0:00
/
0:00
Transcript

OpenAI's New gpt-oss Doesn't Deliver for Healthcare [Video]

OpenAI is pushing HealthBench in every model release like it's a clinical breakthrough, when it's really just a man-made benchmarking gimmick.
Source of original chart: https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf

More on OpenAI’s new gpt-oss model tomorrow morning. But real quick:

  • OpenAI just released its first open-weight language models since GPT-2, called gpt-oss.

  • They keep pushing HealthBench like it’s proof they’ve “solved” healthcare. 🙄

  • You can’t really fine tune gpt-oss. So unless your dataset looks like HealthBench, you’re out of luck. 😉

Check your inbox tomorrow morning, Wednesday, August 5, for my full critique.

Stay safe.

Sergei

Discussion about this video