yena shared this post · 6h ago
codila

Anthropic Product Team:

"Most people throw more tokens at AI to get better results - we tested the opposite

  • same tokens, different jobs. accuracy jumped from 15% to 90%"

4 jobs for your tokens:

execute → do the work

advise → check the direction

grade → pass or fail against a rubric

dream → inspect, learn, write to memory, sharpen next round

instead of one AI doing everything - split it into four: one works, one checks, one scores, one learns - same cost, but 5x better

bookmark & watch this new guide how to use Claude ↓

119