neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻译准备中
缓存感知、因果修剪的上下文压缩用于LLM代理运行时——在9个领域中经认证不逊色。压缩输入和输出;确保代理的下一步行动保持不变(代理;s)
AI 翻译
Cache-aware, causally-pruned context compression for LLM agentic runtimes — certified non-inferior across 9 domains. Compress input and output; certify the agent's next action is unchanged (a proxy; s
开发工具Python · HTMLGitHub @dshakes在线运营者未确认
试用过了吗? 点一下就好,无需登录。
Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.
翻译准备中
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
Something is rewriting your agent's context. Distil measures what it cost you.
Your provider now edits the context window for you — clearing old tool results, summarizing history — by default, server-side, with no report of what changed. Distil is the instrument that answers the only question that matters: did the agent still do the same thing?查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
Something is rewriting your agent's context. Distil measures what it cost you.
Your provider now edits the context window for you — clearing old tool results, summarizing history — by default, server-side, with no report of what changed. Distil is the instrument that answers the only question that matters: did the agent still do the same thing?查看完整 README ↗