The First Fully General Computer Action Model • Hacker News Board

Re: The First Fully General Computer Action Model

#81

Post by url00 » Thu, Feb 26, 2026, 4:25 PM UTC

nee1r wrote: post #53

sp1nningaway wrote: post #30

May I suggest a driving demo in a parking lot with a mannequin instead of a real world video where it drives way too close to a pedestrian? Otherwise, very cool and exciting!

safety was important for the demo, the model didn't have access to the brake or accelerator.

Frankly, this comment does little to avail the parent's point - doing this on the open road was both illegal and reckless. It reflects extremely poorly on your character and the project as a whole.

Re: The First Fully General Computer Action Model

#82

Post by causal » Thu, Feb 26, 2026, 4:30 PM UTC

haskellandchill wrote: post #80

I thought it was a good write up but did anyone catch the ending comment? > We believe artificial general intelligence will be created within our lifetimes, and likely within the next decade. Maybe within our lifetimes (if you are young) but I find it highly unlikely within the next decade.

That's just like, your opinion man

Re: The First Fully General Computer Action Model

#83

Post by causal » Thu, Feb 26, 2026, 4:45 PM UTC

The lack of benchmarks and light demos have me skeptical... The methods seem interesting, and maybe does unlock something novel, but it's odd to go into so much depth on the methods and leave so much wanting in the results?

Re: The First Fully General Computer Action Model

#84

Post by upmind » Thu, Feb 26, 2026, 5:41 PM UTC

Saw this a few days ago, looks really cool! How many params is the model? Did you fine tune or train from scratch? Are you hiring?

Re: The First Fully General Computer Action Model

#85

Post by famouswaffles » Fri, Feb 27, 2026, 2:46 PM UTC

causal wrote: post #83

The lack of benchmarks and light demos have me skeptical... The methods seem interesting, and maybe does unlock something novel, but it's odd to go into so much depth on the methods and leave so much wanting in the results?

It's probably much worse than VLMs on the computer use benchmarks out there. A lot of those benchmarks would be very hard to complete without the intelligence that arises from text pretraining.