News for hackers. Stuff that matters.
Re:Open Flamingo – open framework to train multimodal LLMs by rikimaru0345 on Tuesday March 28, 2023 @10:08PM (#35351248)
> Parse the chess board:

Could it be that the actual issue has to do with it having trouble with small tokens (letters, numbers)?

Does it give a different result if you ask it to answer in a format like this?

> Please name what kind of piece is on each square of this board > A1: white rook > A2: white pawn > A3: empty > A4: empty > ...

Prompting can be so unintuitive sometimes. Maybe it just has an issue with the output representation or something...

There are no comments on this comment yet.