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

    Gemini 4 reportedly struggles with some coding tasks despite doing well on benchmarks

    Bloomberg, citing people with direct access to the effort, reports that Google’s forthcoming model does less well when employees put it to work than it does on industry benchmarks.

    YI
    TK
    4 Sources, ,

    TLDR

    Bloomberg reports that Gemini 4 has performed well on industry benchmarks but does less well in employee use, according to people with direct access to the effort. They say the model struggles with certain coding tasks as Google prepares to launch it.

    Combined views

    363.5K

    4 Sources, first seen 6h ago

    likes

    Combined views

    363.5K

    4 Sources, first seen 6h ago

    1.1K likes
    6h ago
    first seen 6h ago
    1.1K
    87 comments
    248 saves
    53 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source
    87 comments
    248 saves
    53 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    4 Sources

    @firstadopterHOLY CRAP. Bloomberg has the goods on Gemini 4! "it does less well when employees actually put it to work .. The model struggles to handle certain coding tasks" Bloomberg: "As Alphabet Inc.’s Google prepares for the coming launch of Gemini 4, it’s grappling with internal skepticism over how well the flagship artificial intelligence model performs in key areas, such as coding. While Gemini 4 has performed well on benchmarks the industry uses to gauge model efficacy, it does less well when employees actually put it to work, according to people with direct access to the effort. The model struggles to handle certain coding tasks, said the people, who requested anonymity to discuss an internal matter."
    @yishanYeah, well, I don't know why we would expect Google to suddenly jump into the lead after Jeff Dean and Sanjay left.

    4 Sources

    @firstadopterHOLY CRAP. Bloomberg has the goods on Gemini 4! "it does less well when employees actually put it to work .. The model struggles to handle certain coding tasks" Bloomberg: "As Alphabet Inc.’s Google prepares for the coming launch of Gemini 4, it’s grappling with internal skepticism over how well the flagship artificial intelligence model performs in key areas, such as coding. While Gemini 4 has performed well on benchmarks the industry uses to gauge model efficacy, it does less well when employees actually put it to work, according to people with direct access to the effort. The model struggles to handle certain coding tasks, said the people, who requested anonymity to discuss an internal matter."
    @yishanYeah, well, I don't know why we would expect Google to suddenly jump into the lead after Jeff Dean and Sanjay left.
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet