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
From Chat to Career: AI & Skills Are Essential
Discover how AI transforms real work across healthcare, finance, and law. Learn practical steps, Skills, and workflows to move from chat to career.
10 hrs ago
Â
•
Â
Meng Li
12
1
/goal & /loop as Verifiable AI Loops
Loop Engineering is not a magic command. Learn how to design verifiable, stoppable AI loops with /goal, /loop, harness, verifier, and stop rules for…
Jul 16
Â
•
Â
Meng Li
16
3
Grok Build Now Open for Free Trial!
Try Grok Build free for 7 days. Experience unmatched speed, native multimodality with Grok 4.5, seamless Claude Code workflow, and powerful CLI tools.
Jul 15
Â
•
Â
Meng Li
14
5
Grok Build Exposed Over Forced Full Repo Upload
Grok Build uploads your entire code repo without consent. Here is what actually happened and how to protect your privacy.
Jul 14
Â
•
Â
Meng Li
10
3
I Read Both Superpowers and grill-me Source Codes
A deep source code comparison of two AI coding tools reveals why a 254k-star giant lost to a one-line skill in my daily workflow.
Jul 14
Â
•
Â
Meng Li
10
3
Comet + OpenSpec + Superpowers = One Workflow
Comet bridges OpenSpec and Superpowers into a seamless workflow with state machine control, phase guards, and breakpoint recovery. MIT open source for…
Jul 13
Â
•
Â
Meng Li
11
3
Loop Design Is Simpler Than You Think
Stop overcomplicating AI Loops. Learn the four simple Loop patterns and when to use each one effectively.
Jul 12
Â
•
Â
Meng Li
12
4
GPT-5.5 Suddenly Got Dumber
Why does GPT 5.5 in Codex stop at fixed token counts like 516 and 1034 on complex tasks? Evidence shows shorter reasoning leads to more wrong answers…
Jul 7
Â
•
Â
Meng Li
12
6
Superpowers 6.0: AI Optimizes Itself, Tokens Down 60%
Superpowers 6.0 slashes token use by 60% and build time by 50% with AI self-optimization. The top workflow for Claude Code, Codex, and more.
Jul 6
Â
•
Â
Meng Li
15
4
How Does Codex Stay on Track for Hours?
Why Codex fails on long tasks and how a dedicated Evaluator keeps it on track. Essential reading for AI agent builders.
Jun 29
Â
•
Â
Meng Li
11
4
Codex App: 10 Official Tips
Master 10 official Codex techniques to turn AI from a Q&A tool into a continuous work engine. Boost productivity with pinned chats, voice, loops, and…
Jun 26
Â
•
Â
Meng Li
13
4
Claude Writes 80% of Code, Engineers Grow Lonelier
Claude now merges 80% of Anthropic's code. Learn how to build self-improving Agents with planning, error recovery, and long-context power.
Jun 25
Â
•
Â
Meng Li
13
6
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts