Hacker News: shekhar101

New comment by shekhar101 in "HopTab – Open source macOS app switcher and tiler that replaces Cmd+Tab"

shekhar101 — Sun, 22 Mar 2026 14:21:20 +0000

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

New comment by shekhar101 in "Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon"

shekhar101 — Tue, 10 Mar 2026 22:17:54 +0000

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?

New comment by shekhar101 in "Show HN: Tommy – Turn ESP32 devices into through-wall motion sensors"

shekhar101 — Thu, 23 Oct 2025 20:54:35 +0000

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...

New comment by shekhar101 in "Nvidia's new 'robot brain' goes on sale for $3,499"

shekhar101 — Mon, 25 Aug 2025 23:20:41 +0000

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

New comment by shekhar101 in "Gemma 3 270M re-implemented in pure PyTorch for local tinkering"

shekhar101 — Wed, 20 Aug 2025 17:06:19 +0000

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.

New comment by shekhar101 in "Show HN: OWhisper – Ollama for realtime speech-to-text"

shekhar101 — Thu, 14 Aug 2025 22:53:40 +0000

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.

New comment by shekhar101 in "Show HN: I built a playground to showcase what Flux Kontext is good at"

shekhar101 — Thu, 10 Jul 2025 03:15:07 +0000

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.

Magnifier on Mac [video]

shekhar101 — Thu, 15 May 2025 18:22:40 +0000

Article URL: https://www.youtube.com/watch?v=R3rBlZGEssw

Comments URL: https://news.ycombinator.com/item?id=43997793

Points: 1

# Comments: 0

New comment by shekhar101 in "Show HN: Index – New Open Source browser agent"

shekhar101 — Wed, 23 Apr 2025 23:07:20 +0000

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?

New comment by shekhar101 in "Show HN: Index – new SOTA Open Source browser agent"

shekhar101 — Wed, 23 Apr 2025 23:02:01 +0000

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.

Terence Tao on how we measure the cosmos [video]

shekhar101 — Fri, 11 Apr 2025 19:19:16 +0000

Article URL: https://www.youtube.com/watch?v=YdOXS_9_P4U

Comments URL: https://news.ycombinator.com/item?id=43657449

Points: 1

# Comments: 0

The Most Useful Thing AI Has Ever Done [video]

shekhar101 — Mon, 17 Feb 2025 19:09:24 +0000

Article URL: https://www.youtube.com/watch?v=P_fHJIYENdI

Comments URL: https://news.ycombinator.com/item?id=43082264

Points: 1

# Comments: 1

New comment by shekhar101 in "Show HN: A website that heatmaps your city based on your housing preferences"

shekhar101 — Fri, 07 Feb 2025 18:41:03 +0000

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

New comment by shekhar101 in "Show HN: DeepSeek Your HN Profile"

shekhar101 — Tue, 28 Jan 2025 23:32:31 +0000

> 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. :)

New comment by shekhar101 in "Show HN: A daily digest for reMarkable"

shekhar101 — Tue, 14 Jan 2025 19:44:59 +0000

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.

New comment by shekhar101 in "Caltrain's new electric trains"

shekhar101 — Thu, 22 Aug 2024 22:17:36 +0000

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

New comment by shekhar101 in "Show HN: Create interactive vector animations with Lottielab Interactivity"

shekhar101 — Fri, 16 Aug 2024 17:15:54 +0000

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

New comment by shekhar101 in "Show HN: LLM-aided OCR – Correcting Tesseract OCR errors with LLMs"

shekhar101 — Fri, 09 Aug 2024 17:44:02 +0000

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

Steroids Are Awesome [video]

shekhar101 — Mon, 17 Jun 2024 16:29:22 +0000

Article URL: https://www.youtube.com/watch?v=lmClPGvdWTI

Comments URL: https://news.ycombinator.com/item?id=40707542

Points: 3

# Comments: 0

New comment by shekhar101 in "Show HN: Tarsier – Vision utilities for web interaction agents"

shekhar101 — Wed, 15 May 2024 18:25:44 +0000

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?