2026-09-12 10:40 UTC
@tao@mathstodon.xyz Thank you all!
Anyway I think it would be interesting to perform the following experiment to rule out if training on recent unpublished work is being performed:
Start pointing out to fake unpublished local work on millennium problems that contains poisoned stuff and fake evidence.
If they greedy train on this this could be a huge punch to the training of the new model. If they don't nothing happens.
Replies (0)
No replies.