How about reducing the number of catered meals while increasing support for meals outside the venue? Silly example: someone could fill a hotel room with Soylent so that everyone can grab liquid meals and go chat somewhere--sort of a "baguettes and hummus" vibe. Or as @Matt_Sharp pointed out, we could reserve nearby restaurants. No idea if these exact plans are feasible, but I can imagine similarly scrappy solutions going well if planned by actual logistics experts.
Thanks so much for your work and this information!
I'm having an ongoing discussion with a couple professors and a PhD candidate in AI about "The Alignment Problem from a Deep Learning Perspective" by @richard_ngo, @Lawrence Chan, and @SoerenMind. They are skeptical of "3.2 Planning Towards Internally-Represented Goals," "3.3 Learning Misaligned Goals," and "4.2 Goals Which Motivate Power-Seeking Would Be Reinforced During Training". Here's my understanding of some of their questions:
The argument for power-seeking during deployment depends on the model being able to detect the change from the training to deployment distribution. Wouldn't this require keeping track of the distribution thus far, which would require memory of some sort, which is very difficult to implement in the SSL+RLHF paradigm?
What is the status of the model after the SSL stage of training?Â
How robust could its goals be?
Would a model be able to know:
what misbehavior during RLHF fine-tuning would look like?
that it would be able to better achieve its goals by avoiding misbehavior during fine-tuning?
Why would a model want to preserve its weights? (Sure, instrumental convergence and all, but what's the exact mechanism here?)
To what extent would all these phenomena (situationally-aware reward hacking, misaligned internally-represented goals, and power-seeking behaviors) show up in current LLMs (say, GPT-4) vs. current agentic LLM-based systems (say, AutoGPT) vs. different future systems?
Do we get any evidence for these arguments from the fact that existing LLMs can adopt goal-directed personas?
General information about people in low-HDI countries to humanize them in the eyes of the viewer.
Similar for animals (except not “humanizing” per se!). Spreading awareness that e.g. pigs act like dogs may be a strong catalyst for caring about animal welfare. Would need to consult an animal welfare activism expert.
My premise here: it is valuable for EAs to viscerally care about others (in addition to cleverly working toward a future that sounds neat).
Adding more not to defend myself, but to keep the conversation going:
I think that many Enlightenment ideas are great and valid regardless of their creators' typical-for-their-time ideas.Â
Education increasingly includes rather radical components of critical race theory. Students are taught that if someone is racist, then all of their political and philosophical views are tainted. By extension, many people learn that the Enlightenment itself is tainted. Like Charles, I think that this "produces misguided perspectives".
I'm--apparently badly--trying to communicate the following. These students, who have been taught that the Enlightenment is tainted by association with racism, who (reasonably!) haven't bothered to thoroughly research this particular historical movement to come to their own conclusions, who may totally make great EAs, would initially be turned off.
It's quite plausible that it shouldn't be the case that Enlightenment aesthetics might turn people off. But I think this is the case, and I argue that it's likely more important to make a good first impression than to take a stand in favor of a particular historical movement.
Short version: if we can avoid it, let’s not filter potential EAs by the warmth of their feelings toward a specific group of historical figures (especially because history education is inevitably biased)
I actually wouldn’t know where to find a liberal student who respects classics (let alone “our cultural heritage”) at my large American university, after four years in the philosophy department!
Yes, these are great reasons to take inspiration from the Enlightenment!
The point I most want to get across is that, by using Enlightenment aesthetics, EAs could needlessly open themselves up to negative perception.
If EAs use Enlightenment aesthetics more, then EA will be associated with the Enlightenment more.
Regardless of their positive qualities, Enlightenment philosophers racked up plenty of negative qualities among them. Maybe there were 10x as many purely virtuous ones as problematic ones; maybe every problematic one made contributions that vastly outweighed their issues; nonetheless, there are some problems.
People who would otherwise engage with EA might have heard of enough problems that they’d be put off by Enlightenment associations entirely. (I suspect many of my social-justice-y friends would have this reaction.)
Here’s the more nebulous point. I hinted in my original comment that I take issue with the “rational individualistic actor” view. This alone puts me off Enlightenment aesthetics, because I think that particular view is especially dangerous considering how innocent it looks. But that’s a whole big discussion, and I respect the other side! The relevant part here is just that, anecdotally, at least one EA isn’t a huge Enlightenment fan.
Yeah, the magnitude of the problem depends on the empirical question of how many people associate the Enlightenment with racism and such.
Descartes’ moral circle issue is that he believed animals have no moral standing whatsoever, so he enthusiastically practiced vivisection (dissecting animals while they were still alive).
How about reducing the number of catered meals while increasing support for meals outside the venue? Silly example: someone could fill a hotel room with Soylent so that everyone can grab liquid meals and go chat somewhere--sort of a "baguettes and hummus" vibe. Or as @Matt_Sharp pointed out, we could reserve nearby restaurants. No idea if these exact plans are feasible, but I can imagine similarly scrappy solutions going well if planned by actual logistics experts.
Thanks so much for your work and this information!
I'm having an ongoing discussion with a couple professors and a PhD candidate in AI about "The Alignment Problem from a Deep Learning Perspective" by @richard_ngo, @Lawrence Chan, and @SoerenMind. They are skeptical of "3.2 Planning Towards Internally-Represented Goals," "3.3 Learning Misaligned Goals," and "4.2 Goals Which Motivate Power-Seeking Would Be Reinforced During Training". Here's my understanding of some of their questions:
Yep, The Sexual Politics of Meat by Carol J. Adams is the classic I'm aware of.
General information about people in low-HDI countries to humanize them in the eyes of the viewer.
Similar for animals (except not “humanizing” per se!). Spreading awareness that e.g. pigs act like dogs may be a strong catalyst for caring about animal welfare. Would need to consult an animal welfare activism expert.
My premise here: it is valuable for EAs to viscerally care about others (in addition to cleverly working toward a future that sounds neat).
Thanks very much, that helps!
Adding more not to defend myself, but to keep the conversation going:
I think that many Enlightenment ideas are great and valid regardless of their creators' typical-for-their-time ideas.Â
Education increasingly includes rather radical components of critical race theory. Students are taught that if someone is racist, then all of their political and philosophical views are tainted. By extension, many people learn that the Enlightenment itself is tainted. Like Charles, I think that this "produces misguided perspectives".
I'm--apparently badly--trying to communicate the following. These students, who have been taught that the Enlightenment is tainted by association with racism, who (reasonably!) haven't bothered to thoroughly research this particular historical movement to come to their own conclusions, who may totally make great EAs, would initially be turned off.
It's quite plausible that it shouldn't be the case that Enlightenment aesthetics might turn people off. But I think this is the case, and I argue that it's likely more important to make a good first impression than to take a stand in favor of a particular historical movement.
Hope that makes sense!
Short version: if we can avoid it, let’s not filter potential EAs by the warmth of their feelings toward a specific group of historical figures (especially because history education is inevitably biased)
I actually wouldn’t know where to find a liberal student who respects classics (let alone “our cultural heritage”) at my large American university, after four years in the philosophy department!
Yes, these are great reasons to take inspiration from the Enlightenment!
The point I most want to get across is that, by using Enlightenment aesthetics, EAs could needlessly open themselves up to negative perception.
Here’s the more nebulous point. I hinted in my original comment that I take issue with the “rational individualistic actor” view. This alone puts me off Enlightenment aesthetics, because I think that particular view is especially dangerous considering how innocent it looks. But that’s a whole big discussion, and I respect the other side! The relevant part here is just that, anecdotally, at least one EA isn’t a huge Enlightenment fan.
Yeah, the magnitude of the problem depends on the empirical question of how many people associate the Enlightenment with racism and such.
Descartes’ moral circle issue is that he believed animals have no moral standing whatsoever, so he enthusiastically practiced vivisection (dissecting animals while they were still alive).