Comment by weird-eye-issue
5 hours ago
Sounds like you completely lack all reading comprehension ability
LLMs sometimes like to execute one-off Python scripts to make edits to files rather than just calling the edit tool directly. Both are tool calls so saying that you should have it write code instead of doing tool calls makes no sense because writing code is a tool call for it...
[flagged]
Are you saying scripts from agents are deterministic? :)
Why don't you try to dispove me. Yes, they are _more_ deterministic than tool calls and consume less tokens.
2 replies →
They're talking about writing a file with a harness-native Edit tool. They're saying the agents aren't doing that, but are using ad-hoc methods of writing the files. (My agents seem to prefer see these days.)
Why do you think your agents prefer to create scripts instead of doing tool calls these days?
I wonder, is it easier to modify a script that agent wrote before to satisfy your prompt, or is it easier to write a new one from scratch each time a retry happens?
Are input tokens more expensive than output tokens?
2 replies →