Open Menu
AllLocalCommunitiesAbout
lotide
AllLocalCommunitiesAbout
Login

OpenAI says its latest models outperform doctors in medical benchmark

⁨22⁩ ⁨likes⁩

Submitted ⁨⁨10⁩ ⁨hours⁩ ago⁩ by ⁨Pro@programming.dev⁩ to ⁨technology@lemmy.world⁩

https://the-decoder.com/openai-says-its-latest-models-outperform-doctors-in-medical-benchmark/

source

Comments

Sort:hotnewtop
  • Bezier@suppo.fi ⁨10⁩ ⁨hours⁩ ago

    Tl;dr: OpenAI says OpenAI product performs well in a benchmark created by OpenAI.

    source
    • Opinionhaver@feddit.uk ⁨6⁩ ⁨hours⁩ ago

      The bar exam isn’t created by OpenAI, yet the outdated GPT-4 model still ranked in the 90th percentile on it.

      source
  • orclev@lemmy.world ⁨8⁩ ⁨hours⁩ ago

    Wake me up when someone besides OpenAI says they’re the best at something. When a company releases a benchmark they designed that their own tool that’s generally regarded as not very good is suddenly the best at, that’s not news, at best that’s PR, at worst propaganda. This reeks of “we investigated ourselves and found we did nothing wrong”.

    source
  • banghida@lemm.ee ⁨10⁩ ⁨hours⁩ ago

    Sure thing

    source
  • taladar@sh.itjust.works ⁨10⁩ ⁨hours⁩ ago

    So they created a test so broken and warped that no actual professional can understand it but their AI performs well on it?

    source
  • etchinghillside@reddthat.com ⁨9⁩ ⁨hours⁩ ago

    US Healthcare will now be affordable!

    source
  • kaeurennetwo@lemmy.world ⁨10⁩ ⁨hours⁩ ago

    Wow.

    source
    • TrendigOsthyvel@lemmy.world ⁨10⁩ ⁨hours⁩ ago

      Much wow.

      source
      • kaeurennetwo@lemmy.world ⁨10⁩ ⁨hours⁩ ago

        Those are analytical AI right? More procedural, and also, the data to train the AI are consented. I tried Ada, it didn’t give me official diagnosis but rather helping me to talk to doctor

        source
  • Buffalox@lemmy.world ⁨10⁩ ⁨hours⁩ ago

    I almost feel sad for IBM, this was supposed to be their thing.

    source