We are releasing our inverse dynamics model. The model outperforms orders-of-magnitude larger models in predicting a user's next action (mouse movements, keystrokes) based on video frames.
This release supports our long-term approach of learning from long-horizon human data.
If you want models to work on tasks for months, you have to train on months-long trajectories.
Today we release an inverse dynamics model for screencasts.
It watches a screencast and recovers the actions behind the pixels: keys, clicks, cursor movement and scrolls. 🧵(1/5)
We’re p(doom), an AGI research lab. We’ll pay you $300/month to record your screen while working.
If your work is open-source and involves research, engineering, design, editing, or similar long-horizon digital work, fill out the form: https://t.co/NekbmBW6F5
@Cobratate What a looser he is. Embarrassing.. how can you look your family onto their eyes? Because of you your whole family lost their honour.. disgrace to your ancestors
@Cobratate What a looser he is. Embarrassing.. how can you look your family onto their eyes? Because of you your whole family lost their honour.. disgrace to your ancestors
@CountAtlas@Cobratate What a looser he is. Embarrassing.. how can you look your family onto their eyes? Because of you your whole family lost their honour.. disgrace to your ancestors
@Cobratate What a looser he is. Embarrassing.. how can you look your family onto their eyes? Because of you your whole family lost their honour.. disgrace to your ancestors