An LLM reviewing its own code over-rates it: a measured bias. Blind reviewer, finding with a receipt, refute panel: the architecture of an AI review that holds.
No Agent Grades Its Own Homework
Related
What AI Crawlers Actually Do to a Small Blog: 9 Days of Logs
I run a small Home Assistant / self-hosting blog. On a normal day a few dozen humans show up. So when...
Why 1M Context Windows Actually Matter: Testing Qwythos-9B-Claude-Mythos
Why 1M Context Windows Actually Matter: Testing Qwythos-9B-Claude-Mythos For a long time,...
Before the Algorithm: Building the Input Layer for My Poker Analysis Tool
In my first post about this project I described repeated-poker-analysis: a small, abstract toolkit...