Hacker News new | ask | show | jobs
by bandrami 147 days ago
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.
2 comments

Things are changing so fast that "few months" will invalidate most quality watermarks. It's good to re-evaluate frequently.
Are you only talking about open models?