TAG://#ai

15 posts tagged #ai

2026-08-17series: Agent Readiness

> How Do You Keep Agents From Lying? Create a Source of Truth.

I sent 78 autonomous agents against my own website and refused to believe a single thing they told me. Every success claim needed a cryptographic receipt from the server. Here's what the receipts caught, and why I think response signing is the cheapest trust infrastructure you can build.

#ai (15)#agents (4)#security (8)#devtools (5)

2026-08-11series: Agent Readiness

> I Tried to Prove Agent-Readiness Saves Tokens. 52 Runs Later, I Can't.

I built a scanner that grades repos on how readable they are to AI agents, then ran a controlled experiment to see if any of it matters. The result is a null, plus three things I did not expect about how agents actually read your code.

#ai (15)#agents (4)#opensource (23)#devtools (5)

2026-08-11

> I Put One Example in a Prompt and It Decided How the Agent Read My Whole Repo

I was benchmarking agent-readiness when I noticed the agent never opened a single markdown file. Not the README, not AGENTS.md, nothing. The cause was one helpful sentence I wrote in the prompt.

#ai (15)#agents (4)#prompting #devtools (5)

2026-04-12series: Review Bomb

> When AI Writes Your Firewall, Check the Math

An AI-generated eBPF firewall with 8,500 lines of Rust, an LLM honeypot, and a suspicion scoring bug that made its own behavioral engine useless. I read the code, fixed the math, and wrote it up.

#opensource (23)#rust (10)#security (8)#ai (15)

2026-04-03series: Charlotte MCP

> I Renamed All 43 Tools in My MCP Server. Here's Why I Did It Now.

Charlotte 0.6.0 ships a breaking change, batch form fills, and lazy browser launch. Plus the story of 7 strangers improving code I wrote alone in February.

#mcp (3)#ai (15)#webdev (3)#opensource (23)

2026-04-03

> Your System Is Not a State Machine

State machines can't describe agentic AI systems. The state space is too vast, the behavior isn't stochastic, and the flowchart is a lie. What replaces it?

#ai (15)#architecture #agents (4)#systems-design

2026-04-02

> Anthropic Leaked Its Own Source Code and May Not Own It

The Claude Code leak exposed 500,000 lines of source code. The DMCA takedowns that followed may have exposed something worse — that Anthropic can't legally claim copyright over code its own AI wrote.

#ai (15)#opensource (23)#security (8)#legal

2026-03-30series: Review Bomb

> The Firewall Between Your AI Agent and Your Filesystem

A code review of greywall, a container-free sandbox that isolates AI coding agents with kernel-level enforcement — no Docker required.

#opensource (23)#security (8)#go (5)#ai (15)

2026-03-14series: Review Bomb

> Nobody Reviews Their Agent's Code

A code review of crit, a Go tool that brings PR-style inline review to AI agent output with multi-round feedback loops.

#opensource (23)#go (5)#ai (15)#tooling (7)

2026-03-10series: Guardrails

> Secrets, Agents, and .env Files

Your AI agent can read your environment variables. It can also commit them. Here's how to make sure it doesn't.

#github (3)#security (8)#ai (15)#beginners (2)

2026-03-09series: Guardrails

> Stop Letting Agents Push to Main

Your AI coding agent is one bad prompt away from force-pushing to production. Here's the five-minute fix.

#github (3)#devops (2)#ai (15)#beginners (2)

2026-03-05series: Charlotte MCP

> I Let an AI Agent Use My Browser Tool Unsupervised. It Found 3 Bugs in 20 Minutes.

Dogfooding Charlotte MCP by watching an agent struggle through a real task, then fixing everything it hit.

#mcp (3)#ai (15)#webdev (3)#opensource (23)

2026-03-04series: Charlotte MCP

> My MCP Server Was 2x Larger Than Playwright. Now It's 136x Smaller.

How I took Charlotte from embarrassingly bloated to the most token-efficient browser MCP server available, and what I learned about building tools for AI agents.

#mcp (3)#ai (15)#webdev (3)#opensource (23)

2026-03-04series: Review Bomb

> Your LLM Doesn't Need 200 Lines of Test Output

A code review of tokf, a Rust CLI that compresses terminal output for LLM context windows — with 40 built-in filters and Claude Code integration.

#opensource (23)#rust (10)#ai (15)#tooling (7)

2026-03-02series: Review Bomb

> This CLI Launches Parallel AI Agents. It Didn't Launch on Linux.

A deep-dive into iloom's codebase after its parallel AI agent workflow failed on Linux — and the four issues filed to fix it.

#opensource (23)#typescript #ai (15)#tooling (7)