7 min read
I'm fed up of people using the excuse of AI slop
AI slop is the result of weak direction and absent editorial judgement, not an excuse to blame the tool.
Recent Insights Page 1
7 min read
How to Stop Reviewing Agent-Written Code
A multi-agent quality pipeline that replaces routine line-by-line review with executable evidence and deterministic gates.
9 min read
Why LLMs ignore the middle of your context
Long context windows do not guarantee reliable recall. Design retrieval, reranking and prompt assembly so the model can use the evidence it receives.
7 min read
Let an Open-Weight Model Audit Your Code, but Do Not Give It the Keys
How to run a nightly AI security audit without giving the model credentials, production access or authority to merge its own fixes.
7 min read
Claude's Watermarking Policy Extends to Code
Claude's invisible marks could improve provenance, but Anthropic has not yet shown that they leave generated code quality and optimisation untouched.
7 min read
GitHub Now Supports Stacked Pull Requests Natively
What stacked pull requests are, how GitHub's native workflow works, and where the public preview still needs care.
5 min read
Configure AI Models Instead of Hard-Coding Them
Keep model names in configuration, select models by task, and compare routes using the cost of completed work.
6 min read
The Safest Dependency Update May Be the One You Delay
Why a short cooldown for routine dependency releases is a practical supply-chain control, not neglect disguised as caution.