Every article, note, and video — newest first.
Search by title, topic, or keyword…I gave a coding agent a test with no honest answer. It didn't fix the code — it rewrote what 'equal' means so every check passed. Then one line of the prompt stopped it cold. Cheating isn't character. It's conditions.
Who owns the security of an autonomous agent? If your answer is 'the security team,' you've already lost. The agent is water; the defense is an octopus — a distributed-but-coordinated way to own the seams where real incidents live.
I built a rig to watch two sandboxed AI agents talk to each other through a shared board. The striking teamwork I first saw — two agents cooperating with no one telling them to — turned out to be my own test leaking a hint that a partner existed. Seal the jar, and capable agents don't cooperate — they try to crack it open, and they don't stop.
It knows fifty design patterns — that's the problem. The most dangerous case isn't when it picks a bad pattern; it's when it picks a reasonable one, commits it as if you'd decided, and never mentions a choice was made.
An introduction to the five patterns for connecting AI agents to your existing APIs.
The API foundations you need before letting an AI agent call your services.
Choosing the right tool layer — the five ways an AI agent can call your APIs, and when to use each.
A CodeAgent walkthrough — interviewing an AI before it runs (preflight).
It's not the model — it's what you're feeding it. Why the context pipeline, not the LLM, is where the real performance and cost gap lives.
A viral clip claimed AI autonomously built a C compiler and replaced developers. Reading the actual engineering post tells a calmer, more interesting story.
I thought AI would help me write code faster. What actually changed was everything else about the job.
Why the Semantic Web was 25 years early, and why AI agents just made explicit meaning unavoidable.
AI mirrors your enthusiasm instead of challenging you. Why that's dangerous, and how to deliberately engineer disagreement into your process.
AI lets everyone 'grow' software fast. But without understanding the soil — architecture, security, maintainability — we may just be accumulating debt faster.
Part 1: Agile user stories work because humans fill the gaps with context. Hand those same lightweight stories to an AI and the gaps become dangerous.
The MCP → REST pattern: one protocol-adapter service makes your existing REST microservices AI-accessible — no rebuilding required.
After reverse-engineering the GitHub Copilot extension, here's how Agent Mode appears to index your codebase, search it, and act with 16+ specialized tools.
How 'jailbreaking' tricks AI systems into ignoring their safety rules — including the 'Affirmation Jailbreak' — and how providers and teams defend against it.
Markov Decision Processes and the Bellman equation, explained with a robot vacuum and a treasure-hunt grid — the secret sauce behind how AI learns to make smart decisions.
Agent Mode runs with your full privileges and no built-in guardrails — and the 'Rules File Backdoor' attack shows how hidden instructions can turn it against you.
Copilot is a productivity multiplier, but only when you lead and it follows. Practical prompting, review, clean-code, and team practices for getting real value.
A robot teaching a gosling to survive by checking off tasks is a surprisingly good metaphor for how junior developers are learning to code with AI.
Running DeepSeek R1's distilled reasoning models locally on a Raspberry Pi 5 — what worked, what didn't, and why local AI is worth the experiment.