《经济学人》：GPT-6 Astra 等前沿大语言模型或能互相发现并修复缺陷
It seems that cutting-edge large language models, such as OpenAI’s GPT-6 Astra, may be able to find and fix each other’s flaws, according to claims ...
AI 导读
据一篇近期博客文章的说法，OpenAI 的 GPT-6 Astra 等前沿大语言模型可能能够互相发现并修复彼此的缺陷。目前相关信息仅来自该博客的声称，尚需进一步验证。
来源：@TheEconomist · x.com