Claude Code "Simplify", Outages, and Dev Future with AI
And more AI Coding news: March 4, 2026.
Hey hey,
A usual weekly newsletter covering what is happening in AI coding community, including a few of my videos and tutorials. Enjoy!
For Paid Substack Subscribers
Future of Devs in 1-5 Years: Reflection on AI from Laracon EU Conference
“What will we do as devs in five years? Will our jobs survive against vibe-coding wave and agentic coding?” - these are just a few questions I heard over last two days, at a conference in Amsterdam called Laracon EU for Laravel/PHP developers. Most of 1,000+ attendees were talking about AI and how we adapt to that “new era”. I have FOUR thoughts and takeaways from Laracon audience.
My YouTube videos
I Tried a NEW Claude Code /simplify Command to Improve Code
Claude Code released a new feature to launch Code Simplifier automatically, let’s see the result.
NEW Visual Explainer Skill: HTML Plans/Summaries (Claude Code Example)
A new skill that got very popular on Github quickly to visualize the project.
NEW in Claude Code: Git Worktrees - WHEN You Would Use Them?
If you want multiple AI coding agents to run in parallel on the same codebase, worktrees may help.
From AI Coding Community
Announcing Polyscope - the free agent orchestration tool
x.com
Run dozens of AI agents at the same time.
Anthropic’s current reliability is embarrassingly low for any infra company.
x.com
On the other hand, seeing these beyond terrible reliability numbers suggests there might be a downside to all this speed.
Voice mode is rolling out now in Claude Code
x.com
It’s live for ~5% of users today, and will be ramping through the coming weeks. You’ll see a note on the welcome screen once you have access. /voice to toggle it on!
Codex 0.107.0 is here, and with it: FORKS.
x.com
This minor update includes the ability to fork your current chat history directly with custom multi agents with just a quick prompt.
Updates in Claude Code AskUserQuestion tool
x.com
The AskUserQuestion tool can now show markdown snippets to display diagrams, code examples, etc.
Lessons from Building Claude Code: Seeing like an Agent
x.com
Article by Thariq from Claude Code. How do you design the tools of your agent? Do you need just one tool like code execution or bash? What if you had 50 tools, one for each use case your agent might run into?
Claude Code rolled out a new auto-memory feature.
x.com
Claude now remembers what it learns across sessions — your project context, debugging patterns, preferred approaches — and recalls it later without you having to write anything down.
Stop writing agent skills like human docs
x.com
Rethinking how we build for the agentic era. Stop writing agent skills like human docs—it wastes tokens and invites hallucinations.
That’s a wrap for this week. Keep building with AI!
Povilas Korop
AICodingDaily.com