AI Disruption
Subscribe
Sign in
Home
Podcast
Chat
Chip
Meta
Paper
Qwen
Agent
Robot
Cursor
Google
OpenAI
AI Code
AI Video
Amazon
Microsoft
Windsurf
Anthropic
DeepSeek
AI Weekly
Elon Musk
AI Writing
AI Painting
AI Business
🎈 Guest Posts
AI Open Source
Chinese Outbound
Foundation Model
Archive
About
AI Code
Latest
Top
Discussions
Musk's Grok Bot Is Here!
Musk drops Grok Bot—an AI teammate with its own cloud PC. Works 24/7, runs multiple bots, and automates real tasks like a human colleague.
Aug 12
Â
•
Â
Meng Li
15
4
mattpocock's loop-me: Automate Your Weekly Routine
Matt Pocock's loop-me Skill turns repetitive weekly tasks into executable workflow specs through 27 rounds of interrogation—no agent questions left…
Aug 11
Â
•
Â
Meng Li
17
5
Claude Code Starts Managing a Team of Agents
Multi agent collaboration in Claude Code now works with isolated worktrees and cross session messaging.
Aug 10
Â
•
Â
Meng Li
17
4
Claude Code Sessions: Shareable, No Copy-Paste
Claude Code sessions can now exchange messages. Stop copying context between terminals. Learn how to pass handoff summaries, not full history, and…
Aug 8
Â
•
Â
Meng Li
10
2
4
Good Agent use needs a User Harness
Learn how to build a User Harness around your AI Agent with Guides and Sensors to boost accuracy, reduce errors, and improve coding task success.
Aug 7
Â
•
Â
Meng Li
7
2
Meta Officially Releases Muse Code
Meta launches Muse Code beta and Muse Spark 1.2 with aggressive pricing. Can its data sharing discount strategy compete with DeepSeek V4 Flash in the AI…
Aug 6
Â
•
Â
Meng Li
14
3
Claude Code Just Tested Login in Chrome on Its Own
Claude Code Chrome integration lets AI test login flows, fill forms, read console errors, and control your browser in real time. See how it works.
Aug 5
Â
•
Â
Meng Li
11
4
Superpowers vs gstack: AI Coding's 3 Weak Spots, Half-Fixed
Superpowers vs gstack compared. Learn how these AI coding frameworks fix different failure modes: wrong requirements, poor quality, and broken delivery…
Aug 4
Â
•
Â
Meng Li
12
3
My Honest Take on Superpowers & Matt Pocock's 55 Skills
My honest review of Superpowers and Matt Pocock's 55 Skills—what works, what doesn't, and my actual setup.
Aug 3
Â
•
Â
Meng Li
10
4
SuperPowers' Systematic Debugging Impressed Me Most
This deep dive explores how Superpowers systematic debugging skill transforms AI agent coding quality with a four phase root cause process that every…
Aug 2
Â
•
Â
Meng Li
12
3
Claude Agents: 3 Layers Max, but Less Recommended
Claude Code now nests sub-agents 3 layers deep. Official advice warns most programming tasks don't need multi-agent systems.
Jul 31
Â
•
Â
Meng Li
13
3
Messaged Claude Code on Telegram, It Ran in Terminal
Control Claude Code from Telegram or iMessage. Run terminal commands, debug code, and fix bugs remotely from your phone in real time.
Jul 29
Â
•
Â
Meng Li
12
3
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts