Comment on People were mad because they lost their AI boyfriend after GPT-4o deprecation

<- View Parent
brucethemoose@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

This is a common pattern unfortunately. Big LLMs are benchmaxxing coding and one shot answers, and multi turn conversation are taking a nosedive.

arxiv.org/abs/2504.04717

Restructure your prompts, or better yet try non-OpenAI LLMs. I’d suggest z.ai, Jamba, and Gemini Pro for multi turn. Maybe Qwen Code, though it’s pretty deep fried too.

source
Sort:hotnewtop