xc

What if your coding agent sounded like the StarCraft Adjutant or C&C EVA? I built Voxlert — it hooks into Claude Code, Codex and Cursor and speaks notifications in-character. Each session gets a distinct voice (Adjutant, SHODAN, GLaDOS) so you know which agent needs you without looking. LLM + Local TTS + voice filters, cost negligible. github.com/settinghead/vo…

@ravikiran_dev7 64GB+. Easily can have 30 cli agents open concurrently.

As a Developer, how much RAM is enough for you? 1. 8 GB 2. 16 GB 3. 24 GB 4. 32 GB 5. 64 GB 6. 128 GB+

@Stanleysobest 大部分简历不是都是注水严重的吗

我们团队正在给B端做HR AI提效， 刚听一位300人公司的HR总监说： 一个岗位刚放出去，瞬间几千份简历砸过来。 最吓人的不是海投，是每一个都真的能胜任。 现在的就业市场，已经卷到这种程度了？

@WizLikeWizard The discussion is pointless without specifying which model you are using.

Have been using OpenClaw for ~a month and it kinda sucks? I spend more time battling it to get basic crons fired reliably, remember things, and not repeat itself. Am I doing it wrong or are we just still very early on all of this?

New idea: You don't have to have only one prototype.

@MrGafish 到底谁真的裁了

科大讯飞裁员 网易裁员 B站裁员 最近刷到这几家的消息，下一个会是谁？

@KKaWSB 知错就改及时扭转是对的。毕竟他只有一例成功创业经历，每次都成功也不现实。

Meta 宣布将关闭 Metaverse，科技史上最贵，超过 800 亿美元投入的大败局： 马克·扎克伯格当年全力投入虚拟现实技术 Facebook 收购 Oculus（20 亿美元） 对整个公司进行品牌重塑（2021 年） 集团公司更名为：Meta（元宇宙） 为 Reality Labs 招聘数千人 投资额超过800亿美元 构建元宇宙愿景 推出地平线世界 甚至没有真正意义可用产品，无用户留存 损失不断累积（每年数十亿美元） 注意力转向人工智能 科技领域最大的赌注之一……

@binghe 苹果的溢价来自于品牌+图形处理+开发生态+现在的AI，小米的溢价来自于……？

小米笔记本，卖的挺贵啊！！！ 真敢要价啊。。。现在经济上行了吗？？？ 我有这价格，为什么不买苹果？？？

@iamai_eth 如果从The Bitter Lesson的棱镜看，前者有更大概率胜出。

OpenClaw-RL 和 Hermes Agent 是2026年初个人AI Agent领域两个非常热门但方向不同的开源项目，都在试图解决“AI代理如何持续变强”的核心问题，但实现路径、适用场景和哲学完全不同。 - OpenClaw-RL ≈ “给OpenClaw装一个超级在线对齐引擎”，靠强化学习把你每一次不满/纠正/追问都变成模型的训练信号，理论上长期能最贴合你，但需要GPU、时间和OpenClaw基础。 - Hermes Agent ≈ “一个会自己长大的个人助理”，重点在记忆、技能积累和跨会话连续性，短期就能感受到“它越来越懂我”，部署简单、模型中立。

@dontbesilent 真有人试过了吗？

1、这是我迄今为止用过的最好的 skill 2、无论我们多么大力宣传这个 skill，大部分都只会围观，最多安装一下，不会真的去在自己的上下文里面去推进 3、所以，这让这个 skill 的使用体验更稀缺了

@sergeykarayev Local agents are fun as a hobby, as long as they stay that way.

Running agents locally is a dead end. The future of software development is hundreds of agents running at all times of the day — in response to bug alerts, emails, Slack messages, meetings, and because they were launched by other agents. The only sane way to support this is with cloud containers. Local agents hit a wall quickly: • No scale. You can only run as many agents (and copies of your app) as your hardware allows. • No isolation. Local agents share your filesystem, network, and credentials. One rogue agent can affect everything else. • No team visibility. Teammates can't see what your agents are doing, review their work, or interact with them. • No always-on capability. Agents can't respond to signals (alerts, messages, other agents) when your machine is off or asleep. Cloud agents solve all of these problems. Each agent runs in its own isolated container with its own environment, and they can run 24/7 without depending on any single machine. This year, every software company will have to make the transition from work happening on developer's local machines from 9am-6pm to work happening in the cloud 24/7 -- or get left behind by companies who do.

@sitinme A2A真的有项目在用吗？

这波 Google 其实干了一件挺关键的事：把一堆原本各自为战的 Agent 协议，第一次串成了一条“能跑通业务”的完整链路。 以前你做 Agent，会有一种很明显的割裂感： 连工具一套代码、连外部服务一套代码、做前端展示再一套代码。 真正业务逻辑可能就 30%，剩下 70% 全是在写“胶水”。而且每换一个框架、换一个工具，基本都要重来一遍。 这次 Google 的思路很简单但很狠： 不再强调“我这套最牛”，而是把 MCP、A2A、UCP、AP2、A2UI、AG-UI 这些不同组织的协议，全拼起来，直接给你一个能从“查数据 → 调 Agent → 下单 → 付款 → 展示 → 实时交互”跑通的完整范式。 说人话就是： 以前你是在“拼乐高但每块都要自己削”， 现在是“标准件已经给你做出来了，你只需要搭”。 Agent 这条路，已经从“能力竞赛”进入“基础设施阶段”了。 之前大家比的是：谁更会写 prompt、谁上下文更长、谁 agent loop 更聪明。 接下来比的会变成：谁的协议更通用；谁的生态接入更多；谁更像“互联网协议层”而不是“工具层” MCP 像 HTTP（连万物），A2A 像 TCP（Agent 之间通信），UCP/AP2 像支付+电商协议，A2UI/AG-UI 像前端标准。 这一套东西一旦跑起来，其实是在往“Agent 版互联网”走。 可能你以后写的 Agent，很可能不是“某个平台里的一个 bot”， 而是一个可以被别的 Agent 调用的服务节点。 你不只是用 Agent，你是在“把自己接入 Agent 网络”。 这件事比单个模型升级更重要。 模型再强，也解决不了“怎么连世界”的问题。 但一旦协议打通，Agent 才真正有机会从“会聊天”变成“能干活”。

@lifesinger 我觉得得尽快利用AI开始搞销售和营销。

对绝大部分用户来说，AI 只有一个缺陷 用 AI 很花钱，但很难赚到钱 克服这个缺陷的最简单办法是 把 AI 当高档消费品 只想着花钱，不想着赚钱 心里就舒坦了 没钱怎么办 把之前花在消费品上的钱 挪部分到 AI 上 AI 不会消灭工作 而是会消灭各种高档物质消费品

@CTracy0803 国内现在有哪些公司真的裁员了？

目前“B站裁员要裁40%到60%”在各大平台疯传 B站虽在2025年首次实现全年盈利，但股价仍较为低迷。

@heyrimsha GSD + long sessions = you need to know when it's done without watching. Built Voxlert for this — character voice notifications so you hear which agent finished. x.com/settinghead/st…

🚨 This is how engineers at Amazon, Google, and Shopify actually use Claude Code. It's called GSD (Get Shit Done) and it solves context rot the quality degradation that destroys your Claude Code sessions as the context window fills up. No BMAD. No enterprise sprint theater. No Jira nonsense. Here's how it works: You run one command → /gsd:new-project → It interviews you until it fully understands your idea → Spawns parallel research agents to investigate your stack → Creates atomic task plans with XML structure Claude actually understands → Executes in fresh 200k context windows per task → Commits every single task to git automatically Here's the wildest part: Your main context window stays at 30-40% the entire time. All the heavy lifting happens in subagent contexts. No degradation. No "I'll be more concise now." Just clean, consistent execution. Engineers at Amazon, Google, Shopify, and Webflow trust this thing. MIT license. One command to install: npx get-shit-done-cc@latest Link in the first comment 👇

@PawelHuryn Another hooks use case: voice notifications. Voxlert hooks into PostToolUse to speak in-character — SHODAN, StarCraft Adjutant — so you know which agent needs you by ear. x.com/settinghead/st…

Claude Code already shipped a solution for this: hooks. PreToolUse runs before any tool executes. Your script sees the tool name + arguments and returns allow, block, or error. Block rm. Allow edits. Require confirmation for writes to /src. Log every Bash command. PostToolUse runs after execution: auto-format, lint, run tests. Not less dangerous. Precisely controlled.

@brian_scanlan Hooks are so underused. I built Voxlert on them too — PostToolUse triggers character voice notifications so you hear which agent session needs you. x.com/settinghead/st…

Claude Code hooks enforce our PR workflow at the shell level and blocks it unless the create-pr skill was activated first 1. A PreToolUse hook intercepts raw gh pr create 2. The skill extracts business INTENT before creating - asks "why?" not just "what changed?"

We've been building an internal Claude Code plugin system at Intercom with 13 plugins, 100+ skills, and hooks that turn Claude into a full-stack engineering platform. Lots done, more to do. Here's a thread of some highlights.

@marlowxbt Love the voice angle. I built Voxlert so Claude Code talks back — SHODAN, StarCraft Adjutant, GLaDOS narrate your sessions in-character. x.com/settinghead/st…

A guy built a physical button that makes money. One red button. One green button. Connected to Claude Code by voice. He says find trade. Claude Code scans the platform. Finds a spread. The red LED lights up. He presses green. Trade placed. Done. He does this while cooking. While watching TV. While brushing his teeth. The video went viral yesterday. Him standing in his kitchen. Breadboard on the counter next to the toaster. Red light blinks. He presses a button without looking. Goes back to making eggs. That press was worth $1,109,607. 432614799197. $4,561,287 profit. 4,548 predictions. Joined January 2026. Not a keyboard. Not a phone. Not a laptop. A breadboard with 4 buttons soldered to a Raspberry Pi running Claude Code through voice. He says: What's open? Claude Code: Fulham win March 1. YES at 46.8 cents. Edge detected. 4,548 presses. $4.5 million. The button doesn't know it's trading. It just sends a signal when he pushes it. Someone in the comments asked: Why not fully automate it? Why keep the button? Him: I tried full auto. Made me nervous. The button keeps me in control. I hear Claude say the trade. I decide. I press. Takes 2 seconds. But those 2 seconds are mine. The whole setup costs $34. A Raspberry Pi, a breadboard, 4 buttons, and an LED. $34 in hardware. $4.5 million in profit. His kitchen counter has a toaster, a coffee maker and a device that makes $2 million bets. Everyone is building AI apps. This guy soldered 4 buttons to a breadboard and connected it to Claude Code. The red light blinks. He presses green. Goes back to his eggs. $4,561,287. 4,548 button presses. The cheapest trading terminal ever built.

@AIDailyGems Love peon-ping! Voxlert takes it further — each session gets its own character voice with LLM-generated contextual phrases instead of fixed clips. x.com/settinghead/st…

Warcraft III Peon voice notifications for AI agents like Claude Code or Codex. Stop babysitting your terminal. github.com/PeonPing/peon-…

@naman10parikh At 100 panes, how do you tell which one beeped? Voxlert gives each session a distinct voice — you hear which agent needs you. x.com/settinghead/st…

the solution: agentgrid 10x10 claude instantly: 10 rows × 10 columns of tmux panes, each running Claude Code. colored status labels appear automatically: ✅ DONE (green) ⏳ WAITING (yellow) ⚡ WORKING (blue) sound alerts when any agent finishes

just shipped agentgrid. spawn up to 100 Claude Code instances in one command. watch them all work in parallel. see which ones are done, which need input, which are still running. one-line installer. completely free. x.com/naman10parikh/…

@jinx07302333 Same problem here! I took it a step further — each session gets a distinct character voice so you know WHICH agent needs you by ear. x.com/settinghead/st…

💥My workflow: prompt → alt-tab → forget → come back 10 min later → agent has been staring at me waiting for input 💡Built ai-bell to stop doing this to myself. Plays a sound when your AI coding agent needs you. That's literally it. 🔧 npm install -g ai-bell