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

    Prompting Claude with a goal, an effort level and a way to check its work

    A Claude user says most tasks need no elaborate instructions; they suggest talking to the model like a coworker.

    Boris ChernyBC
    Danielle Fong 🔆DF
    2 Sources, ,

    TLDR

    A Claude user says prompts mattered more in the Sonnet 3.5 days. Now, they advise telling Claude what to do, how much effort to spend and how it should verify the result, rather than giving overly prescriptive instructions for most tasks.

    Combined views

    222.6K

    2 Sources, first seen 2h ago

    Combined views

    222.6K

    2 Sources, first seen 2h ago

    3.9K likes
    2h ago
    first seen 2h ago
    3.9K likes
    259 comments
    2.7K saves
    183 reposts
    259 comments
    2.7K saves
    183 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

    2 Sources

    Boris Cherny@bchernyI am surprised that people are surprised this is how I prompt Claude. Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out. Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model: 1. What you want it to do 2. How much effort you want it to spend 3. How it should verify that it did the right thing2h
    Danielle Fong 🔆@DanielleFongmake it really good. make it beautiful and amazing. use lots of tokens and iterate until it's really great. -- the buddha1h

    2 Sources

    Boris Cherny@bchernyI am surprised that people are surprised this is how I prompt Claude. Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out. Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model: 1. What you want it to do 2. How much effort you want it to spend 3. How it should verify that it did the right thing2h
    Danielle Fong 🔆@DanielleFongmake it really good. make it beautiful and amazing. use lots of tokens and iterate until it's really great. -- the buddha1h