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

    A Devin prompt claimed to support hours of autonomous autoresearch

    A user says the prompt sets a budget and time limit, then asks sub-Devins to work in parallel.

    Jared PalmerJP
    1 Source, 2h ago, first seen 2h ago

    TLDR

    A user says they spent about a week experimenting nightly with Devin and autoresearch. Their prompt asks Devin to improve verifiable metrics within a budget and time limit, track its progress, and manage its own pull requests. They say Devin can run autonomously for hours with the prompt, and that encouragement such as “boil the ocean” seems to improve exploration and make models less likely to give up early.

    Combined views

    4.6K

    1 Source, first seen 2h ago

    Combined views

    4.6K

    1 Source, first seen 2h ago

    83 likes
    83 likes
    8 comments
    83 saves
    3 reposts
    8 comments
    83 saves
    3 reposts
    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    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

    Jared Palmer@jaredpalmerI’ve been experimenting with Devin and autoresearch every night for the past week or so. The prompt I’ve been using for is pretty simple: `I want you to do autoresearch to improve {verifiable metric(s)}. Hill climb. You have a budget of ${budget} and {time limit}. Use sub-devins to parallelize work. Track your plans and progress as you go in the filesystem. Work methodically. Create abstractions if you need to to help you verify faster. Manage your own PRs/babysit code review and merge as you see fit until you get a candidate that passes gates you set. Boil the ocean. Believe in yourself. You got this. {+more confidence/hype statements}` After you have the setup you like, just make this into a skill and turn on automatic code review. With this prompt, Devin can run for hours autonomously. Funny enough, the “boil the ocean” and hype statements seem to yield better exploration behavior and make most models less likely to give up early or reward hack changes/ship incremental fallback stuff. Inspiration for this was @jarredsumner’s prompts during his Riemann work.2h