News for hackers. Stuff that matters.

A comment on Google's Bard shows big leap on LLM performance leaderboard.

Re:Google's Bard shows big leap on LLM performance leaderboard by ipsum2 on Friday January 26, 2024 @02:43PM (#39147166)
It's not a valid comparison. Bard uses Google (ie the Internet) to answer things, while GPT4 doesn't. So bard can answer things like, "what's the weather in SF today" or "who won the basketball game last night".
[ Parent | on HN ]
Re:Google's Bard shows big leap on LLM performance leaderboard by robinjhuang on Friday January 26, 2024 @02:48PM (#39147236)
Chat GPT4 does do internet searches now.
[ Parent | on HN ]
Re:Google's Bard shows big leap on LLM performance leaderboard by ipsum2 on Friday January 26, 2024 @02:51PM (#39147277)
The model being compared on the LLM Arena does not use ChatGPT4, it uses GPT4 API, which does not have access to the internet by default.
[ Parent | on HN ]
Re:Google's Bard shows big leap on LLM performance leaderboard by 2OEH8eoCRo0 on Friday January 26, 2024 @02:48PM (#39147235)
I'm not sure what you mean. ChatGPT with GPT4 uses Bing to search the web.
[ Parent | on HN ]
Re:Google's Bard shows big leap on LLM performance leaderboard by ipsum2 on Friday January 26, 2024 @02:51PM (#39147281)
See reply to sibling comment.
[ Parent | on HN ]