• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Deepagents gets a new file-reading format

    A LangChain team member says the team's evaluations show 15% fewer edit_file errors and 10% lower total input token usage with the new format.

    SR
    1 Source, 16d ago, first seen 16d ago

    TLDR

    A LangChain team member announced a change to how deepagents reads files. They say the new format reduced edit_file errors by 15% and total input token usage by 10% in the team's evaluations, describing it as one of several small agent optimizations underway.

    Combined views

    24.2K

    1 Source, first seen 16d ago

    likes

    Combined views

    24.2K

    1 Source, first seen 16d ago

    146 likes
    146
    29 comments
    92 saves
    11 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    29 comments
    92 saves
    11 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    @sydneyrunklewe just changed how deepagents read files! our evals show that this new format reduces edit_file errors by 15% AND total input token usage by 10% the little things really add up w/ agents; we're hard at work on these small but mighty optimizations at @LangChain

    1 Source

    @sydneyrunklewe just changed how deepagents read files! our evals show that this new format reduces edit_file errors by 15% AND total input token usage by 10% the little things really add up w/ agents; we're hard at work on these small but mighty optimizations at @LangChain