News for hackers. Stuff that matters.

A comment on GPT-5.4. Parent comment

Re:GPT-5.4 by selcuka on Thursday March 05, 2026 @07:02PM (#47268943)
With Anthropic you always have 3 models to choose from: Opus-latest, Sonnet-latest, and Haiku-latest, from the best/slowest to the worst/fastest.

The version numbers are mostly irrelevant as afaik price per token doesn't change between versions.

[ Parent | on HN ]
Re:GPT-5.4 by maxo99 on Thursday March 05, 2026 @07:18PM (#47269079)
Three random names isn't ideal. I'm often need to double check which is which. This is why we use numbers
[ Parent | on HN ]
Re:GPT-5.4 by echoangle on Thursday March 05, 2026 @07:33PM (#47269200)
How are the names random?

https://en.wikipedia.org/wiki/Masterpiece

https://en.wikipedia.org/wiki/Sonnet

https://en.wikipedia.org/wiki/Haiku

They dropped the magnum from opus but you could still easily deduce the order of the models just from their names if you know the words.

[ Parent | on HN ]
Re:GPT-5.4 by dseravalli on Thursday March 05, 2026 @07:35PM (#47269220)
They aren't random. Opus's are very long poems, haikus are very short ones (3 lines), sonnets are in between (~14 lines)
[ Parent | on HN ]
Re:GPT-5.4 by oliwary on Friday March 06, 2026 @01:02AM (#47271446)
What's next? Claude Iliad?
[ Parent | on HN ]