Are ‘visual’ AI models actually blind?

  • AI
  • July 11, 2024
  • 0 Comments

The latest round of language models, like GPT-4o and Gemini 1.5 Pro, are touted as “multi-modal,” able to understand images and audio as well as text — but a new study makes clear that they don’t really see the way you might expect. In fact, they may not see at all. To be clear at […]

© 2024 TechCrunch. All rights reserved. For personal use only.

  • Related Posts

    5 days left to claim your exhibitor table for TechCrunch All Stage 

    Time is running out. Exhibitor tables for TechCrunch All Stage, happening July 15 in Boston, are nearly gone — and the final deadline to secure your spot is this Friday,…

    Continue reading
    Day 5 of TechCrunch Sessions: AI Trivia Countdown — Test your knowledge, win big tickets

    Think you know which AI beat a human champion in the game of Go? Or which company developed the Transformer architecture that powers many modern language models? This is your…

    Continue reading

    Leave a Reply

    Your email address will not be published. Required fields are marked *

    You Missed

    5 days left to claim your exhibitor table for TechCrunch All Stage 

    • By staff
    • June 2, 2025
    • 1 views

    Major record labels are reportedly in licensing talks with AI firms Udio and Suno

    • By staff
    • June 2, 2025
    • 1 views

    3 days until the doors open at TechCrunch Sessions: AI at UC Berkeley

    • By staff
    • June 2, 2025
    • 1 views

    Day 5 of TechCrunch Sessions: AI Trivia Countdown — Test your knowledge, win big tickets

    • By staff
    • June 2, 2025
    • 1 views

    Samsung may incorporate Perplexity’s AI tech in its phones

    • By staff
    • June 2, 2025
    • 2 views

    For the love of God, stop calling your AI a co-worker

    • By staff
    • June 2, 2025
    • 2 views