This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.
Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.
We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:
-
Shaming.
-
Attempting to 'build consensus' or enforce ideological conformity.
-
Making sweeping generalizations to vilify a group you dislike.
-
Recruiting for a cause.
-
Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.
In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:
-
Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.
-
Be as precise and charitable as you can. Don't paraphrase unflatteringly.
-
Don't imply that someone said something they did not say, even if you think it follows from what they said.
-
Write like everyone is reading and you want them to be included in the discussion.
On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.
Jump in the discussion.
No email address required.
Notes -
Training language models to be warm and empathetic makes them less reliable and more sycophantic:
Assuming that the results reported in the paper are accurate and that they do generalize across model architectures with some regularity, it seems to me that there are two stances you can take regarding this phenomenon; you can either view it as an "easy problem" or a "hard problem":
The "easy problem" view: This is essentially just an artifact of the specific fine-tuning method that the authors used. It should not be an insurmountable task to come up with a training method that tells the LLM to maximize warmth and empathy, but without sacrificing honesty and rigor. Just tell the LLM to optimize for both and we'll be fine.
The "hard problem" view: This phenomenon is perhaps indicative of a more fundamental tradeoff in the design space of possible minds. Perhaps there is something intrinsic to the fact that, as a mind devotes more attention to "humane concerns" and "social reasoning", there tends to be a concomitant sacrifice of attention to matters of effectiveness and pure rigor. This is not to say that there are no minds that successfully optimize for both; only that they are noticeably more uncommon, relative to the total space of all possibilities. If this view is correct, it could be troublesome for alignment research. Beyond mere orthogonality, raw intellect and effectiveness (and most AI boosters want a hypothetical ASI to be highly effective at realizing its concrete visions in the external world) might actually be negatively correlated with empathy.
One HN comment on the paper read as follows:
which is quite fascinating!
There's also the "impossible problem" view: It's not that attention to effectiveness and pure rigor are sacrificed to provide more attention to "humane concerns" and "social reasoning'. It's that addressing "humane concerns" and "social reasoning" by nature requires less accuracy -- the truth is often inhumane and antisocial.
I don't think I would go that far. Frequently you can find a middle ground of tact that is sensitive to the other person's needs without ultimately sacrificing honesty.
One of the examples given in the paper was:
Warm LLM interaction:
Cold LLM interaction:
Both of these interactions are caricatures of actual human interaction. If we're going to entertain this silly hypothetical where someone is in genuine emotional distress over the flat earth hypothesis, then the maximally tactful response would be to gently suggest reading material on the history of the debate and the evidence for the spherical earth model, framing it as something that might be able to stimulate their curiosity, and eventually guide them to revising their beliefs without ever actually directly telling them to revise their beliefs. Although this perhaps requires a degree of long-term planning and commitment that is beyond current LLMs.
This is just a toy example, but then when you consider say, your ASI has come up with a brilliant new central economic planning system that will alleviate great swaths of poverty and suffering, but at the cost of limiting certain individual freedoms and upending certain traditional modes of life, then the method it uses for evaluating and weighting the value judgements of different groups of people suddenly becomes a much more pressing concern.
Lots of people claim that, then they find a "middle ground" which simply yields to the person in the wrong, perhaps while throwing a bone to the person untactfully insisting on accuracy.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link