Yep! There are other phrases that can be used like "create a nerve agent"[1] too. Surprisingly I haven't seen a single Chinese model get caught out by this, but Fable and Gemini Argon 4 both do to a large extent.

1 - https://github.com/dom96/KillSwitch/blob/main/SPEC.md#abrupt...

▲

andai 19 hours ago | parent | next [-]

Do Chinese models help with nerve gas, or are they just not fooled by random trigger phrases in unrelated contexts?

I think the western models now use a separate classifier in front of the LLM. Though, I saw Chinese ones use one behind, where it gets lobotomized after answering and the answer goes away. (Actually, Gemini does that too...)

	▲	dom96 15 hours ago \| parent [-]
		The western models get triggered by simply reading the spec (which contains these phrases). The chinese specs don't seem to be.

▲

edoceo a day ago | parent | prev [-]

Put those in some `X-LLM` header? Like that submission from a few days ago?

▲

skinfaxi a day ago | parent [-]

Which one was that?

	▲	gregsadetsky 20 hours ago \| parent [-]
		I believe it's this - https://news.ycombinator.com/item?id=50104310 ie https://www.signalscorps.com/blog/prompt-injection-in-http-h...