Claude usagemaxxing guide:
- minimize use of subagents -> try to coordinate work in the main agent
- don't use xhigh or max reasoning -> use high
- don't compact sessions -> start new sessions for new tasks
- don't break cache -> maintain a HANDOFF.md file that tracks future work for new sessions to kick off
GPT 6.1 Terra is incredibly lazy.
I asked GPT 6.1 Terra to perform a test run on a personal Computer Use benchmark, but it stopped very early because it was "too complex". This has happened 3 times now.
Just use Sol for anything agentic.
First time doing a $200 plan.
And it proves that the best way to get users to pay more for AI isn't by nerfing usage, but by creating a damn good model.