探索LLM能否通过牺牲人类可读性，用紧凑非标准文本编码语义，实现更高效模型间通信
arXiv:2606.19857v1 Announce Type: cross Abstract: Large language models (LLMs) are commonly prompted and interfaced with human-readable natural langua…
反AI入侵的字体与键盘固件项目，专为人类阅读设计，让机器人再难识别你打的字
Article URL: https://github.com/convictional/souls-only Comments URL: https://news.ycombinator.com/item?id=48445469 Points: 3 # Comments: 1
为AI代理设计的Token高效UUID替代方案，生成人类可读的ID，提升交互效率。
Article URL: https://github.com/vostride/id-agent Comments URL: https://news.ycombinator.com/item?id=48191852 Points: 10 # Comments: 15