- ai
A reader read my benchmark better than I did
I published a fine-tune that beat prompting by 29 points. A commenter said the gap between my two accuracy drops was the real signal. He was right that my table was misleading, wrong about which arm was inflated, and the experiments I ran to check produced a third answer.
- aidevtools
My fine-tuned model scored 100%. The benchmark was lying.
I fine-tuned Mistral 7B with LoRA on a MacBook to detect personal data. On my own test set it scored 100% and prompting nearly matched it. On real data the fine-tune won by 29 points. The dataset had been choosing my conclusion.
- aidevtools
The MCP servers that actually earn their keep with Claude Code
Not a directory of 200 MCP servers: the three I still use after a month of real work, how to wire them cleanly, and the ones I removed.
- aidevtools
Sharing a Claude Code config across a team
Versioned CLAUDE.md, settings.json vs settings.local.json, shared MCP servers, hooks: what gets shared, what stays local, and the traps in between.
- aidevtools
Multiple accounts in Claude Code: the complete setup
How to run multiple Claude Code accounts on one machine, with shell aliases, config isolation, per-project defaults, and the pitfalls nobody warns you about.
- devtoolsai
AI-powered git branch diff summaries
How to generate a smart summary of branch diffs, highlighting deleted files and renames so AI agents have context to review, refactor, or document it.
-
AI infrastructure: a maintenance nightmare
I asked AI to generate Terraform for a standard AWS setup. It produced 2,400 lines that worked perfectly. Here's why I'd never deploy it to production.
- ai
How to check your AI's actual context window
How to verify the actual context window of an LLM, understand external vs internal context, and avoid the silent truncation problem.
- aidevtools
Token economy: cutting context waste
How loom-memory turns a Git repository into a persistent knowledge base for AI agents, cutting token spend with durable context instead of cold reads.