jsd comments on Trust me bro, just one more RL scale up, this one will be the real scale up with the good environments, the actually legit one, trust me bro

[jsd]

I already expect some (probably substantial) effect from AIs helping to build RL environments

I think scraping and filtering MCP servers then RL training to navigate them is largely even if not fully automatable and already being done (cf this for SFT), but doesn’t unlock massive value.