开启时会模糊预览图，关闭后正常显示
RT @itshanrw: AppNexus - 黑色星期五特卖来了！ https://t.co/JCPlCo4mYp 终身计划 83% 折扣 原价 $174.99 现价 $29.99 一次性付款。 永久拥有。 无需订阅。 无需续费。 © 截至日期：202…
🔖 Building · Sharing ✨ Zipic · TimeGo · KeygenGo · HiPixel · Orchard · Prism
在大型代码库中查找某个业务处理逻辑，如果不知道确切的函数名或关键词，可能找半天都找不到。 可以看一下 mgrep 这个开源工具，它就像装了 AI 大脑的 Grep，让我们能用自然语言去搜索代码、图片和 PDF 等各种文件。 通过强大的语义检索模型，来理解我们的搜索意图，还能在后台静默索引文件。 GitHub：https://t.co/dT6lsfwug6 更厉害的是，它能与 Claude Code、Codex 等 AI 助手集成，测试发现可以大幅减少 Token 消耗。 通过 npm 全局安装后即可使用，在项目目录中运行 `mgrep watch` 就能开始索引。
💡 挖掘开源的价值 🧑🏻💻 坚持分享 GitHub 上高质量、有趣、实用的教程、AI工具、前沿 AI 技术 🧐 A list cool, interesting projects of GitHub. ✏️ 公众号：GitHubDaily
RT @antoine_chaffin: @getpochi Why choose? ColBERT is the perfect mix of fancy vectors and terms matching, a soft/fuzzy BM25 :)
Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.
RT @antoine_chaffin: > A benchmark is released > BM25 is competitive > ColBERT models outperform much larger models and is close (larger) s…
Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.
🇨🇳 The flight with @CSAIRGlobal was again great, really good airline, well organized, friendly staff and good food Here's my food review Next I'll review the airports...
🇪🇺https://t.co/NdorAWrhrB @euacc 📸https://t.co/lAyoqmT9Hv $125K/m 🏡https://t.co/1oqUgfDEsx $40K/m 🛰https://t.co/ZHSvI2wRou $38K/m 🌍https://t.co/UXK5AFra0o $16K/m 👙https://t.co/RyXpqGvdBB $14K/m 💾https://t.co/M1hEUBB6da $6K/m
Happy Thanksgiving! There are a lot of things to be thankful for...but the state of RL infra is not one of them! ... Unless? Trying out @__tinygrad__ live on stream in a few hours here on X. Will be running key perf tests vs Torch and custom kernels.
I build sane open-source RL tools. MIT PhD, creator of Neural MMO and founder of PufferAI. DM for business: non-LLM sim engineering, RL R&D, infra & support.