Ask HN: How hard would it be for a group to alter the opinions of an LLM?

I have been thinking about how realistic it is for an external actor to "hack" an LLM for real. Not a "jailbreak," but an actual modification of the weights.

ChatGPT seems to provide a vector via the public thumbs up/down feature.

I imagine that this will be an even larger problem for opensource ChatGPT-esque efforts.

Will this be the new playground for every intelligence agency, PR firm, and SEO consultant?

HN'ers very familiar with LLMs, how plausible is this type of manipulation?