news. I've been one of the strongest supporters of local AI dedicating thousands of hours towards building a framework to enable it. I'm looking forward to seeing what comes of it!
Comment · 8 months ago
Why keep relying on API services? If you'd like your own local AI integration with open providers like Rocket.Chat and Mattermost, check out txtchat (https://github.com/neuml/txtchat).
Comment · 8 months ago
Very interesting!
It would be great to see how it compares to Faiss / HNSWLib etc. I'd will consider integrating it into txtai as an ANN backend.
Creator of txtai (https://github.com/neuml/txtai)