1
动视暴雪打击《使命召唤》外挂，律师上门拍“击杀回放”视频
IT之家 8 月 29 日消息，《使命召唤》官方 X 账号近日发布了一段现实版“击杀回放”视频，主要展示动视暴雪律师团队上门向一家游戏外挂供应商送达“停止侵权通知”的画面。 IT之家注意到，此次行动针对的是位于美国俄亥俄州的外挂供应商 Elocarry，官方以《使命召唤》经典“Killcam”击杀回…
2
Show HN: MTL Explorer – Self-hosted archive for GPS tracks
自托管GPS轨迹库，支持3D电影级回放和路线规划，适合户外爱好者部署到NAS。
Article URL: https://github.com/mindalyze-com/mtl-explorer Comments URL: https://news.ycombinator.com/item?id=49427510 Points: 1 # Comments: 1
3
Ask HN: GitHub project that showed all edits (somewhat proving human authorship)
寻找一个能回放文章逐字修订过程的GitHub项目，用编辑历史证明人类创作痕迹，脑洞与实操兼备。
I am trying to find a GitHub project from a technical person who wrote about getting married/engaged and knowing someone for 10 years and how he knew …
4
Show HN: Codex Plays NetHack
通过终端录像观看AI Codex自动游玩经典游戏NetHack，展示人工智能在复杂环境中的决策能力
I'll add a link to the completed recording after the stream completes. Comments URL: https://news.ycombinator.com/item?id=49065825 Points: 1 # Comment…
5
Show HN: Fable 5 vs Kimi K3 in CNC Red Alert 2
展示AI玩红警2对决的思考过程，包含带字幕视频、地图状态和可回放的比赛文件，深入理解AI决策逻辑
link includes video with thinking captions, map state along with thinking of each player and replay file which can be viewed in game.chronodivide.com …
6
Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters
LLM预测评估存在后测信息泄漏，Hindcast方法提出用预测市场回放来规避这种偏差。
arXiv:2607.14051v1 Announce Type: new Abstract: Forecasters are evaluated by backtesting, which replays resolved questions and grades the probability …
7
直播回放·含 ACL'26 杰出论文 | 美团 AI 顶会论文 32 篇精讲
如果你正在关注 AI 前沿，这篇内容值得收藏。2026 年，美团技术团队数十篇论文被 ACL、SIGIR、ICML、KDD 等顶会收录。我们精选 32 篇，进行了 5 大专场直播。
8
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
长上下文推理新突破，递归证据回放让LLM精准捕捉关键信息
arXiv:2607.02509v1 Announce Type: new Abstract: Understanding and reasoning over long contexts has become a key requirement for deploying large langua…
9
Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning
提出非策略回放机制，有效提升大模型强化遗忘的学习效率与数据利用率
arXiv:2606.15333v1 Announce Type: cross Abstract: LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous…
10
Show HN: GitHits Public Beta 0.9
可视化Git提交历史，一键重放代码演变，让协作与复盘更直观。
Hi HN, I’m Olli-Pekka, co-founder of GitHits (and the creator of opencv-python package). GitHits is a CLI and local MCP server that gives coding agent…
11
Show HN: Building a Time Machine for Sports
像时间机器一样回放体育赛事，通过AI数据分析与多维时间线帮助球队和球迷精准回顾关键时刻，提升观赛与分析效率。
Article URL: https://www.microleaguesports.com/blogs/microleague-dev-blog-vol-1 Comments URL: https://news.ycombinator.com/item?id=48540973 Points: 1 …
12
Show HN: Galdor – a Go LLM agent framework with built-in tracing and replay
Go语言LLM Agent框架，内置追踪与回放，开源且原生兼容OpenTelemetry，Agent开发利器。
Article URL: https://github.com/YasserCR/galdor Comments URL: https://news.ycombinator.com/item?id=48520360 Points: 3 # Comments: 0
13
Show HN: GPX Flight Replays
将GPX轨迹变成酷炫的3D飞行回放，足不出户体验航拍视角的运动旅程
Hello HN! I am a flight student and made this tool to replay and study my flights. It is completely opensource [1] and everything works in the browser…
14
Show HN: RePlaya – self-hosted browser session replay with live tailing
自托管浏览器会话回放利器，基于rrweb以持久流为架构，支持实时尾随调试。
Hi HN, I'm one of the founders of s2.dev. RePlaya ( https://github.com/s2-streamstore/replaya ) is a self-hosted browser session replay tool using rrw…
15
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
用预测性路由重放技术优化MoE大模型强化学习，显著提升训练效率与模型性能
arXiv:2606.00395v1 Announce Type: new Abstract: Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, re…
16
Dis Dat – Loom for AI coding agents
专为AI编程代理打造的录制回放工具，类似Loom但聚焦代码协作场景。
Article URL: https://disdat.dev Comments URL: https://news.ycombinator.com/item?id=48317796 Points: 2 # Comments: 0
17
Show HN: Offline Typing Mastery
离线打字练习神器：用真实语料训练，可视化回放和习惯日历让你快速提升。
I built this typing mastery application yesterday. It took just few hours. I wanted to have features that I wanted to use for improving the typing spe…
18
SteelSpine: Replay tool for debugging AI agents
一款本地优先、合规就绪的AI代理调试回放工具，支持SOC 2与EU AI Act标准，无需云依赖。
Article URL: https://steelspine.ai Comments URL: https://news.ycombinator.com/item?id=48239816 Points: 2 # Comments: 1
19
ARROW: Augmented Replay for RObust World models
提出ARROW增强回放框架，显著提升世界模型在分布外场景的鲁棒性。
arXiv:2603.11395v2 Announce Type: replace Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previousl…