Looking at the diagram in the gh repo, it looks like this is entirely jev. Are there any examples of people having a big model like Fable handle high level goals?
Frontier reasoning models do pretty well in Pokemon: <a href="https://github.com/benchflow-ai/pokemon-gym" rel="nofollow">https://github.com/benchflow-ai/pokemon-gym
The interesting thing here imo is the cost and latency. So far we're at 4 badges for less than $0.5
lwarfield · · focus · HN ↗
pancomplex · · focus · HN ↗
The interesting thing here imo is the cost and latency. So far we're at 4 badges for less than $0.5