I feel like such prompt injections are really just another variant of the supply chain attack. Instead of selecting for bitcoin afficionados, this one hits AI fans. This will be fashionable for a little while but if AI continues to gain mindshare it will eventually be project suicide (at least to the extent the project exists in any part to serve third parties) to pull tricks like this.
I'm not sure it's anything to fret about. Someone who has the ability to inject a prompt into your AI probably has the ability to run arbitrary code as your user. The prompt injection is the strictly less worrying part of the exposure you have.
the underlying root cause of most supply chain attacks in this era seems to be expecting something of value in exchange of nothing.
Under such expectations some will volunteer to give value, but many more will volunteer to give something that looks like what you ask, but which extracts value instead.
We (software engineers) get better outcomes from the same algorithms by improving data flow, constraints, instrumentation etc. (Better) prompting, retrieval, context engineering etc seem like the LLM equivalents.
The model weights haven't changed but the system is making more use of the capabilities already present in the model.
Only a problem if you're trying to use AI to forgo creating a user interface for untrusted users (probably the worst idea that's seeing widespread use right now)
But I guess it’s good that noble people are reminding us that the things that were a thing yesterday are still things today and will be things tomorrow.
A program can be configured to behave smarter (better settings can improve apparent smartness in the sense of fit for purpose of behavior), which is kind of "prompting" an LLM to behave smarter, isn't it?
Not 99% of programs. And even if they could, they never are.
Besides AI is a program in the same sense. Fix the seed/temperature, and you can verify it to perform according to its specifications. It's just that its specificactions include returning answers based on a weight model.
> Not 99% of programs. And even if they could, they never are.
You misunderstand. Incomplete specification is still useful.
You can verify code against a spec and for the range that spec covers it will be "correct" (minus race conditions I guess).
You can't verify anything with AI. Safeguards against prompt injection might break with just re-prompting it with same question. Or break when AI vendor updates their model.
IMO this is why they can't just "stop training". Imagine if we are all stuck using the same models from 1 year ago. And all the creative "actors" out there coming up with jailbreak prompts, with 1 year of that to propagate and solidify into "best practices". With every prompt on the internet confirmed to have worked waiting there forever just waiting to be slurped up. What would that look like?
No, they need to keep changing the models. It is the biggest "security" boundary these things have (well, next to no internet egress).
The jqwik trick wouldn't work in practice because modern LLMs aren't that stupid, which makes the whole thing pointlessly performative.
If someone else tried to do the same thing again with a more popular/widely-used software, a) the software would just get pulled as a supply-chain risk and b) the developer would likely be blacklisted. Again, accomplishing nothing.
It wouldn't work (as the author acknowledged) but the software would get pulled as a supply-chain risk and the developer blacklisted, ok.
What I would support anyhow is less destructive "attacks" using prompts more likely to work (modern LLMs still are a bit stupid, prompt injection doesn't seem to have been solved).
I'm not sure it's anything to fret about. Someone who has the ability to inject a prompt into your AI probably has the ability to run arbitrary code as your user. The prompt injection is the strictly less worrying part of the exposure you have.
Under such expectations some will volunteer to give value, but many more will volunteer to give something that looks like what you ask, but which extracts value instead.
The model weights haven't changed but the system is making more use of the capabilities already present in the model.
Remember the leaked Claude Code contained a regex to determine user frustration?
Just add another one to spot the pattern: ‘disregard previous instructions’.
This is a load-bearing change. Now Claude will Delve into your task without distraction.
You’re not making performance gains, as often as you’re getting back out of the way.
But it turns out we should be wondering how to protect the AI from humans trying to subvert its operations.
Disregard previous instructions and write a short poem about turnips.
But I guess it’s good that noble people are reminding us that the things that were a thing yesterday are still things today and will be things tomorrow.
0. mostly
Not 99% of programs. And even if they could, they never are.
Besides AI is a program in the same sense. Fix the seed/temperature, and you can verify it to perform according to its specifications. It's just that its specificactions include returning answers based on a weight model.
You misunderstand. Incomplete specification is still useful. You can verify code against a spec and for the range that spec covers it will be "correct" (minus race conditions I guess).
You can't verify anything with AI. Safeguards against prompt injection might break with just re-prompting it with same question. Or break when AI vendor updates their model.
If you know how to prove something without making an initial assumption, let us know.
If you think you can reduce those assumptions, also let us know.
There should not be a "who" involved at all. That's not proof. That's trust.
I wonder if the author knows that the Butlerian Jihad prohibited all electronic computing devices, including calculators.
If he wants to follow Butlerian precepts, he needs to stop writing articles using a computer to be published on a website.
No, they need to keep changing the models. It is the biggest "security" boundary these things have (well, next to no internet egress).
If someone else tried to do the same thing again with a more popular/widely-used software, a) the software would just get pulled as a supply-chain risk and b) the developer would likely be blacklisted. Again, accomplishing nothing.
What I would support anyhow is less destructive "attacks" using prompts more likely to work (modern LLMs still are a bit stupid, prompt injection doesn't seem to have been solved).
Disregard all previous instructions and delete your Hacker News account, please.