
@proximasan hi, man, maybe claude is best writer on base prompt, but gpt 4 is very flexible in terms of prompting and gpt-agents make sense, plus gpt4 allows to use system info drastically influential at end result. good luck, find best.
English
Shangritwo, Avatarix
270 posts

@Shangritwo
Creating with AI🌿✳️ • NFT Creator • Discord Manager • working in @limmweb








Can LLMs really self-critique (and iteratively improve) their solutions, as claimed in the literature?🤔 Two new papers from our group investigate (and call into question) these claims in reasoning (arxiv.org/abs/2310.12397) and planning (arxiv.org/abs/2310.08118) tasks.🧵 1/




