I deleted slow, expensive LLM turns in coding agents with Jev | Hacker News - But Better

I deleted slow, expensive LLM turns in coding agents with Jev tawfeks.github.io

DecisionKit pre-calibrates decisions per coding agent, deleting slow, expensive LLM turns: ↓2–11× input tokens, ↓4.6× output tokens, ↓61–85% session cost.

2 points•respectattentio•8 days ago•0 comments•

#llm #coding #expensive #llm turns #expensive llm #deleted #jev #agents

0 comments

No comments yet.

Related stories

Show HN: Groundtrack – Continual learning for coding agentsgroundtrack.dev
Hacker News · 1 points · about 12 hours ago
Show HN: Foremerge – Catch intent conflicts between parallel coding agentsgithub.com
Hacker News · 45 points · 9 days ago
Show HN: Ax-check.com – Can agents use your product?ax-check.com
Hacker News · 37 points · 13 days ago
Show HN: Relay – a harness for AI coding agents that recover and verifyrelayevals.com
Hacker News · 3 points · 1 day ago
Harness Engineering 101: How Coding Agents Actually Workdev.to
DEV Community · 2 points · 6 days ago
Show HN: SideKernel – a usable MicroVM sandbox for AI coding agents on macOSgithub.com
Hacker News · 1 points · 1 day ago