Post

it’s nuts to think how easy it is to do this to yourself and not realize it how many times did i use o3-mini-high bc i really just wanted that extra juice, that mini high, regardless if i really NEEDED it

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)

The way I've found to get past this is to feed all the instructions (prompt, tools, etc) into a LLM and just ask to re-write all the prompts and documentation without useless or redundant instructions. Drops the prompt sizes massively (60~80% in my case) and makes a HUGE performance boost

i feel like claude code’s subagents also deal with this by just taking it out-of-band