LLM切换时上下文丢失与token超支的痛点，看看社区如何破局？
I'm hitting a wall with model context management. On free or lower-tier API plans, those token limits vanish incredibly fast when you're passing back-…
Python 库 Llmbuffer 通过分离不可变前缀与可变尾部，实现 LLM 对话历史的缓存优化，大幅减少重复计算。
I was not getting good cache utilization when including dynamic context in agent threads. After a lot of experimentation, I found a good pattern that …
本地搜索Claude聊天记录的开源神器，混合检索top-1达68.7%，高效管理超万条消息。
Article URL: https://github.com/luckyrmp/tinderbox-archive Comments URL: https://news.ycombinator.com/item?id=48421160 Points: 2 # Comments: 0
针对LLM长对话中历史信息丢失问题，提出分层存档与时间情景检索网络，轻量高效恢复关键细节。
arXiv:2606.05182v1 Announce Type: new Abstract: Large language models discard critical details when conversation history is compacted to fit within fi…