Ok this is quite cool research and ultimately must be the eventual architecture of agents. In the limit, AI will obviously be better at determining its own harness once it sees the task at hand, than us being able to do this in advance: https://x.com/levie/status/2109788979952…

Pedro Domingos@pmddomingos1d ago

That didn’t take long: the model swallows the harness. https://arxiv.org/abs/2609.35738