korrents

Our readingWhat is a korrent?

The risk of AI behavior being unpredictable can be managed and trained out of models.

Drawn from what Steven Novella said

What Steven Novella actually said

  1. Steven Novella Academic clinical neurologist at Yale School of Medicine
    Further, it seems that this kind of behavior is a manifestation of the training data, and it can often be likewise trained out of the models. So yes, there is a potential risk here, but it appears to be a completely manageable risk.

Added to korrents 24 Oct 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

I hold this too

Related korrents

Not worked out yet — this claim is newer than the last pass. Every hour, each claim that is new or has changed is compared with every other one in the archive; the last pass () came before this claim was recorded. The next is due , and this claim will be in it.