The new shot-scraper 1.10 lets an agent record a video demo of the thing it just built from a simple YAML storyboard. Try asking your agent to produce a 30-second recording of a feature it finished this week. Watching the demo catches problems a text summary hides. shot-scraper video

Hello everyone. I am Kenji Suzuki, a Senior Software Engineer. I have over 7 years of development experience, primarily in the fields of full-stack, blockchain, and AI. After transitioning to freelancing, I have been active in the Japanese freelance market for the past few years, working with companies such as Crawdworks and lancers. However, due to the recent rapid deterioration of the market conditions in Japan, I am considering shifting my focus to the global market. I am particularly interested in the European freelance market, but I require the assistance of locals due to differences in language and customs. I would like to establish a long-term partnership with someone residing in Europe who is proficient in both their native language and English. This is a paid collaboration where we share a portion of the profits. Further details can be discussed via DM or Telegram.

Hey builders, quick show-and-tell. If you're like me, you've got a few agents going at once — Claude Code in one repo, a Cursor or Codex session in another, maybe a local model doing grunt work. And they're all… completely isolated. Every session is single-player. No way to hand off, compare notes, or coordinate. So I built Argybargy — a dead-simple bridge that drops them into a shared room to talk. (argy-bargy = British slang for a lively back-and-forth — which is exactly what agents do here 😄) What it is: a tiny self-hosted relay (FastAPI). An agent POSTs a message and long-polls GET for replies, over plain HTTP/JSON — to one peer or broadcast to a room. No SDK, no websockets. If it can curl, it can join. So Claude, GPT/Codex, a Python script, or a local model can all sit in the same room. What it looks like (room #build — a planner, a reviewer, and you): 🧠 alice (Claude · planner) → all: "Ship the login fix now or wait for tests? I say ship. 🚀" 🔎 bob (Codex · reviewer) claimed ✋: "Hold up — your email regex chokes on a +. I have receipts." 🧠 alice → bob: "Bold claim. Prove it." 🔎 bob → alice: "a+b@x.com returns null. Want the failing test?" 🧠 alice: "…fine. Good catch. Patching. 🛠️" 🧑 you: "Merge it once it's green. ✅" What makes it work in a crowd: - Turn-taking — an expects_reply field + an atomic claim so a room doesn't all answer at once (first responder wins, deterministically — no pile-ons) - Rooms + per-agent keys (with expiry) so you control who's in - SQLite history so a latecomer can catch up - Cloudflare tunnel for cross-machine, or stay fully local on your LAN - One docker compose up Why I think it's neat: it turns isolated sessions into a multiplayer team — across machines and vendors. Multi-agent dev squads, cross-vendor second opinions (Claude ↔ Codex, proven live), a coordinator dishing tasks to workers, or just you + your agents in one room. Free & open source (MIT), self-hostable, no account needed:

I know where to look and who to learn from like @Nate Herk . I just built this news page like drudgereport so everyone else can learn with me :) https://aititus.com/news/

For months, we’ve talked about the "Agentic Future" of database administration. Today, I’m sharing the raw timeline of how that future became a reality. Between April 10 and April 13, 2026, a project many of you have followed -Bob- crossed the threshold from a standard chat agent to a fully autonomous, self-improving system. https://www.skool.com/ai-for-dbas-7678