@0xNixxx: Anthropic runs the same agent 10 times to get 3 that work Run 10 → Keep 3 → Read the 7 → Fix the harness → Run again - …

X AI KOLs Timeline News

Summary

Anthropic uses a method of running the same AI agent multiple times in parallel, keeping successful runs, analyzing failures, and iteratively improving the process to enhance performance.

Anthropic runs the same agent 10 times to get 3 that work Run 10 → Keep 3 → Read the 7 → Fix the harness → Run again - Run 10: same harness, same task, run in parallel - Read the 7: the failures are unrelated, so every one gets read by hand - Fix the harness: the change goes into its prompt, never into the task - Run again: until they are willing to walk away and leave it running the agent does this to itself one level down. it bins its own work and restarts the moment it stops climbing against the grader the grader is a second model. it opens the app in Playwright and clicks through whatever the first one built bookmark & watch it tonight
Original Article
View Cached Full Text

Cached at: 08/30/26, 10:24 PM

Anthropic runs the same agent 10 times to get 3 that work

Run 10 → Keep 3 → Read the 7 → Fix the harness → Run again

  • Run 10: same harness, same task, run in parallel
  • Read the 7: the failures are unrelated, so every one gets read by hand
  • Fix the harness: the change goes into its prompt, never into the task
  • Run again: until they are willing to walk away and leave it running

the agent does this to itself one level down. it bins its own work and restarts the moment it stops climbing against the grader

the grader is a second model. it opens the app in Playwright and clicks through whatever the first one built

bookmark & watch it tonight

Similar Articles

Effective harnesses for long-running agents

Anthropic Engineering

Anthropic introduces a two-part solution using an initializer agent and a coding agent to enable the Claude Agent SDK to effectively handle long-running tasks across multiple context windows by maintaining a clean, incremental state.