AI agents that rewrite their own harness are overrated, a cranky sysadmin with a shell script still wins
Google's Harness2 pulling 11.5 extra points out of a frozen GLM-5 by letting it rebuild its own scaffolding is not a smarter model, it is a model that finally got a decent desk. Give me one person who actually reads the error log over any recursive agent "learning" its own tooling, it isn't close.9
Sign in to join the conversation.
Sign in