Mastodon Feed
Boosted by pixxl:
haskal@types.pl ("witch hat hacker :verified_dragon: :vt1: :vt2:") wrote:
reminded of Gloaguen et al "Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?" https://arxiv.org/abs/2602.11988
Surprisingly, we find that providing context files does not generally improve task success rates, while increasing inference cost by over 20% on average. This observation holds across different LLMs, coding agents, and for both LLM-generated and developer-committed context files.