logoalt Hacker News

thenewwazooyesterday at 5:40 PM4 repliesview on HN

Every time I see something about trying to control an LLM by sending instructions to the LLM, I wonder: have we really learned nothing of the pitfalls of in-band signaling since the days of phreaking?


Replies

quadratureyesterday at 5:46 PM

Sure but the exploit here isn’t prompt injection, it is an edge case in their billing that isn’t attributing agent calls correctly.

show 1 reply
cpayesterday at 5:50 PM

It reminds me of when I used to write lisp, where code is data. You can abuse reflection (and macros) to great effect, but you never feel safe.

See also: string interpolation and SQL injection, (unhygienic) C macros

direwolf20yesterday at 6:56 PM

Allowing phreaking was an intentional decision, because otherwise they could have carried half as many channels on each link.

Mountain_Skiesyesterday at 5:44 PM

It'll be a sad day for Little Bobby Tables if in-band signaling ever goes out of fashion.