alt Hacker NewsI had the opposite experience. Claude models and its harness feel like they are set to eat tokens for everything, especially if it’s ultracode effort. I have seen it spawn 6 agents and eat my 4-hour quota right in front of me. Codex is on point and follows instructions well even with max effort. I like my analogy of Claude being garrulous and Codex being laconic. If I see more limit hits in same sitting session, I have to rearrange my workflows. my experiments with qwen and deepseek have been good, cant wait to try glm and other models.
Replies
Here is an excerpt from the system prompt for UltraCode (Same for Fable,Opus,Sonnet):
"Ultracode. When a system-reminder confirms ultracode is on, that opt-in is standing: author and run a workflow for every substantive task by default. The goal is the most exhaustive, correct answer you can produce — token cost is not a constraint."
Requesting ultracode is basically asking for maximum token usage. If you want to limit consumption, use medium or high.
Just before I canceled my 20x Max sub I had a day where I had ~15% of my weekly I was trying to burn. I set it on ultracode and because I had set the max agents 32 for another project and forgot, the five research agents ended up spinning up a total of 26 subagents and burned through the remainder of my weekly in the span of 20 minutes before I noticed and shut it down.
“No, not like THAT!”