Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

github.com

Post reply on HN
Print view View original

51–60 of 255 posts

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#51

Post by HenryNdubuaku »

rsolva wrote: post #48

Can it summarize text it fetches? Come to think of it, this could be a nice model to have as the first pass in a more complex agent system where Needle hands of the results of a tool call to a larger model. I will defiantly play around with this!

The codebase is fully open, feel free to play around!

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#52

Post by giancarlostoro »

bityard wrote: post #50
giancarlostoro wrote: post #44

Earlier quoted context omitted.

I know we all think of bad things when we hear "short form video" but short demos can do a LOT for any project, shows the user how its used, what it looks like, what it solves, etc all in anywhere from 15 seconds to a couple of minutes, doesn't need to be ultra fancy, screen recording is fine. :)

Since there is no GUI here, I feel like a simple plaintext chat transcript would be both 100x smaller and 100x easier to read. (Not to mention accessible.)

Sure, and we've seen those terminal screen recorders that give you back a replayable demo, that could work too.

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#53

Post by bityard »

This is pretty much exactly what I want for Home Assistant. I yell out, "Computer! Lights!" and it toggles the lamp in the room on or off. (I mean I can do that now, I think, but probably with a much larger model.)

I haven't played with it yet, but does it ever return anything other than a tool call? What are the failure modes? What if it doesn't understand the request? Does it ever say it can't find a tool? Does it get confused if there are two similar (but different) tools? Can it chain tools together (e.g. one tool to look up and address and another to get directions to the address)?

I mean, I plan on downloading the model later tonight and finding out for myself, but since I'm stuck at work right now, I figured I'd ask anyway...

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#54

Post by cmrdporcupine »

Balinares wrote: post #26
cmrdporcupine wrote: post #10

This is very cool I'm going to try to carve out some time to try building this into my MOO system ( https://codeberg.org/timbran/moor / https://timbran.org/moor.html ) as alternative command parser front end.

Man, I love that there are still people writing new MOO servers in 2026. Any game out there already running on mooR?

Many people tease that they will, and start... but then kinda stop. But mostly just been building my own bespoke thing on my own bespoke platform, and kinda running out of steam because I need to make $$ instead.

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#55

Post by BoredPositron »

I source old, defective high-end radios with timeless designs from brands like Grundig or Braun, and replace the original hardware with a Raspberry Pi while using the original audio parts to build custom smart speakers. Reliable hotword detection and voice command recognition have been a persistent challenge over the years, but whisper and other small models have helped enormously. At the moment I have ollama running on my server with qwen 9b which works fine but a 26M that could be deployed on the pi itself would be amazing.

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#59

Post by z3ugma »

I don't really understand what this is for... there is a lot of ML-researcher talk on the GH page about the model architecture, but how should I use it?

Is it a replacement for Kimi 2.7, Claude Haiku, Gemini Flash 3.1 lite, a conversational LLM for the situations where it's mostly tool-calling like coding and conversational AI?

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#60

Post by HenryNdubuaku »

bityard wrote: post #53

This is pretty much exactly what I want for Home Assistant. I yell out, "Computer! Lights!" and it toggles the lamp in the room on or off. (I mean I can do that now, I think, but probably with a much larger model.) I haven't played with it yet, but does it ever return anything other than a tool call? What are the failure modes? What if it doesn't understand the request? Does it ever say it can't find a tool? Does it…

Let me know what you think!
Post reply on HN