Hacker News new | ask | show | jobs
by vnglst 486 days ago
Oh no, thanks for pointing this out! I asked GTP-4o to convert the image to text for me and I only checked some of the cards, assuming the rest would be correct. That was a mistake.

I've now corrected the experiment to accurately take the image into account. This meant that Deepseek was no longer able to find all the sets, but o3-mini still did a good job.