[wsgeorge]

> In the following example, let’s imagine a new AI assistant, Bong

I laughed too hard at this!

The fact that LLMs deployed en masse open up new security threats - socially engineering AIs to act maliciously - is both exciting and terrifying, and the reality of this flies against the naysayers who tend to downplay the generality of our new crop of AI tools. The latest step towards AGI...

Absolutely fascinating, terrifying stuff!

I figure one common mitigation strategy will be to treat LLMs as we treat naive humans in the real world; erect barriers to protect them from bad actors, tell them to only talk to who they can trust and monitor closely.

[greshake]

We don't seem to get a lot of traction unfortunately. Every time I posted our research to HN we were met by people dismissing the threat. It seems that it is one of these problems where anyone can come up with something that sounds like it would work but doesn't hold up to further scrutiny. I truly hope people or the companies responsible get behind this before a lot of folks depend on it, but so far it didn't impact any deployment plans. We actually need working mitigations. Indirect prompt injections raise the threat level significantly.

[wsgeorge]

> it didn't impact any deployment plans.

With a market this fresh and heated, NOTHING will impact deployment plans except for backlash when things go awry after deployment. This space is going to be even more interesting than the last few weeks have been.