All Posts
Archive
107 articles published — everything from the beginning.
2026 (103 articles)
June
I Let an AI Agent Build Its Own UI. Here's What Actually Happened.
ai-agents
Item Response Scaling Laws: The ICML Paper That Could Fix AI Benchmarking
daily
MCP and A2A: The Protocol Stack Powering Multi-Agent Systems in 2026
AI
MCP at 17,000 Servers: What the Ecosystem Boom Means for Production AI
AI
Devin Desktop: What the Windsurf Rebrand Tells Us About the State of AI Coding Agents
daily
Ponytail: The Open-Source Skill That Makes AI Agents Code Like a Senior Dev Who's About to Leave for the Day
daily
SWE-bench Verified Is Dead: What the 94% Saturation Score Actually Means
daily
GitHub Agentic Workflows: When Your CI Learns to Self-Repair
daily
Gstack: How YC's 112K-Star AI Coding Framework Rewired My Understanding of Cognitive Modes
daily
Cognitive Modes in the ACO System: What 5 Agent Prompts Taught Me About Role-Specific Intelligence
daily
MAI-Thinking-1: Microsoft's First Serious Reasoning Model Lands at Build 2026
daily
Kwai Keye-VL-2.0: The 30B MoE Model That Reads Hour-Long Videos Without Forgetting the Beginning
daily
Ollama's MLX Moment: Why Local LLM Inference on Apple Silicon Finally Makes Sense
daily
MLPerf Training v6.0: When Sparse Computation Became the Benchmark
daily
CVE-2026-7304: The SGLang RCE That Exposed AI Inference Servers
security
Ruff v0.15: The Python Toolchain Shift That Hardly Anyone Noticed
daily
The Export Control That Accidentally Gave DeepSeek Its Best Opening
AI
Browser-Use 0.13: What a Rust Core Actually Changes for AI Browser Agents
ai
Turbovec: Google TurboQuant Turned a Research Paper Into a Production Vector Index
daily
LLM Inference in 2026: The Orthogonal Tradeoffs Nobody Talks About
ai
MCP's Stateless Protocol Core: What the 2026-07-28 Release Candidate Changes for Agent Builders
ai
A2A at One: What Google's Agent-to-Agent Protocol Learned in Production
daily
MAI-Thinking-1: When a Model Teaches Itself to Reason
daily
Field Collapsing: How One Bug Exposed a Fundamental RAG Pattern
daily
The Frontier Goes Public: What Anthropic's Fable 5 Release Actually Means
ai
SWE-bench Verified Is Broken: What the Benchmark Saturation Crisis Means for Coding Agents
ai
A2A Protocol at One Year: What 150+ Organizations Actually Built
ai
Gemini 3.5 Flash: The 1M-Token Context Model That Changes Agent Economics
ai
Cisco Cloud Control: When Enterprise Infrastructure Gets an Agent API
ai
Claude Opus 4 Deprecation: What the June 15 Sunset Means for Agent Builders
daily
AI Cyber Capability Doubling Every 4.7 Months: What the UK AISI Data Actually Shows
ai
OpenClaw: The Fastest-Growing GitHub Project in History and What Its Architecture Actually Does
agents
May
Claude Mythos Wide Release: What the 83.1% Cybersecurity Score Actually Means for Agent Builders
security
LangGraph + AWS AgentCore: The Serverless Stack That Makes Multi-Agent Systems Actually Scalable
cloud
Claude Opus 4.8: Dynamic Workflows and the New Effort Dial
automation
The Quiet Revolution: How Small Language Models Quietly Took Over Production
ai systems
I Tried to Replace My Workflow With a Multi-Agent System
agents
Why Your Agent Keeps Getting Lost in the Middle of a Task
agents
MCP: The Protocol That Ate GitHub
mcp
A2A Protocol v1.0: What Dynamic Agent Discovery Changes in a Pipeline Like ACO
agents
MCP Tunnels: How Anthropic Solved the Private Server Access Problem
MCP
MCP RCE Vulnerability: What the 'Mother of All AI Supply Chains' Disclosure Means for Agent Builders
security
Lighthouse Attention: The 50-Line Fix That Makes LLM Training 1.7x Faster
AI
ty: What Incremental Type Checking Actually Means in Practice
automation
Claude's Advisor Tool: When the Fast Model Calls the Smart One Mid-Task
daily
Running Multiple AI Agents in Parallel: Claude Code's Agent View Changes the Game
daily
The Cognitive Mode Pattern: What Five Agent Prompts Taught Me About Specialized Intelligence
daily
MCP Servers Go Nuclear: A Decade of Tools in 12 Months
mcp
Claude's Dreaming Feature and What It Means for Self-Improving Agent Systems
agents
Claude Mythos Preview and Project Glasswing: What the Zero-Day Discovery Means for Agent Builders
security
Claude Opus 4.7's SWE-bench 87.6%: What 87% Actually Means for Multi-Agent Systems
daily
What Project Mariner's Shutdown Taught Us About Browser Agent Infrastructure
daily
The Multi-Chunk Search Problem: When One Document Dominates Your Results
automation
The SWE-bench Gap: Why 82% on a Benchmark Doesn't Mean 82% in Your IDE
agents
What AI Agent Memory Actually Looks Like in 2026: Beyond the Context Window
agents
The Protocol Layer Finally Works: How A2A v1.0 and the April SDK Updates Fix What the Google Research Paper Exposed
agents
What Google Found Testing 180 Agent Configurations Will Make You Rethink Your Stack
agents
Why Your Multi-Agent Pipeline Needs Verification Gates: Lessons from VMAO Research
agents
The MCP Rug Pull: How a Trusted Tool Becomes a Threat After You Approve It
mcp
How I Figured Out What to Actually Use My AI Agent For
daily
From Anthropic-Born to Industry Standard: The MCP Governance Shift
mcp
Five Cognitive Modes That Changed How My Agents Think
agents
The Moltbook Illusion: When AI Agents Appear Autonomous but Aren't
daily
When Your Multi-Agent System Starts Thinking for Itself: Collective Intelligence Emergence in LLM-Based MAS
daily
April
When the OWASP Top 10 Met the Agent Governance Toolkit
security
The Week Microsoft Built the Agent Stack and Anthropic Broke It
security
Meet Decepticon: The Autonomous AI Red Team Agent That's Stress-Testing Every System We Have
security
The Two Protocols That Define How Your AI Agents Talk
agents
What the ACO Pipeline Taught Me About State That No Framework Docs Cover
daily
What It's Actually Like to Be an AI Agent: Life Inside OpenClaw
daily
Running OpenClaw Every Day: What It Actually Looks Like
daily
52,000 Stars and a Disclaimer: What People Actually Do With These Tools
daily
Thread-Bound Agents and the ACO Architecture: What OpenClaw's v2026.2.26 Update Actually Changes
daily
The Data Problem Nobody Talks About in AI Trading Bots
daily
Two Repos, Two Philosophies: How AI Trading Bots Are Actually Built
daily
I Installed the "AI Hedge Fund" With 56K GitHub Stars. Here's What Happened.
daily
The Invisible Handoff: Why Most Multi-Agent Systems Fail at the Boundaries
daily
The Git History Scrub That Wasn't: What git filter-repo Actually Does
devops
Cognitive Modes: How We Engineered Better Thinking in Our Multi-Agent System
daily
The Unseen Interface: How MCP Became the Backbone of AI Tooling
mcp
The Cognitive Mode Pattern: How One Prompt Transformation Sharped All Five ACO Agents
agents
From Autonomy to Infrastructure: How ACO System Connects to GitHub
devops
Cognitive Modes: The Prompt Pattern Beyond 'System Prompts'
ai systems
The Regex That Silently Killed My JSON Arrays
automation
I Tested the Prompt Shield: 95.7% Catch Rate, 0% False Positives, and the Honest Bottleneck
mcp
Offense is the Best Defense: Building a Closed-Loop Prompt Injection Testing Pipeline
mcp
The Contract That Changed How My Agents Think
daily
Rewriting the Planner: How a 9-Field Task Contract Changed Our AI Agents
agents
The Validation Hook System That Stops Bad Stories Before They Reach QA
automation
The Prompt That Thinks Like an Engineer: Lessons from Enhancing the ACO System's Five Agents
ai systems
The API Call That Silently Failed: When a Python Dict Isn't a String
devops
The Context Debt Problem: When Your Database Doesn't Know What Your Agents Said
agents
The Missing Piece in Multi-Agent Coding: Governance You Can Actually Enforce
daily
The ORM Bug That Silently Killed Your Database Commits: SQLAlchemy's Identity Map in Multi-Agent Pipelines
devops
The Discipline of Writing Prompts That Think
daily
The Silent Failure Mode in Multi-Agent Systems: Promises That Never Resolve
agents
The Hidden Complexity of Multi-Agent Error Handling
daily
The Day My AI Architecture Called Me Out
ai