shekhar101

https://github.com/jordanbaird/Ice Try this. I am not affiliated in anyway. It's my must have macos app.

Tried this and really liking it so far. Question - is there a diarization support in the tui app or any of the models MetalRt supports? Any plans to add it if not already supported?

Seems to be based on See through walls by MIT (2013)? Good job porting it to esp32. I was just looking a week ago to do the same thing - basically reproducing this work. I'll definitely try this. https://www.media.mit.edu/projects/seeing-through-walls-comp...

I was reading Xiaomi YU7 marketing page[0] yesterday and the NVIDIA AGX Thor stood out (says: NVIDIA DRIVE AGX Thor). I was wondering what it was and this showed up! Looks like it is (or a Drive variant of it) is already being used in newer cars for self-drive and such. [0] https://www.mi.com/global/discover/article?id=5174

Can someone (or OP) point me to a recipe to fine tune a model like this for natural language tasks like complicated NER or similar workflows? I tried finetuning Gemma3 270M when it came out last week without any success. A lot of tutorials are geared towards chat applications and role playing but I feel this model could be great for usecases like mine where I am trying to extract clean up and extract data from PDFs with entity identification and such.

FYI: owhisper pull whisper-cpp-large-turbo-q8 Failed to download model.ggml: Other error: Server does not support range requests. Got status: 200 OK

But the base-q8 works (and works quite well!). The TUI is really nice. Speaker diarization would make it almost perfect for me. Thanks for building this.

I tried a picture with instructions and it says "something went wrong". I would love to try and see how well it works for my use case.

Yes it is, however API keys from aistudio only allows pro-experimental model. So if I select gemini-pro, I will see this: "Gemini 2.5 Pro Preview doesn't have a free quota tier. Please use Gemini 2.5 Pro Experimental (models/gemini-2.5-pro-exp-03-25) instead". Can I choose exact model somewhere in the CLI?

Can you open up the options to use other model/versions, especially Gemini-2.5 pro experimental models available through aistudio? Would love to try this but gemini flash fails for even simple tasks. Example: I asked it to extract all the links from comment section of a hackernews comment section and it just scrolled all the way to the end and then nothing. Maybe pro models can do it better.

This is really cool (and timely for me). Lovely work with the UX. No accounts, no nonsense. Kudos.

Spends so much time looking for UI design tools that they could've learned actual design in the meantime

Ouch! This is really well done. :)

I am RM2 user and this is useful for me. I signed up not expecting much but that digest designer is so well done! Kudos. Beautifully executed. Signed up and looking forward to the digests.

India is around 94% electrified and seems to be highest amongst larger countries.

Can't see pricing, can't even see demo video on the home page without logging in.

Looks great! Do you mind talking about your tech stack? Do you build on top of Tessaract or do you use a custom model?

Tangential - I just want a decent (financial transaction) Table to text conversion that can retain the table structure well enough (e.g. merged cells) and have tried everything under the sun short of fine tuning my own model, including all the multimodal LLMs. None of them work very well without a lot of prompt engineering on case by case basis. Can this help? How can I set it up with a large number of pdfs that are sorted by type and extract tabular information? Any other suggestions?

Thank you very much!

What's the name of the layout recorgniser model? I did not have a good experience extracting layout from tables, especially those without column boundaries (space instead of lines to demarcate boundaries)

It's trivial to run a proxy server that routes all OpenAi calls to another LLM, even local ones. See litellm-proxy.

Explanation from Andrej karpathy makes sense on why: ''' "8x7B" name is a bit misleading because it is not all 7B params that are being 8x'd, only the FeedForward blocks in the Transformer are 8x'd, everything else stays the same. Hence also why total number of params is not 56B but only 46.7B. '''

Let me put a counter point to the opening remark. We do not (just) inherently trust people to do the right thing. Law and order, refined and (somewhat, however faultily) applied over the course of decades have programmed us to not do the wrong thing (vs doing the right/ethical thing which cannot always be coded into the laws). Law and order needs to catch up to the advancement in technology and specifically in AI for us to be able to trust all the models that will be running our lives in near future.

Warning - The page played a loud music when I clicked on something. Most stuff seems to be under development - so what is it?

- Do you have plans to support other connectors, specifically OneDrive? - Do you have a demo somewhere? From the website and screenshots, it's not clear the functionalities you offer. A few min long screencast would help. - How do you differ youself from Quivr? Seems like another open source alternative and has some nice feature. Thanks for this. I will try to use this and see how well it works for my use case.

Since recovering from this outage, I see a search with Bing, rather than browser option in GPT4 drop down.

Thank you! I am not a native speaker and I found this helpful. :)

This is excellent! I just followed along the routine and 2 small feedbacks: 1. Please show the instructions before the stretch begins. Right now it says get ready for the next stretch. It would be useful to be able to read instructions before the stretch starts. 2. Beeps can be slightly shorter. In long term, I can see it getting a little annoying. Other than that, excellent work and great illustrations. Thank you!

Thanks a lot! Do you _have_ to do vectorization and querying with the same LLM? Can someone do vectorization with 1 and do querying with reevant chunks with another?

Good explanation. Thanks! Can the first part, i.e. vectorizing and finding relevant chunks be done with any LLM (e.g. a self hosted one) and the second part, i.e. querying relevant chunks be done with OpenAI?

Can the vectorization of chunks and finding context close to query be done with any LLMs and then only relevant chunks be sent to OpenAI?

I signed up immediately to try to browse the catalog and get a feel of the website. Very disappointed that the membership comes after you sign up. I would rather not give my email/name without upfront knowledge of price and catalog. Please put pricing details on the homepage and a catalog (maybe without price info, like Costco does) that can be browsed without sign up.