gabegrand / world-models Goto Github PK

Hi!

Very cool work! It would be nice to have the model checkpoints on the Hugging Face Hub rather than a Dropbox link

Some of the benefits of sharing your models through the Hub would be:

• versioning, commit history and diffs
• repos provide useful metadata about their tasks, languages, metrics, etc that make them discoverable
• multiple features from TensorBoard visualizations, PapersWithCode integration, and more
• wider reach of your work to the ecosystem

Creating the repos and adding new models should be a relatively straightforward process if you've used Git before. This is a step-by-step guide explaining the process in case you're interested. Please let us know if you would be interested and if you have any questions.

I am using https://v1.probmods.org/play-space.html. I cut and paste the tug of war example but get the error query not defined

Hi @gabegrand friendly ping
Reality is indeed isomorphic to our mental semantic spaces and this paper seems very interesting!

If I understand correctly the process described in the paper is in two phases and the first is to use an LLM to generate a program, such as Codex or GPT-4.
The thing is, if we look at the reference benchmark leaderboard on code generation, Codex has 28.81% in accuracy, GPT-4 has a mere 67%, while the recent paper Reflexion, which is a modification/augmentation of GPT-4 has a remarkable accuracy of 91%
https://paperswithcode.com/paper/reflexion-an-autonomous-agent-with-dynamic