This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Tim Duffy
timfduffy.com
did:plc:mk7qlghvwdjjayu5x3bo3lx2
I often see claims that because RL signal requires at least one successful rollout, it can only reinforce existing capabilities, not add new ones. This is not true, the update from one RL step can change a model's thinking to allow it to succeed on a problem it couldn't get before
2025-12-28T15:45:11.435Z