> In my experience the use of agents and harnesses and other scaffolding around them doesn’t improve the performance of LLMs much

I have to say - that seems straight-up crazy to me. Would you mind digging into that discussion?

As just one example - in a harness I can ask an agent to confirm everything it says via a second sub agent - which dramatically improves the output. It almost entirely solves the problem of hallucinations. You don't see that as an improvement?