AI

2024/9/9 更新: mattshumer/Reflection-Llama-3.1-70B - Discussions 討論區裡大量回報此模型的詐欺行為。

看了 The Super Effectiveness of Pokémon Embeddings Using Only Raw JSON and Images 這篇，才發現不一定需要不可靠又緩慢的 LLM 來做 RAG，只要 embedding 就能做出高效低成本且可靠可上線的 AI 應用。

====================== 棄 GPT-4o 等 GPT-5

前陣子看的幾篇，如何得到更好的答案:

OpenAI has recently begun training its next frontier model and we anticipate the resulting systems to bring us to the next level of capabilities on our path to AGI.