News for hackers. Stuff that matters.
Re:From GPT-4 to GPT-5: Measuring Progress in Medical Langua... by dang on Thursday August 21, 2025 @10:23PM (#44980419)
OK, we've removed all understanding from the title above.
Re:From GPT-4 to GPT-5: Measuring Progress in Medical Langua... by fragmede on Friday August 22, 2025 @01:43PM (#44987404)
Care to provide reasoning as to why?
Re:From GPT-4 to GPT-5: Measuring Progress in Medical Langua... by dang on Friday August 22, 2025 @01:56PM (#44987555)
The article's actual title was longer than 80 chars, which is HN's limit. There's more than one way to truncate it.

The previous truncation ("From GPT-4 to GPT-5: Measuring Progress in Medical Language Understanding") was baity in the sense that the word 'understanding' was provoking objections and taking us down a generic tangent about whether LLMs really understand anything or not. Since that wasn't about the specific work (and since generic tangents are basically always less interesting), it was a good idea to find an alternate truncation.

So I took out the bit that was snagging people ("understanding") and instead swapped in "MedHELM". Whatever that is, it's clearly (1) something in the medical domain and (2) has no sharp edge of offtopicness. Seemed fine, and it stopped the generic tangent from spreading further.

Re:From GPT-4 to GPT-5: Measuring Progress in Medical Langua... by fragmede on Friday August 22, 2025 @02:08PM (#44987699)
Well thought out, thank you!

Generic Tangents is my new band's name.