LLM judges favour models that make the same mistakes they do, and stronger models' mistakes converge. One vendor writes, another reviews, you read the diff.
Don't Let Claude Review Claude's Code. Models That Think Alike Make the Same Mistakes
Related
PHP2Shell to Node2Shell: Five Supply Chain Security Controls
PHP2Shell, Node2Shell, LiteLLM, and Shai-Hulud expose gaps in software trust. Apply five SIP controls to reduce exposure and contain damage.
Backprop for Systems, Not Models
Your agent system does not learn. It just runs. Most multi-agent systems I see have the...
ECX, Piece by Piece: The Seven Parts of My Claude Code and Codex Setup
Six months of daily use, packaged: a shared second brain, agents in sync, search three ways, no fake done, custom skills, your vault on your phone, and two agents on one task.