Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on What We Learned from a Year of Building with LLMs. Parent comment
I like to think of LLMs as client-side code, at least in terms of their risk-profile.
No data you put into them (whether training or prompt) is reliably hidden from a persistent user, and they can also force it to output what they want.
There are no comments on this comment yet.
I like to think of LLMs as client-side code, at least in terms of their risk-profile.
No data you put into them (whether training or prompt) is reliably hidden from a persistent user, and they can also force it to output what they want.