News for hackers. Stuff that matters.

A comment on Expensively Quadratic: The LLM Agent Cost Curve.

Re:Expensively Quadratic: The LLM Agent Cost Curve by collinwilkins on Monday February 16, 2026 @11:59AM (#47037381)
what i've learned running multi-agent workflows... >use the expensive models for planning/design and the cheaper models for implementation >stick with small/tightly scoped requests >clear the context window often and let the AGENTS.md files control the basics
[ Parent | on HN ]
Re:Expensively Quadratic: The LLM Agent Cost Curve by rubicon33 on Monday February 16, 2026 @12:05PM (#47037462)
there’s something of a paradox there. Reduce the context window and work on smaller/tightly scoped requests? Isn’t the whole value proposition that I can work much faster? To do that, I naturally try to describe what I want at a higher, vaguer level.
[ Parent | on HN ]
Re:Expensively Quadratic: The LLM Agent Cost Curve by readyforbrunch on Monday February 16, 2026 @01:53PM (#47038719)
That's where something like openspec and beads come in. You work high level, create a spec and break it down into beads (small tasks). Your main agent then spawns workers that perform a task with limited scope.
[ Parent | on HN ]