Suggestion: publish a live demo of the "needle playground". It's small enough that it should be pretty cheap to run this on a little VPS somewhere!
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
11–20 of 255 posts
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#12Suggestion: publish a live demo of the "needle playground". It's small enough that it should be pretty cheap to run this on a little VPS somewhere!
thanks, yeah, the problem is just handling scale, we don't have the infra ready to go, but anyone can do that. Its easy for people to run on their laptops straight up. Will try the VPS route.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#13This 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.
Thanks, let us know how it goes!
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#14Suggestion: publish a live demo of the "needle playground". It's small enough that it should be pretty cheap to run this on a little VPS somewhere!
thanks, yeah, the problem is just handling scale, we don't have the infra ready to go, but anyone can do that. Its easy for people to run on their laptops straight up. Will try the VPS route.
Alternatively, record a video that showcases it.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#15Earlier quoted context omitted.
thanks, yeah, the problem is just handling scale, we don't have the infra ready to go, but anyone can do that. Its easy for people to run on their laptops straight up. Will try the VPS route.
Alternatively, record a video that showcases it.
Ok, will do that now!
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#16Suggestion: publish a live demo of the "needle playground". It's small enough that it should be pretty cheap to run this on a little VPS somewhere!
Should be quick and easy with WebGPU, too.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#17FYI, distilling Gemini is explicitly against the ToS:
"You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio). You also may not attempt to reverse engineer, extract or replicate any component of the Services, including the underlying data or models (e.g., parameter weights)."
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#18Can this be a Siri-like core? Set me a timer, tell me what’s the weather, etc. Here is transcribed text and available list of tools for the model to call, and voice the output.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#19FYI, distilling Gemini is explicitly against the ToS: "You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio). You also may not attempt to reverse engineer, extract or replicate any component of the Services, including the underlying data or models (e.g., parameter weights)."
Oh no! They stole the model weights!
Distillation "attacks" is such bullshit
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#20FYI, distilling Gemini is explicitly against the ToS: "You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio). You also may not attempt to reverse engineer, extract or replicate any component of the Services, including the underlying data or models (e.g., parameter weights)."
I think GLM 5.1 or Kimi 2.6 could substitute for this type of purpose.