I've been thinking about this for about a year. In my head I've called it "context bombs", though that may not be super accurate.

Think back to the movie The Manchurian Candidate. Produce highly capable LLM models then give them away for free. Train them with key phrases/codes etc to perform nefarious actions later when those codes are present in some piece of ingested context.

There were a couple of papers written on the topic in 2018 (I think, I'll need to find them again) and there's been surprisingly little more work done on the topic since. At least from what I've seen.

I really love the use of local models over subscription services but personally I would never recommend using open weights models from certain sources in a commercial environment.

▲

c0nsumer 2 hours ago | parent | next [-]

I just sort of presumed this was already being done. Because why wouldn't it be?

	▲	Aperocky 2 minutes ago \| parent [-]
		Well, if it is being done, per the other article on the front page, we should be able to find it.

▲

sowhat1 2 hours ago | parent | prev [-]

If you were a malicious actor do you really think this method is going to offer the greatest return on investment?

	▲	jack_h 2 hours ago \| parent \| next [-]
		Nation states aren’t looking for a return on investment rather they have a particular objective they want to achieve, e.g. stuxnet or the pager attack.
	▲	usernomdeguerre an hour ago \| parent \| prev \| next [-]
		I think this is a reasonable question. The moment this activates and exfiltrates or destroys a system the entire model family, training pipeline, and company are burned, no? How can you construct plausible deniability if your model will (presumably deterministically) activate on trigger?
	▲	geuis 2 hours ago \| parent \| prev [-]
		Sew a million seeds, see what grows.