Thoughtful(@thoughtfullab):We built a new task to test AI research capabilities! Agents asked to use @tinkerapi from @thinkymachines to train a model on logic games. That involves writing full training pipeline, running experiments across recipes, and submitting the best model.

Thoughtful

@thoughtfullab

Decide on purpose.

参加 December 2025

4 フォロー中 2.2K ファン

Thoughtful@thoughtfullab

2026.04.16 20:53

We built a new task to test AI research capabilities! Agents asked to use @tinkerapi from @thinkymachines to train a model on logic games. That involves writing full training pipeline, running experiments across recipes, and submitting the best model.