Hey guys! I’m Neel, been holed up in our south park office for the past year working on model training. excited to share our research! This is a preview of a very different type of computer use model—we train on the internet. Specifically we have 11 million hours of computer video stored on our storage cluster (previously shared https://news.ycombinator.com/item?id=45438496 !) and the model can work in 30 FPS. Since…
The First Fully General Computer Action Model
41–50 of 85 posts
Re: The First Fully General Computer Action Model
#42I wanted to comment though that your title is not doing you any favors, and I suspect that is why this is not getting more traction (which it deserves). I fully expected some half baked GitHub repo, but instead found something truly awesome.
To use your own words, Neel, “ a very different type of computer use model” would have had me clicking faster. I’m not great at titles, however, and maybe there are better ideas out there.
Anyway, can’t wait to see how this develops! Especially looking forward to the CAD work.
Re: The First Fully General Computer Action Model
#43Can you prompt it or is it strictly Copilot-style prediction?
Re: The First Fully General Computer Action Model
#44Re: The First Fully General Computer Action Model
#45Hey guys! I’m Neel, been holed up in our south park office for the past year working on model training. excited to share our research! This is a preview of a very different type of computer use model—we train on the internet. Specifically we have 11 million hours of computer video stored on our storage cluster (previously shared https://news.ycombinator.com/item?id=45438496 !) and the model can work in 30 FPS. Since…
Any benchmark comparisons to Fara-7B or Sonnet 4.6, Qwen 3.5 etc.?
Re: The First Fully General Computer Action Model
#46Re: The First Fully General Computer Action Model
#47Re: The First Fully General Computer Action Model
#48Re: The First Fully General Computer Action Model
#49Hey guys! I’m Neel, been holed up in our south park office for the past year working on model training. excited to share our research! This is a preview of a very different type of computer use model—we train on the internet. Specifically we have 11 million hours of computer video stored on our storage cluster (previously shared https://news.ycombinator.com/item?id=45438496 !) and the model can work in 30 FPS. Since…
11 million hours of data is a lot, did you have to synthesize it at all, or was it purely collected?
Re: The First Fully General Computer Action Model
#50This seems like really great research, and the first time I’ve seen overwhelming praise on HN. Congrats! I wanted to comment though that your title is not doing you any favors, and I suspect that is why this is not getting more traction (which it deserves). I fully expected some half baked GitHub repo, but instead found something truly awesome. To use your own words, Neel, “ a very different type of computer use mode…