Comparison of large language models

sporkman

Wise, Aged Ars Veteran
213
Seeing as how it takes hours of interactions to really get a feel for what an ai can do, how do they compare?

I’ve spent some time on ChatGPT mainly. Claude is supposedly a more sensitive llm? I haven’t noticed that yet in Claude. Gemini feels really cautious but with research it is thorough. It did write an interesting physics game with just a few prompts, and it’s way more usable than actual google search because actual google search is filled with ad junk now X.ai seems kind of wild. I have not spent time with deep seek aside from seeing how disruptive it is in the news. Anything interesting amongst the various ai models?