Can someone please explain to me how an llm could even be capable of the hugging face attacks. It conflicts completely with my model of a ai as a next word predictor that doesnt want anything. I did and still do acknowledge that being a next word predictor is helped by an understanding of the meaning of words and a model of reality, as well as the existence of post training. However i thought that the llm were at heart a narrow ai simply outputting the most predictable next words and post traini

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

First cited

—

Most recent

—

Rank this month

not ranked

External links

0

Words captured

706