News for hackers. Stuff that matters.
Re:Expensively Quadratic: The LLM Agent Cost Curve by tekacs on Monday February 16, 2026 @04:53AM (#47033063)
I think that's reasonable, but then they should have the ability for the agent to, on the next call, override it. Even if it requires the agent to have read the file once or something.

In the absence of that you end up with what several of the harnesses ended up doing, where an agent will use a million tool calls to very slowly read a file in like 200 line chunks. I think they _might_ have fixed it now (or agent-fixes, my agent harness might be fixing it), but Codex used to do this and it made it unbelievably slow.

Re:Expensively Quadratic: The LLM Agent Cost Curve by reactordev on Monday February 16, 2026 @10:01AM (#47035858)
You’re describing peek.

An agent needs to be able to peek before determining “Can I one shot this or does it need paging?”

Re:Expensively Quadratic: The LLM Agent Cost Curve by tekacs on Tuesday February 17, 2026 @05:54PM (#47054593)
Yep, I previously implemented it under that name in my own harness. That being said, there is value in actually performing a normal read, because you do often complete it on that first glance.
Re:Expensively Quadratic: The LLM Agent Cost Curve by reactordev on Thursday February 19, 2026 @11:17AM (#47075368)
Confession, I too implemented a “smart” read. A read unless it’s over a size, then it’s paged, or if it’s a specific format, a summary. However, I also supply `cat`