Hacker News new | past | comments | ask | show | jobs | submit
alexfortin | on: GLM-5.1: Towards Long-Horizon Tasks
Try lowering thinking level with GLM-5.1, to me that seems to have an impact on mitigating the blocking behaviour.
stavros | parent
Hmm I'll try that, but OpenCode shows me the thinking and it's not even doing that. I'm just getting no tokens from it at all.