News for hackers. Stuff that matters.
Re:Comparison of Claude Sonnet 3.5, GPT-4o, o1, and Gemini 1... by WorkerBee28474 on Thursday November 21, 2024 @03:38PM (#42208385)
The article seems like cork-sniffing to me, so I'll just link a couple coding LLM leaderboards that have actual numbers:

https://aider.chat/docs/leaderboards/

https://livebench.ai/

Re:Comparison of Claude Sonnet 3.5, GPT-4o, o1, and Gemini 1... by Terretta on Thursday November 21, 2024 @03:37PM (#42208375)
This piece has characteristics of being LLM written or at least LLM edited.

It also makes unusually phrased assertions: "A key advantage of GPT-4o is its ability to stay updated with recent programming practices, libraries, and frameworks."

Re:Comparison of Claude Sonnet 3.5, GPT-4o, o1, and Gemini 1... by airstrike on Thursday November 21, 2024 @03:45PM (#42208477)
It also has multiple entries for the words "crucial" and "essential" which LLMs love to insert.
Re:Comparison of Claude Sonnet 3.5, GPT-4o, o1, and Gemini 1... by petercooper on Thursday November 21, 2024 @03:49PM (#42208517)
This sort of dross makes me long for a downvote button (even if only for items that make it to the front page to avoid abuse). It's not flag-worthy but it's not front page material. A listed disadvantage of Gemini 1.5 Pro is "higher computational overhead" as if I'm running it locally or something..
Re:Comparison of Claude Sonnet 3.5, GPT-4o, o1, and Gemini 1... by rmbyrro on Thursday November 21, 2024 @03:37PM (#42208381)
The TL;DR says all the obvious things every developer who has awareness already knew for some time.