someguy101010

Yea it seems to be very jagged so far but will be training on more datasets.

I just added evals for existing datasets and some classic controls problems.

Will likely look for more commercial datasets and synthetic data too.

I’m funding personally in short term but if I can find some compute can see how well this scales!

a foolish consistency is the hobgoblin of little minds

been working on a javascript runtime for agents and recently got grpc working with modal!

Our cloud platform supports gpu but we haven’t shipped it yet. I’ll be sure to update guide when that’s shipped!

Totally agree. I’ve built a bunch of harnesses for Minecraft and a specialized one will almost certainly out preform a general purpose one.

I believe the way we advance the capabilities for general computer use is to to attempt harder and harder tasks with it, and build up the necessary infrastructure to accomplish it along the way.

Even when we don’t achieve the goal, the infrastructure we build is often useful for easier and more obtainable goals as well.

If your computer use environment can pilot Minecraft, it can also probably do your taxes