Comment by ChadNauseam

17 days ago

First try with claude: https://claude.ai/share/fabaf585-3732-4264-9ff3-03e4182c82a4

Very cool. Claude failed hard on this a few months ago. Gemma and phi have gotten better at it in recent versions, too, though qwen is still confidently getting it wrong.

  • Things are changing so fast that "few months" will invalidate most quality watermarks. It's good to re-evaluate frequently.