~/blog/series/ai-skeptic
The AI Skeptic
Using AI without outsourcing your thinking.
You don't have an AI problem. You have a process problem.
AI doesn't introduce new mistakes. It exposes existing gaps in your process. On source maps, pipelines, and why you can't outsource discipline.
read →Why you should never ship code you don't understand
If you can't explain your code to a colleague without saying 'the AI wrote that', it doesn't belong in your repo. On black boxes, self-validating tests, and why hope is not a strategy.
Stop copy-paste engineering
We're breeding a generation of developers sprinting full speed toward a cliff. On AI hallucinations, echo chamber tests, and why your brain is the only real debugger.
The Lava Layer: Why AI Code is Slowly Petrifying Your Codebase
We’re building faster than ever, but at what cost? Exploring the invisible accumulation of code that no one truly understands and why your application is turning into impenetrable rock.
The Prompt Is Not the Spec
Developers are treating AI prompts like requirements documents. They're not. On vague intent, confident hallucinations, and why the wrong thing built fast is still the wrong thing.
The Brilliant Parrot Problem: What AI Actually Does When It 'Thinks'
Transformers are extraordinary algorithms. But they are algorithms. On next-token prediction, the blindness of generation, and why a system that cannot see where it's going almost certainly cannot be conscious.
The bureaucracy of bots: Why we are checking the checker
Deploying an AI to double-check the work of another AI produces better results. But we are unwittingly recreating the slow, complex corporate bureaucracy we tried to escape.
The arms race for your trust: Mythos, Cyber and the security hype
Anthropic and OpenAI are fighting for market share with AI security tools they call "too dangerous" to release. But the facts tell a different story than the press releases.
Stop letting your agents write Markdown
Everyone is excited about AI agents generating HTML instead of Markdown. The output looks beautiful. But nobody is asking what it costs, or what we lose when every agent response becomes a single-use webpage.