Reposted by kat
Scaling up and shaping up large language models increased their tendency to provide sensible yet incorrect answers at difficulty levels humans cannot supervise, highlighting the need for a shift in AI design towards reliability, according to a paper in Nature. go.nature.com/4eCAnis 🧪
![a "brain-to-brain communication" meme, edited to replace certain words: I'm a [reverse engineer]. Sometimes I can tell how [software works] simply by deciding how I think [it works] in my own mind and instantly believing it.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:vwzwgnygau7ed7b7wt5ux7y2/bafkreibuohb3jis52c4dhi2juaofqyu2tpb57w4anvol4ilwobfxul3v5e)
