What's happening today?
Trying to build webgazer in python xD
Got FaceMesh from google mediapipe ready. Now I can get 468 3D landmark coordinate for face, and 52 blendshapes (idk what this means, will fig it out)
Ref: https://t.co/leVFCYaxk1
@koltregaskes@btibor91@rileybrown@Obsidian i did not know about the extension either. Thanks tibor.
i generally just ask claude to open chrome with remote debugging so that it can directly talk with the browser.
@threepointone I built something like what you want … it’s crude …
GH link: https://t.co/K6PrizpSXS
initially it was supposed to be gaze tracking, but hand tracking was a bit more robust
Well this sunday, I wanted to continue my gaze tracking project, and tbh its difficult. I got the mouse movement to stabilise using ema, but the edges were left out.
so switched to using index finger for mouse movement
added gestures for:
- click
- scroll
@ottogin1 ohh this is grok 4 heavy model from https://t.co/mqa1KV2kJu.
i don’t know what the interface means though … i dont pay for super grok subscription
if you have been living under a rock for the past 7 months and have no clue about RL and want to understand the current state of RL and GRPO and Agents and VERL and how you can do asynchronous GRPO or DAPO
you should go watch this small talk
well in my neovim editor, i usually have a https://t.co/qYmmhb9kJS file which is like my chats with LLM
it’s like cursor but for neovim
- can search web and answer questions
- can search the current codebase using find and grep to answer questions
- can make changes to file
can take in files as context
and streams the output into the editor
well in my neovim editor, i usually have a https://t.co/qYmmhb9kJS file which is like my chats with LLM
it’s like cursor but for neovim
- can search web and answer questions
- can search the current codebase using find and grep to answer questions
- can make changes to file
can take in files as context
and streams the output into the editor
HF transformers is standardizing variable names for at least decoder-only transformers.
this way I don't have to if-elif-else my way through supporting multiple models for tensor parallelism
tbh w/o HF I don't think we would have had chatGPT at least not in 2022
love you HF
now i can generate completions from multiple llms ... meaning i can generate 5 different options to solve the same thing simultaneously and choose the best one, while you are waiting for your chatgpt to generate one solution ... assuming you dont get rate limited ... meaning i can solve problems way faster than you .. hehehe