11 articles

📰 Dev.to · Laurent DeSegur

Articles from Dev.to · Laurent DeSegur · 11 articles · Updated every 3 hours · View all reads

All ⚡ AI Lessons (9068) ArXiv cs.AIDev.to · FORUM WEBForbes InnovationOpenAI NewsDev.to AIHugging Face Blog
Cross-Session Lessons in Carnival9: How an Agent Remembers What Worked
Dev.to · Laurent DeSegur 9h ago
Cross-Session Lessons in Carnival9: How an Agent Remembers What Worked
The problem nobody admits is hard An agent runs the same task twice and makes the same...
Read article → + Playlist
Two Ends of the Token Budget: Caveman and Tool Search
Dev.to · Laurent DeSegur 13h ago
Two Ends of the Token Budget: Caveman and Tool Search
Every Claude Code session has a single budget: the context window. Two hundred thousand tokens, give...
Read article → + Playlist
Five Atomic Skills, Two Approaches: Claude Code and a Paper
Dev.to · Laurent DeSegur 1d ago
Five Atomic Skills, Two Approaches: Claude Code and a Paper
The Paper's Claim In late 2025, a paper appeared on arXiv arguing that the way the field...
Read article → + Playlist
How Claude Code Remembers (And Forgets): The Memory and Persistence Architecture
Dev.to · Laurent DeSegur 1d ago
How Claude Code Remembers (And Forgets): The Memory and Persistence Architecture
Claude Code processes thousands of lines of code, generates insights, solves bugs, discovers...
Read article → + Playlist
The Upstream Proxy: How Claude Code Intercepts Subprocess HTTP Traffic
Dev.to · Laurent DeSegur 2d ago
The Upstream Proxy: How Claude Code Intercepts Subprocess HTTP Traffic
When Claude Code runs in a cloud container, every subprocess it spawns — curl, gh, python, kubectl —...
Read article → + Playlist
How Tool Search Defers Tools to Save Tokens
Dev.to · Laurent DeSegur 3d ago
How Tool Search Defers Tools to Save Tokens
Claude Code can use dozens of built-in tools and an unlimited number of MCP tools. Every tool the...
Read article → + Playlist
How Claude Code Extends Itself: Skills, Hooks, Agents, and MCP
Dev.to · Laurent DeSegur 3d ago
How Claude Code Extends Itself: Skills, Hooks, Agents, and MCP
The Problem You want Claude Code to know your team's conventions, run your linter after...
Read article → + Playlist
What Happens When Claude Code Calls the API
Dev.to · Laurent DeSegur 3d ago
What Happens When Claude Code Calls the API
The Problem You type a message. The model needs to see it, along with every previous...
Read article → + Playlist
94% Exposed, 30% Adopted: Why Engineering Leaders Need to Rethink How They Hire
Dev.to · Laurent DeSegur 4d ago
94% Exposed, 30% Adopted: Why Engineering Leaders Need to Rethink How They Hire
Anthropic's own economist says the "Great Recession for white-collar workers" is possible....
Read article → + Playlist
How Bash Command Safety Analysis Works in AI Systems
Dev.to · Laurent DeSegur 5d ago
How Bash Command Safety Analysis Works in AI Systems
Most people think validating shell commands is simple. Scan for rm, block eval, done. It's...
Read article → + Playlist
OpenAI Just Shipped a Plugin So Codex Runs Inside Claude Code
Dev.to · Laurent DeSegur 1w ago
OpenAI Just Shipped a Plugin So Codex Runs Inside Claude Code
The real story isn't the three commands. It's the admission hiding inside the...
Read article → + Playlist