NEW Claude Code Update Changes EVERYTHING!
Skills:
LLM Engineering70%
Key Takeaways
Updates Claude code using new features and tools
Full Transcript
New Claude code update changes everything. Claude code just dropped version 2.1.178 and it fixes three things that actually matter. First, search got dramatically faster. Claude code is now guided to use rip grep under the hood, which can run code searches five to 10 times faster on large projects. Since the agent searches your files constantly while it works, everything downstream speeds up with it. Second, permissions went surgical. You can now write rules down to a specific tool, parameter, and value with wildcards to cover a whole category at once. Rather than trusting an agent with everything or locking it down completely, you can say edit only this folder or block any command that touches that directory. Third, and this is the big one, sub-agents can no longer slip past your rules. Before, a parent agent could spawn a sub-agent that bypassed its permissions just because the check ran too late in the sequence. Now, every sub-agent gets evaluated before it launches, and if it tries a blocked action, the call is denied. Faster search, precise permissions, sub-agents that stay in bounds,
Original Description
Get the Agent OS 👉 https://www.skool.com/ai-profit-lab-7462/about
Want to make money and save time with AI? Join here: https://www.skool.com/ai-profit-lab-7462/about
Video notes + links to the tools 👉 https://www.skool.com/ai-profit-lab-7462/about
Get a FREE AI Course + Community + 1,000 AI Agents 👉 https://www.skool.com/ai-seo-with-julian-goldie-1553/about
Get a FREE AI SEO Strategy Session → https://go.juliangoldie.com/strategy-session?utm=julian
Get 200+ Free AI SEO Prompts → https://go.juliangoldie.com/chat-gpt-prompts
Get out SEO link building book here 👉 https://go.juliangoldie.com/opt-in?utm=julian
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
More on: LLM Engineering
View skill →Related Reads
📰
📰
📰
📰
Prompts Are Not Dead, Bad Prompts Are. How to write a Perfect Prompt?
Medium · Programming
Chunking Isn’t Preprocessing, It’s Architecture
Medium · LLM
Running LLMs Locally in 2026: The Complete Guide to Benefits, Trade-offs, and Getting Started
Dev.to AI
A Four-Part Prompt Structure for Financial Variance Commentary (That Actually Holds Up)
Dev.to · Clarity With AI
🎓
Tutor Explanation
DeepCamp AI