Post

Inverse scaling of reasoning models a research collab demonstrated that there are certain types of tasks where all top reasoning models do WORSE the longer they think things like getting distracted by irrelevant info, spurious correlations, etc. www.arxiv.org/abs/2507.14417

That's very similar to what I can the "breakdown threshold": Especially with agents, there is a limit number of bullet points/instructions that you can feed to the LLM. Add just one more and everything falls appart (tool calls become unreliable AF, constraints are half-followed, etc)