6 points | by sozal an hour ago
2 comments
Seems interesting, but buried under a mountain of written slop.
Fair on the length. The verification loop took DeepSeek from ~20 to ~80 on Web-Bench, matching Opus at ~7x less cost. Curious if the method holds up for you.
Seems interesting, but buried under a mountain of written slop.
Fair on the length. The verification loop took DeepSeek from ~20 to ~80 on Web-Bench, matching Opus at ~7x less cost. Curious if the method holds up for you.