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

    Elvis Saravia Describes GPT-6 Astra Replication Technique

    Elvis Saravia shares steps to replicate impressive demos from tweets using the model.

    EL
    2 Sources, 25d ago, first seen 25d ago

    TLDR

    @omarsar0 posted that a prompting approach works really well with GPT-6 Astra. The method starts by giving the model a tweet of an impressive Astra demo. It then asks Astra medium to replicate the demo to the best of its ability while accepting any extra instructions and adaptations the user supplies. A goal such as providing proof of results is set so the model has a target to compare against after the first run.

    Combined views

    18.4K

    2 Sources, first seen 25d ago

    Combined views

    18.4K

    2 Sources, first seen 25d ago

    108 likes
    108 likes
    16 comments
    104 saves
    17 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    16 comments
    104 saves
    17 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

    2 Sources

    @omarsar0This works really well with GPT-6 Astra: Give it a tweet of an impressive Astra demo. Ask Astra (medium) to replicate it to the best of its ability and giving it whatever extra instructions and adaptations you want. Set a /goal like provide proof of the results so it has something to compare to. After the first run, switch to Astra (max) and give it instructions to polish. And you can keep doing this iteratively to keep improving results. So there is one component to build and one to optimize/tune. I think it works well because it breaks the problem down and allows the models to focus efforts as opposed to trying to use lots of tokens for many things at once (usually lower quality results). This can essentially be done in one go using subagents and /goal.

    2 Sources

    @omarsar0This works really well with GPT-6 Astra: Give it a tweet of an impressive Astra demo. Ask Astra (medium) to replicate it to the best of its ability and giving it whatever extra instructions and adaptations you want. Set a /goal like provide proof of the results so it has something to compare to. After the first run, switch to Astra (max) and give it instructions to polish. And you can keep doing this iteratively to keep improving results. So there is one component to build and one to optimize/tune. I think it works well because it breaks the problem down and allows the models to focus efforts as opposed to trying to use lots of tokens for many things at once (usually lower quality results). This can essentially be done in one go using subagents and /goal.