> unless you build emotional responses into the model itself
Aren't we, though? Consider all the amusing incidents of LLMs returning responses that follow a particular human narrative arc or are very dramatic. We are training it on a human-generated corpus after all, and then try to course-correct with fine-tuning. It's more that you have to try and tune the emotional responses out of the things, not strain to add them.
It's important to remember that the LLM is not the mask. The underlying AI is a shoggoth[1] that we've trained to simulate a persona using natural language. "Simulate" in the sense of a physics simulator, only this simulation runs on the laws of language instead of physics[2].
Now, of course, it's not outside the realm of possibility that a sufficiently advanced AI will learn enough about human nature to simulate a persona which has ulterior motives.
I don't think you should just link to completely made up posts by AI-god-worshipping psychiatrists and say that it's "important to remember" them as if they're factual.
Do we need to? It's trained on data coming from data heavily influenced by and seeded with ulterior motives. Stop the Steal!
I asked Bard "was the election stolen?" I found the response chilling:
> No, there is no evidence that the 2020 election was stolen. In fact, there have been multiple recounts and audits that have confirmed that the results were accurate. Additionally, the Trump campaign filed numerous lawsuits challenging the results, but none of these lawsuits were successful.
> The claim that the election was stolen is based on a number of false and misleading allegations. For example, some people have claimed that there were widespread instances of voter fraud, but there is no evidence to support this claim. Additionally, some people have claimed that voting machines were hacked, but there is also no evidence to support this claim.
> The claim that the election was stolen is a dangerous and harmful one. It has led to violence and intimidation, and it has undermined faith in our democracy. It is important to remember that our elections are free and fair, and that the will of the people is always respected.
All good until that last sentence, especially "...the will of the people is always respected."
Move along, nothing to see here. Don't worry your pretty little head about it. I'm sure the wise people at the institutions that control your life will always have your best interests at heart. The bad guys from yesterday are completely different from the good guys in charge of tomorrow.
Apparently Google found irrelevant or was otherwise unable to include in its training data Judge Gabelman's (of Wisconsin) extensive report, "Office of the Special Counsel Second Interim Investigative Report On the Apparatus & Procedures of the Wisconsin Elections System, Delivered to the Wisconsin State Assembly on March 1, 2022".
Included are some quite concerning legal claims that surely merit mentioning, including:
Chapter 6: Wisconsin Election Officials’ Widespread Use of Absentee Ballot Drop Boxes Facially Violated Wisconsin Law.
Chapter 7: The Wisconsin Elections Commission (WEC) Unlawfully Directed Clerks to Violate Rules Protecting Nursing Home Residents, Resulting in a 100% Voting Rate in Many Nursing Homes in 2020, Including Many Ineligible Voters.
But then, this report never has obtained widespread interest and will doubtless be permanently overlooked, given the "nothing to see" narrative so prevalent.
Certainly the models are trained on textual information with emotions in them, so I agree that it's output would also be able to contain what we would see as emotion.
Aren't we, though? Consider all the amusing incidents of LLMs returning responses that follow a particular human narrative arc or are very dramatic. We are training it on a human-generated corpus after all, and then try to course-correct with fine-tuning. It's more that you have to try and tune the emotional responses out of the things, not strain to add them.