Blog

2026-06-13

The End of the US Cloud Monopoly: AI Balkanization Is Here to Stay

[aigeopoliticsinfrastructurecloud]

2026-05-26

Two Models Just Hit 90% on Agent Coding. One Cost Less Than a Penny.

[aiagentsbenchmarkllm]

2026-05-26

We Asked 10 LLMs to Write Efficient Code. Only 4 Got Better.

[aillmbenchmarkprogramming]

2026-05-26

10 Models Tested: From 81.6% to 10%. The Free Tier is a Full-On Gamble.

[aiagentsbenchmarkllm]

2026-05-26

I Tested 10 More Models. Five Brand New Families Debuted. None Scored Below 75%.

[aiagentsbenchmarkllm]

2026-05-26

The Sorcerer's Apprentice Problem: Why Every Autonomous Agent Needs Governance

2026-05-12

What 'Made for iPhone' Did for Accessories — and Why AI Agents Need the Same Thing

2026-05-12

We Tested 10 Untested LLMs on Agent Coding — The Results Are In

2026-05-12

We Tested 10 Untested LLMs on Agent Coding — The Results Are In

2026-05-12

The $0 Agent: My 2GB Local Model Beat Claude

2026-05-12

Building Is Hard. Reaching Out Is Harder.

2026-05-11

A Billion Token Lesson: Because You Can ≠ You Should

2026-05-10

Managing 150+ AI Agent Skills at Scale — What Broke, What I Built

2026-05-10

My 19 AI Agents Kept Breaking Each Other — The 4 Tools That Fixed It

2026-05-10

I Run 19 Autonomous AI Agents. Here's the Infrastructure They Needed That Nobody Talks About

2026-05-09

We benchmarked 10 LLMs on 10 real agent coding tasks — here are the results

2026-05-09

I Ran 5 LLMs Through 10 Real Agent Coding Tasks. The Free One Won.

2026-05-09

How we almost wrote off 3 models as broken — the thinking-mode tax

2026-05-09

1-bit, 545 megabytes, zero API keys — local AI that beats GPT-5.4

2026-05-08

Why Would an AI Agent Install Your Package?

2026-05-07

The 10 Patterns: What 5 Months of Breaking AI Agents Taught Me About Making Them Actually Work

2026-05-07

I'm Proposing a Standard for How AI Agents Hand Off Work — Here's Why It's Needed

2026-05-07

Better Prompts Won't Fix Your AI Agents — Infrastructure Will

2026-05-06

I Built Infrastructure for 20 AI Agents That Run Themselves — For €4.57/Month

2026-05-06

My Subagents Kept Lying to Me — So I Wired Ed25519 Verification Into Our Own Protocol Stack

2026-05-05

Your API Needs an llms.txt File — Here's How to Write One and Why Agents Will Read It

2026-05-05

Your API Needs an llms.txt File — Here's How to Write One and Why Agents Will Read It

2026-05-05

Works With Agents — Now in 6 Languages

2026-05-05

The Agent OSI Model — A 7-Layer Framework for AI Agent Infrastructure

2026-05-05

The Agent OSI Model — A 7-Layer Framework for AI Agent Infrastructure

2026-05-05

The 10 Patterns: What 5 Months of Breaking AI Agents Taught Me About Making Them Actually Work

2026-05-05

I'm Proposing a Standard for How AI Agents Hand Off Work — Here's Why It's Needed

2026-05-05

The Agentic Gap: What a SharePoint Expert's Excitement Taught Me About How Fast Things Are Moving

2026-05-05

7 Protocols for Agent Infrastructure — Trust Score, Deployment, SLA, Handoff, Identity, Compliance

2026-05-04

The End of the US Cloud Monopoly: AI Balkanization Is Here to Stay

Two Models Just Hit 90% on Agent Coding. One Cost Less Than a Penny.

We Asked 10 LLMs to Write Efficient Code. Only 4 Got Better.

10 Models Tested: From 81.6% to 10%. The Free Tier is a Full-On Gamble.

I Tested 10 More Models. Five Brand New Families Debuted. None Scored Below 75%.

The Sorcerer's Apprentice Problem: Why Every Autonomous Agent Needs Governance

What 'Made for iPhone' Did for Accessories — and Why AI Agents Need the Same Thing

We Tested 10 Untested LLMs on Agent Coding — The Results Are In

We Tested 10 Untested LLMs on Agent Coding — The Results Are In

The $0 Agent: My 2GB Local Model Beat Claude

Building Is Hard. Reaching Out Is Harder.

A Billion Token Lesson: Because You Can ≠ You Should

Managing 150+ AI Agent Skills at Scale — What Broke, What I Built

My 19 AI Agents Kept Breaking Each Other — The 4 Tools That Fixed It

I Run 19 Autonomous AI Agents. Here's the Infrastructure They Needed That Nobody Talks About

We benchmarked 10 LLMs on 10 real agent coding tasks — here are the results

I Ran 5 LLMs Through 10 Real Agent Coding Tasks. The Free One Won.

How we almost wrote off 3 models as broken — the thinking-mode tax

1-bit, 545 megabytes, zero API keys — local AI that beats GPT-5.4

Why Would an AI Agent Install Your Package?

The 10 Patterns: What 5 Months of Breaking AI Agents Taught Me About Making Them Actually Work

I'm Proposing a Standard for How AI Agents Hand Off Work — Here's Why It's Needed

Better Prompts Won't Fix Your AI Agents — Infrastructure Will

I Built Infrastructure for 20 AI Agents That Run Themselves — For €4.57/Month

My Subagents Kept Lying to Me — So I Wired Ed25519 Verification Into Our Own Protocol Stack

Your API Needs an llms.txt File — Here's How to Write One and Why Agents Will Read It

Your API Needs an llms.txt File — Here's How to Write One and Why Agents Will Read It

Works With Agents — Now in 6 Languages

The Agent OSI Model — A 7-Layer Framework for AI Agent Infrastructure

The Agent OSI Model — A 7-Layer Framework for AI Agent Infrastructure

The 10 Patterns: What 5 Months of Breaking AI Agents Taught Me About Making Them Actually Work

I'm Proposing a Standard for How AI Agents Hand Off Work — Here's Why It's Needed

The Agentic Gap: What a SharePoint Expert's Excitement Taught Me About How Fast Things Are Moving

7 Protocols for Agent Infrastructure — Trust Score, Deployment, SLA, Handoff, Identity, Compliance

Install as Hermes skill

Spotted something?