Comments URL: https://news.ycombinator.com/item?id=47812142 Points: 10 # Comments: 4
Article URL: https://glassroom.sageframe.net Comments URL: https://news.ycombinator.com/item?id=47807262 Points: 1 # Comments: 0
Once subagents start spawning other subagents, basic questions get hard to answer: what is running right now, what tool did it just call, did the child agent actually do what the parent asked. I wanted a way to verify that each agent is doing the work that fits its role, and to spot when a run goes off track. Lazyagent is a terminal TUI that collects events from Claude Code, Codex, and OpenCode and shows them in one place. It groups sessions from different runtimes by working directory, so Claude and Codex runs on the same repo appear under the same project. Features: - Filter events by type: tool calls, user prompts, session lifecycle, system events, or code changes only. - See which agent or subagent is responsible for each action. The agent tree shows parent-child relationships, so you can trace exactly what a spawned subagent did vs what the parent delegated. - View code diffs at a glance. Editing events render syntax-highlighted diffs inline, with addition/deletion stats. - Search across all events. You know a file was touched but not which agent did it -- type `/` and find it. - Check token usage per session. A single overlay shows cost, model calls, cache hit rate, per-model breakdowns, and which tools ran the most. - Watch a run in real time, or go back through a completed session to audit what happened. Please let me know if there's any feature you want! Comments URL: https://news.ycombinator.com/item?id=47805963 Points: 1 # Comments: 0
I wanted a way to disambiguate my search queries in a sleek user interface so I created this tool that generates google search queries with advanced operators for me. Comments URL: https://news.ycombinator.com/item?id=47805015 Points: 1 # Comments: 0
Article URL: https://github.com/Wassist/cli Comments URL: https://news.ycombinator.com/item?id=47804372 Points: 1 # Comments: 2
Article URL: https://nofs.ai/ Comments URL: https://news.ycombinator.com/item?id=47800340 Points: 3 # Comments: 0
What's New in v0.3 Retry failed transcriptions – history entries that failed can now be retried with saved audio Cancel with ESC – press ESC during recording to cancel without creating invalid entries More stable long recordings – fixed truncation issues for extended sessions Fn key support – custom hotkeys now support Fn key combinations Comments URL: https://news.ycombinator.com/item?id=47795617 Points: 2 # Comments: 1
Article URL: https://menggg.me/vibes/week-15 Comments URL: https://news.ycombinator.com/item?id=47789231 Points: 1 # Comments: 0
优惠码: WHATSNEWPRO2 1 个帖子 - 1 位参与者 阅读完整话题
IT之家 4 月 16 日消息，欧盟委员会 4 月 15 日发布公报称，已向美国元宇宙平台公司（Meta）发出补充异议声明，初步认定该公司在调整了限制第三方人工智能（AI）助手接入其旗下即时通信应用程序 WhatsApp 的相关措施后，仍违反欧盟反垄断规则， 拟要求该公司恢复第三方 AI 助手对 WhatsApp 的访问权限 。 IT之家从公告中获悉，2025 年 10 月 15 日，Meta 宣布更新《WhatsApp 商业解决方案条款》，自 2026 年 1 月 15 日起， 实质上禁止第三方通用 AI 助手接入该应用 。 2025 年 12 月 4 日，欧盟委员会就此正式启动调查程序；2026 年 2 月 9 日，欧盟委员会向 Meta 发送异议声明，告知其行为初步涉嫌违反欧盟竞争法规，并拟采取临时措施。2026 年 3 月 2 日，Meta 就该异议声明提交了回应材料。 2026 年 3 月 4 日，Meta 公布修订版政策，撤销此前禁令， 但对第三方通用 AI 助手增设收费框架 。 在最新的补充异议声明中，欧盟委员会告知 Meta，修订后的政策仍会产生将第三方 AI 助手排除出 WhatsApp 的效果，初步涉嫌违反欧盟竞争法规。为避免对市场竞争造成严重且不可挽回的损害，委员会拟下令 Meta 按 2025 年 10 月 15 日前的原有条件， 恢复第三方 AI 助手的访问权限 ，直至就 Meta 行为作出最终裁决。
Spent 4 months and built Omi for Desktop, your life architect: It sees your screen, hears your conversations and will advise you on what to do next Basically Cluely + Rewind + Granola + Wisprflow + ChatGPT + Claude in one app I talk to claude/chatgpt 24/7 but I find it frustrating that i have to capture/send screenshots of my screen and that it doesn't help proactively during my work Whenever omi sees something wrong about my workflow, it will send me a proactive notification with advice. It will also point to something I'm missing. The hardest part was to nail proactivity - after trying 20+ similar tools I didn't find a single one with smart proactive notifications based on content on your screen. I made it look at your screen every second with 4 main prompts: 1. Is the user productive or distracted? 2. Is there anything useful to say right now? 3. is there any task to add to do later? 4. is there anything important to remember about the user? Full stack: - Swift - Rust backend - Deepgram transcription - Claude code for messaging - GPT 5.4 summaries - Gemini for embeddings and translation Open source, stores screenshots locally, uses Claude Code for chat. Has cloud to sync with hardware or mobile app but can be disabled in settings Comments URL: https://news.ycombinator.com/item?id=47784914 Points: 7 # Comments: 3
请教下各位佬，现在注册一个gpt账号，这么困难了么，手机验证跳whatsapp验证了 2 个帖子 - 2 位参与者 阅读完整话题
As I got older I found myself buying games that just ended up sitting in my backlog. I just couldn’t get into the mood to play them. I realized there was a disconnect between what excited me and what actually fit my energy levels and time. That’s what led me to build Slated.gg. Most game recommenders look at games from the outside (genre, themes, etc.) What mattered to me was what’s it like to play. How much focus it needs, what type of thinking it requires, can I play in short bursts, is it emotionally taxing, etc. I built a game recommender around experience and landed on 30 experiential dimensions (so far). I created an AI pipeline that researches and analyzes games by those dimensions and stores them in a vector space. Think sentiment analysis, but for player experience. The recommender then finds similarities by geometric (Euclidean) distance based on other games you like. When I mapped 297 games, it was really interesting to see what clusters emerged. AAA games cluster tightly together, exposing how they are built with the same formula. The edges are more interesting and surface games with real differentiation. These tend to be the kinds of games players have a hard time finding good recommendations for. Visualization and methodology: https://slated.gg/map Try it: https://slated.gg/discover-games Happy to answer questions about the approach or where it falls short. Comments URL: https://news.ycombinator.com/item?id=47766624 Points: 1 # Comments: 0
Article URL: https://github.com/ginlix-ai/langalpha Comments URL: https://news.ycombinator.com/item?id=47766370 Points: 2 # Comments: 1
Article URL: https://nobulex.com/playground Comments URL: https://news.ycombinator.com/item?id=47765454 Points: 1 # Comments: 0
Every time I hit "address already in use" I'd run `lsof -i :3000`, grep for the PID, then kill -9 it. Three commands, every single time. So I wrote `pkll`, one command that does all of it, but asks for confirmation with all info about the process, and warns if it is important system process first. You run `pkll [PORT]`, then it shows all the essential info about the process. Then after confirmation the process is killed. This became especially annoying with coding agents. They just spin up dev servers, then leave bun instances and other processes sitting silently in the background. You go to start your server and something invisible is already holding the port. I built this to keep it dead simple: one thing, one command, works the same on Linux, macOS, and Windows. No config, no flags to memorize making it deadly simple. Also I wrote it while learning Rust, so feedback on the code is very welcome. Comments URL: https://news.ycombinator.com/item?id=47763300 Points: 1 # Comments: 0
Discover how compatible you are with friends, family and dates. Comments URL: https://news.ycombinator.com/item?id=47751985 Points: 1 # Comments: 0
Article URL: https://shukla.io/blog/2026-04/b01t.html Comments URL: https://news.ycombinator.com/item?id=47751686 Points: 2 # Comments: 0
Apple's $599 Laptop Is Real — Here's What You Give Up https://vucense.com/tech-reviews/reviews-hardware/macbook-ne... Comments URL: https://news.ycombinator.com/item?id=47749843 Points: 1 # Comments: 0
Hermes在阿里云上官方一键安装，卡在了what apps安装上，有没有什么办法能自定义选择安装的插件？ 1 个帖子 - 1 位参与者 阅读完整话题