31–40 of 255 posts
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!
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.
You can check the very simple docker file there.
Can 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.
Sounds interesting. Got a bunch of errors trying to run it on CPU though. Very likely connected to me running this in a container (unpriv LXC), but figured for 26M CPU would suffice. https://pastebin.com/PYZJKTNk
[0]: http://www.incompleteideas.net/IncIdeas/BitterLesson.html
FYI, 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 find this stuff super fascinating and been thinking about it myself. Maybe one could bootstrap tiny models on a rather 'pure' procedural data set. Neglecting [0] of course... [0]: http://www.incompleteideas.net/IncIdeas/BitterLesson.html
This is really cool. Any plans to release the dataset?