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

    Jev AI model reportedly plays Super Mario Bros.

    A user credits fast inference and structured outputs for making Jev surprisingly good for real-time use cases.

    Kyle RussellKR
    Faadil ShaikFS
    aizk ✡️A
    3 Sources, ,

    TLDR

    A user says they got @typesafeai’s new Jev model to play Super Mario Bros. They credit its fast inference and structured outputs for what they describe as surprisingly good real-time performance.

    Combined views

    283.9K

    3 Sources, first seen 22d ago

    Combined views

    283.9K

    3 Sources, first seen 22d ago

    2.6K likes
    22d ago
    first seen 22d ago
    2.6K likes
    93 comments
    826 saves
    198 reposts
    93 comments
    826 saves
    198 reposts

    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

    3 Sources

    Faadil Shaik@faadilhshaikgot @typesafeai’s new model Jev to play Super Mario Bros. fast inference + structured outputs makes it surprisingly good for real time use cases. I'm excited to see what can be done with these new models!22d
    aizk ✡️@AizkmusicMelee meets Jev, but running on Featherless! We actually have our own classifier endpoint -- here it's Gemma 4 reading the game and making a decision every half-second. I wired up Gemma into libmelee so it continuously can read the game state and gave it basic instructions to approach and attack. So far, Fox is doing pretty decent against CPU level 3. Extremely fast and cheap rapid decision making is the future. (Actually it's old tech everyone's rediscovering, but I digress) What should we point the classifier to next? If you're interested in this endpoint, let us know!20d
    Kyle Russell@kylebrussellRT @Aizkmusic: Melee meets Jev, but running on Featherless! We actually have our own classifier endpoint -- here it's Gemma 4 reading the…20d

    3 Sources

    Faadil Shaik@faadilhshaikgot @typesafeai’s new model Jev to play Super Mario Bros. fast inference + structured outputs makes it surprisingly good for real time use cases. I'm excited to see what can be done with these new models!22d
    aizk ✡️@AizkmusicMelee meets Jev, but running on Featherless! We actually have our own classifier endpoint -- here it's Gemma 4 reading the game and making a decision every half-second. I wired up Gemma into libmelee so it continuously can read the game state and gave it basic instructions to approach and attack. So far, Fox is doing pretty decent against CPU level 3. Extremely fast and cheap rapid decision making is the future. (Actually it's old tech everyone's rediscovering, but I digress) What should we point the classifier to next? If you're interested in this endpoint, let us know!20d
    Kyle Russell@kylebrussellRT @Aizkmusic: Melee meets Jev, but running on Featherless! We actually have our own classifier endpoint -- here it's Gemma 4 reading the…20d