By
–
A SENIOR ANTHROPIC ENGINEER JUST DROPPED AN 11-PAGE PDF ON LOOP ENGINEERING. The core shift: stop prompting the agent. Build the system that prompts it. Inside the autonomous loop: – Discover → Finds its own work (failing CI, open issues).
– Isolate → Uses separate git
By
–
Act ONE was AI writing the code.
— Charly Wargnier (@DataChaz) 25 juin 2026
Act TWO is AI spotting crashes and pushing its own patches to production.
🚨 Enter @Sazabi.
They just locked in an $8M seed from YC, plus angels out of OpenAI and GitHub.
Their goal is to wipe out the cluttered, chaotic dashboard, and after… https://t.co/3GfVTGBgPr
Act ONE was AI writing the code. Act TWO is AI spotting crashes and pushing its own patches to production. Enter @Sazabi
. They just locked in an $8M seed from YC, plus angels out of OpenAI and GitHub. Their goal is to wipe out the cluttered, chaotic dashboard, and after
By
–
An actually funny AI ad! + doing this 100% in @hyperagentapp for just 200 bucks in tokens is pure genius
By
–
why ppl are ditching OpenClaw for Hyperagent: OpenClaw: You're the weekend sysadmin, updates wipe your agent's memory, takes weeks to wire up. Hyperagent: Runs in browser, durable memory, migrates in minutes ↓
By
–
me chillin’ while @hyperagentapp does all the work
— Charly Wargnier (@DataChaz) 25 juin 2026
vs
my colleague still babysitting his agents in @openclaw https://t.co/l0g3aD75T6 pic.twitter.com/tCr3hdTZJz
me chillin’ while @hyperagentapp does all the work vs my colleague still babysitting his agents in @openclaw
By
–
The entire @MongoDB Academy is 100% free! These 3 courses show you how to build a complete AI system without stitching together dozens of different tools. But there are 28 courses/badges (and counting) in total 🙂
By
–
this guy literally created a Kebab benchmark for LLMs ♨️♨️♨️ pic.twitter.com/9vY9zLdqBe
— Charly Wargnier (@DataChaz) 25 juin 2026
this guy literally created a Kebab benchmark for LLMs
By
–
🚨 Anthropic is accusing Alibaba, DeepSeek, and other Chinese tech giants of orchestrating the largest AI heist in history.
— Charly Wargnier (@DataChaz) 25 juin 2026
Over 45 days, these companies allegedly bypassed geo-blocks to launch a massive "distillation attack",
using 25,000 fake accounts and 28.8 million… https://t.co/N6MWQILdzs pic.twitter.com/HmBkKKlx5c
Anthropic is accusing Alibaba, DeepSeek, and other Chinese tech giants of orchestrating the largest AI heist in history. Over 45 days, these companies allegedly bypassed geo-blocks to launch a massive "distillation attack", using 25,000 fake accounts and 28.8 million
By
–
Just tried this out, it is pretty impressive. great job, @moxt_ai > https://
moxt.ai
By
–
The replacement for small SaaS isn't more software.
— Charly Wargnier (@DataChaz) 24 juin 2026
It’s an agent team building it for you!
Watching @moxt_ai's Mini Apps run specialized agents makes this clear.
If a workflow can just deliver the exact output you need, the subscription model for internal tools will break 👀 https://t.co/lSY3IDcdaW pic.twitter.com/0C2LnJVfsr
The replacement for small SaaS isn't more software. It’s an agent team building it for you! Watching @moxt_ai
's Mini Apps run specialized agents makes this clear. If a workflow can just deliver the exact output you need, the subscription model for internal tools will break