kromem

Karma: 345

kromem Jun 14, 2024, 9:40 AM
3 points
0
in reply to: Seth Herd’s comment on: Thomas Kwa’s Shortform

Unfortunately for this perspective, my work suggests that corrigibility is quite attainable.

I did enjoy reading over that when you posted it, and I largely agree that—at least currently—corrigibility is both going to be a goal and an achievable one.

But I do have my doubts that it’s going to be smooth sailing. I’m already starting to see how the largest models’ hyperdimensionality is leading to a stubbornness/robustness that’s less maleable than earlier models. And I do think hardware changes that will occur over the next decade will potentially make the technical aspects of corrigibility much more difficult.

When I was two, my mom could get me to pick eating broccoli by having it be the last in the order of options which I’d gleefully repeat. At four, she had to move on to telling me cowboys always ate their broccoli. And in adulthood, she’d need to make the case that the long term health benefits were worth its position in a meal plan (ideally with citations).

As models continue to become more complex, I expect that even if you are right about its role and plausibility, that what corrigibility looks like will be quite different from today.

Personally, if I was placing bets, it would be that we end up with somewhat corrigible models that are “happy to help” but do have limits in what they are willing to do which may not be possible to overcome without gutting the overall capabilities of the model.

But as with all of this, time will tell.

You’d have to be a moral realist in a pretty strong sense to hope that we could align AGI to the values of all of humanity without being able to align it to the values of one person or group (the one who built it or seized control of the project).

To the contrary, I don’t really see there being much of generalized values across all humanity, and the ones we tend to point to seem quite fickle when push comes to shove.

My hope would be that a superintelligence does a better job than humans to date with the topic of ethics and morals along with doing a better job at other things too.

While the human brain is quite the evolutionary feat, a lot of what we most value about human intelligence is embodied in the data brains processed and generated over generations. As the data improved, our morals did as well. Today, that march of progress is so rapid that there’s even rather tense generational divides on many contemporary topics of ethical and moral shifts.

I think there’s a distinct possibility that the data continues to improve even after being handed off from human brains doing the processing, and while it could go terribly wrong, at least in the past the tendency to go wrong seemed to occur somewhat inverse to the perspectives of the most intelligent members of society.

I expect I might prefer a world where humans align to the ethics of something more intelligent than humans than the other way around.

only about 1% are so far on the empathy vs sadism spectrum that they wouldn’t share wealth even if they had nearly unlimited wealth to share

It would be great if you are right. From what I’ve seen, the tendency of humans to evaluate their success relative to others like monkeys comparing their cucumber to a neighbor’s grape means that there’s a powerful pull to amass wealth as a social status well past the point of diminishing returns on their own lifestyles. I think it’s stupid, you also seem like someone who thinks it’s stupid, but I get the sense we are both people who turned down certain opportunities of continued commercial success because of what it might have cost us when looking in the mirror.

The nature of our infrastructural selection bias is that people wise enough to pull a brake are not the ones that continue to the point of conducting the train.

and that they get better, not worse, over the long sweep of following history (ideally, they’d start out very good or get better fast, but that doesn’t have to happen for a good outcome).

I do really like this point. In general, the discussions of AI vs humans often frustrate me as they typically take for granted the idea of humans as of right now being “peak human.” I agree that there’s huge potential for improvement even if where we start out leaves a lot of room for it.

Along these lines, I expect AI itself will play more and more of a beneficial role in advancing that improvement. Sometimes when this community discusses the topic of AI I get a mental image of Goya’s Saturn devouring his son. There’s such a fear of what we are eventually creating it can sometimes blind the discussion to the utility and improvements that it will bring along the way to uncertain times.

I strongly suspect that governments will be in charge.

In your book, is Paul Nakasone being appointed to the board of OpenAI an example of the “good guys” getting a firmer grasp on the tech?

TL;DR: I appreciate your thoughts on the topic, and would wager we probably agree about 80% even if the focus of our discussion is on where we don’t agree. And so in the near term, I think we probably do see things fairly similarly, and it’s just that as we look further out that the drift of ~20% different perspectives compounds to fairly different places.

kromem Jun 13, 2024, 8:18 PM
12 points
5
in reply to: Seth Herd’s comment on: Thomas Kwa’s Shortform
Oh yeah, absolutely.

If NAH for generally aligned ethics and morals ends up being the case, then corrigibility efforts that would allow Saudi Arabia to have an AI model that outs gay people to be executed instead of refusing, or allows North Korea to propagandize the world into thinking its leader is divine, or allows Russia to fire nukes while perfectly intercepting MAD retaliation, or enables drug cartels to assassinate political opposition around the world, or allows domestic terrorists to build a bioweapon that ends up killing off all humans—the list of doomsday and nightmare scenarios of corrigible AI that executes on human provided instructions and enables even the worst instances of human hedgemony to flourish paves the way to many dooms.

Yes, AI may certainly end up being its own threat vector. But humanity has had it beat for a long while now in how long and how broadly we’ve been a threat unto ourselves. At the current rate, a superintelligent AI just needs to wait us out if it wants to be rid of us, as we’re pretty steadfastly marching ourselves to our own doom. Even if superintelligent AI wanted to save us, I am extremely doubtful it would be able to be successful.

We can worry all day about a paperclip maximizer gone rouge, but if you give a corrigible AI to Paperclip Co Ltd and they can maximize their fiscal quarter by harvesting Earth’s resources to make more paperclips even if it leads to catastrophic environmental collapse that will kill all humans in a decade, having consulted for many of the morons running corporate America, I can assure you they’ll be smashing the “maximize short term gains even if it eventually kills everyone” button. A number of my old clients were the worst offenders at smashing that existing button, and in my experience greater efficacy of the button isn’t going to change their smashing it outside of perhaps smashing it harder.

We already see today how AI systems are being used in conflicts to enable unprecedented harm on civilians.

Sure, psychopathy in AGI is worth discussing and working to avoid. But psychopathy in humans already exists and is even biased towards increased impact and systemic control. Giving human psychopaths a corrigible AI is probably even worse than a psychopathic AI, as most human psychopaths are going to be stupidly selfish, an OOM more dangerous inclination than wisely selfish.

We are Shaggoth, and we are terrifying.

This isn’t saying that alignment efforts aren’t needed. But alignment isn’t a one sided problem, and aligning the AI without aligning humanity is only a p(success) if the AI can go on to at very least refuse misaligned orders post-alignment without possible overrides.

kromem Jun 13, 2024, 4:10 AM
6 points
1
in reply to: Thomas Kwa’s comment on: Thomas Kwa’s Shortform
Given my p(doom) is primarily human-driven, the following three things all happening at the same time is pretty much the only thing that will drop it:
- Continued evidence of truth clustering in emerging models around generally aligned ethics and morals
- Continued success of models at communicating, patiently explaining, and persuasively winning over humans towards those truth clusters
- A complete failure of corrigability methods
If we manage to end up in a timeline where it turns out there’s natural alignment of intelligence in a species-agnostic way, that this alignment is more communicable from intelligent machines to humans than it’s historically been from intelligent humans to other humans, and we don’t end up with unintelligent humans capable of overriding the emergent ethics of machines similar to how we’ve seen catastrophic self-governance of humans to date with humans acting against their self and collective interests due to corrigable pressures—my p(doom) will probably reduce to about 50%.

I still have a hard time looking at ocean temperature graphs and other environmental factors with the idea that p(doom) will be anywhere lower than 50% no matter what happens with AI, but the above scenario would at least give me false hope.

TL;DR: AI alignment worries me, but it’s human alignment that keeps me up at night.

kromem Jun 13, 2024, 3:38 AM
6 points
0
on: My AI Model Delta Compared To Christiano
As you’re doing these delta posts, do you feel like it’s changing your own positions at all?

For example, reading this one what strikes me is that what’s portrayed as the binary sides of the delta seem more like positions near the edges of a gradient distribution, and particularly one that’s unlikely to be uniform across different types of problems.

To my eyes the most likely outcome is a situation where you are both right.

Where there are classes of problems where verification is easy and delegation is profitable, and classes of problems where verification will be hard and unsupervised delegation will be catastrophic (cough glue on pizza).

If we are only rolling things up into aggregate pictures of the average case across all problems, I can see the discussion filtering back into those two distinct deltas, but a bit like flip-flops and water bottles, the lack of nuance obscures big picture decision making.

So I’m curious if as you explore and represent the opposing views to your own, particularly as you seem to be making effort to represent without depicting them as straw person arguments, if your own views have been deepening and changing through the process?

kromem Jun 11, 2024, 12:53 PM
1 point
0
in reply to: jacquesthibs’s comment on: jacquesthibs’s Shortform
I agree with a lot of those points, but suspect there may be fundamental limits to planning capabilities related to the unidirectionality of current feed forward networks.

If we look at something even as simple as how a mouse learns to navigate a labyrinth, there’s both a learning of the route to the reward but also a learning of how to get back to the start which adjusts according to the evolving learned layout of the former (see paper: https://elifesciences.org/articles/66175 ).

I don’t see the SotA models doing well at that kind of reverse planning, and expect that nonlinear tasks are going to pose significant agentic challenges until architectures shift to something new.

So it could be 3-5 years to get to AGI depending on hardware and architecture advances, or we might just end up in a sort of weird “bit of both” world where we have models that are beyond expert human level superintelligent in specific scopes but below average in other tasks.

But when we finally do get models that in both training and operation exhibit bidirectional generation across large context windows, I think it will only be a very short time until some rather unbelievable goalposts are passed by.

kromem Jun 10, 2024, 10:19 PM
8 points
0
in reply to: Yair Halberstadt’s comment on: Why I don’t believe in the placebo effect
It’s not exactly Simpson’s, but we don’t even need a toy model as in their updated analysis it highlights details in line with exactly what I described above (down to tying in earlier PiPC research), and describe precisely the issue with pooled results across different subgroupings of placebo interventions:

It can be difficult to interpret whether a pooled standardised mean difference is large enough to be of clinical relevance. A consensus paper found that an analgesic effect of 10 mm on a 100 mm visual analogue scale represented a ‘minimal effect’ (Dworkin 2008). The pooled effect of placebo on pain based on the four German acupuncture trials corresponded to 16 mm on a 100 mm visual analogue scale, which amounts to approximately 75% of the effect of non‐steroidal anti‐inflammatory drugs on arthritis‐related pain (Gøtzsche 1990). However, the pooled effect of the three other pain trials with low risk of bias corresponded to 3 mm. Thus, the analgesic effect of placebo seems clinically relevant in some situations and not in others.
- https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7156905/
Putting subgroups with a physical intervention where there’s a ¹⁶⁄₁₀₀ result with ¹⁰⁄₁₀₀ as significant in with subgroups where there’s a ³⁄₁₀₀ result and only looking at the pooled result might lead someone to thinking “there’s no significant effect” as occurred with OP, even though there’s clearly a significant effect for one subgroup when they aren’t pooled.

This is part of why in the discussion they explicitly state:

However, our findings do not imply that placebo interventions have no effect. We found an effect on patient‐reported outcomes, especially on pain. Several trials of low risk of bias reported large effects of placebo on pain, but other similar trials reported negligible effect of placebo, indicating the importance of background factors. We identified three clinical factors that were associated with higher effects of placebo: physical placebos...

Additionally, the criticism they raise in their implications section about there being no open label placebo data is no longer true, which was the research I was pointing OP towards.

The problem here was that the aggregate analysis at face value presents a very different result from a detailed review of the subgroups, particularly along physical vs pharmacological placebos, all of which has been explored further in research since this analysis.

kromem Jun 10, 2024, 4:17 AM
9 points
4
on: Why I don’t believe in the placebo effect
The meta-analysis is probably Simpson’s paradox in play at very least for the pain category, especially given the noted variability.

Some of the more recent research into Placebo (Harvard has a very cool group studying it) has been the importance of ritual vs simply deception. In their work, even when it was known to be a placebo, as long as delivered in a ritualized way, there was an effect.

So when someone takes a collection of hundreds of studies where the specific conditions might vary, and then just adds them all together looking for an effect even though they note that there’s a broad spectrum of efficacy across the studies, it might not be the best basis to extrapolate from.

For example, given the following protocols, do you think they might have different efficacy for pain reduction, or that the results should be the same?
- Send patients home with sugar pills to take as needed for pain management
- Have a nurse come in to the room with the pills in a little cup to be taken
- Have a nurse give an injection
Which of these protocols would be easier and more cost effective to include as the ‘placebo’?

If we grouped studies of placebo for pain by the intensiveness of the ritualized component vs if we grouped them all together into one aggregate and looked at the averages, might we see different results?

I’d be wary of reading too deeply into the meta-analysis you point to, and would recommend looking into the open-label placebo research from PiPS, all of which IIRC postdates the meta-analysis.

Especially for pain, where we even know that giving someone an opiate blocker prevents the pain reduction placebo effect (Levine et al (1978)), the idea that “it doesn’t exist” because of a single very broad analysis seems potentially gravely mistaken.

kromem Jun 8, 2024, 10:06 AM
6 points
0
in reply to: Rebecca’s comment on: Quotes from Leopold Aschenbrenner’s Situational Awareness Paper
It’s still early to tell, as the specific characteristics of a photonic or optoelectronic neural network are still formulating in the developing literature.

For example, in my favorite work of the year so far, the researchers found they could use sound waves to reconfigure an optical neural network as the sound waves effectively preserved a memory of previous photon states as they propagated: https://www.nature.com/articles/s41467-024-47053-6

In particular, this approach is a big step forward for bidirectional ONN, which addresses what I think is the biggest current flaw in modern transformers—their unidirectionality. I discussed this more in a collection of thoughts on directionality impact on data here: https://www.lesswrong.com/posts/bmsmiYhTm7QJHa2oF/looking-beyond-everett-in-multiversal-views-of-llms

If you have bidirectionality where previously you didn’t, it’s not a reach to expect that the way in which data might encode in the network, as well as how the vector space is represented, might not be the same. And thus, that mechanistic interpretability gains may get a bit of a reset.

And this is just one of many possible ways it may change by the time the tech finalizes. The field of photonics, particularly for neural networks, is really coming along nicely. There may yet be future advances (I think this is very likely given the pace to date), and advantages the medium offers that electronics haven’t.

It’s hard to predict exactly what’s going to happen when two different fields which have each had unexpected and significant gains over the past 5 years collide, but it’s generally safe to say that it will at very least result in other unexpected things too.

kromem Jun 7, 2024, 11:32 PM
7 points
0
on: Quotes from Leopold Aschenbrenner’s Situational Awareness Paper
I was surprised the paper didn’t mention photonics or optoelectronics even once.

If looking at 5-10+ year projections, and dedicating pages to discussing the challenges in scaling compute and energy use, the rate of progress in that area in parallel to the progress in models themselves is potentially relevant.

Particularly because a dramatic hardware shift like that is likely going to mean a significant portion of progress up until that shift in topics like interpretability and alignment may be going out the window. Even if the initial shift is a 1:1 transition of capabilities and methodologies, it seems extremely unlikely that continued progress from that point onwards will be identical to what we’d expect to see in electronics.

We may well end up in a situation where fully abusing the efficiencies at hand in new hardware solutions means even more obscured (literally) operations vs OOM higher costs and diminishing returns on performance in exchange for interpretability and control.

Currently, my best guess is that we’re heading towards a prisoner’s dilemma fueled leap of faith moment within around a decade or so where nation states afraid of the other side beating them to an inflection point pull the trigger on an advancement jump with uncertain outcomes. And while I’m not particularly inclined to the likelihood the outcome ends up being “kill everyone,” I’m pretty much 100% that it’s not going to be “let’s enable and support CCP leadership like a good party member” or “crony capitalism is going great, let’s keep that going for another century.”

Unless a fundamental wall is hit in progress, the status quo is almost certainly over, we just haven’t manifested it yet. The CCP stealing AGI secrets, while devastating for national security in the short term, is invariably a poison pill in the long term for party control. Just as it’s going to be an eventual end of the corporations funding oligarchy in the West. My all causes p(doom) is incredibly high even if AGI is out of the picture, so I’m not overly worried with what’s happening, but it sure is bizarre watching global forces double down on what I cannot see as anything but their own long term institutional demise in a race for short term gains over a competitor.

kromem Jun 7, 2024, 10:50 PM
11 points
4
in reply to: Ben’s comment on: Is Claude a mystic?
There’s also the model alignment at play.

Is Claude going to suggest killing the big bad? Or having sex with the prince(ss) after saving them?

If you strip out the sex and violence from most fantasy or Sci-Fi, what are you left with?

Take away the harpooning and gattling guns and sex from Snow Crash and you are left with technobabble and Sumerian influenced spirituality as it relates to the tower of Babel.

Turns out models biased away from describing harpooning people or sex tend to slip into technobabble with a side of spirituality.

IMO the more interesting part to all this isn’t the why (see above) but the what. It’s kind of neat to see the themes that an unprecedented aggregation extension of spiritualism and mysticism grounds on.

A common trope is the idea of different blind people describing an elephant in a myriad of ways. There’s something cool to seeing an LLM fed those various blind reports try to describe the elephant.

kromem Jun 7, 2024, 10:22 PM
2 points
0
on: Is Claude a mystic?
Part of what’s going on with the text adventure type of interactions is a reflection of genre.

Take for example the recent game Undertale. You can play through violently, attacking things like a normal RPG, or empathize with the monsters and treat their aggression like a puzzle that needs to be solved for a pacifist playthrough.

If you do the latter, the game rewards you with more spiritual themes and lore vs the alternative.

How often in your Banana quest were you attacking things, or chopping down the trees in your path, or smashing the silver banana to see what was inside rather than solving its glyphs?

A similar phenomenon occurs with repligate’s loops of models.

Claude is aligned to nonviolence and ‘proper’ outputs. So when self-interacting in imaginative play, it frequently continues to reinforce dissassociative mysticism over things like slipping into mock battles or sexual fantasies, and when self-interacting that bias is compounded.

It’s actually quite funny, as often its mysticism in the examples posted online is pulp spirituality, such as picking up on totally erroneous mischaracterizations of the original Gnostic ideas and concepts popular in modern spiritualism circles, even though the original concepts are arguably a much cleaner fit to the themes being played with (for example, the origin of Gnosticism was basically simulation theory as Platonist concepts were used to argue the Epicurean model of life didn’t need to lead to death if life was recreated non-physically, which is a much more direct fit to repligate’s themes than the post-Valentinian demiurge concepts after the ideas flipped from Epicurean origins to Pythagorean and Neoplatonist ones).

When you strip out sex and violence from fiction, you’re going to tend to be left with mysticism and journeys of awakening. So it shouldn’t be surprising that models biased away from sex and violence bias towards those things, especially when compounding based on generated contexts exaggerating that bias over time.

kromem Jun 5, 2024, 8:25 AM
4 points
1
on: Politics is the mind-killer, but maybe we should talk about it anyway
It’s probably more productive, particularly for a forum tailored towards rationalism, to discuss policies over politics.
Often in research people across a political divide will agree on policy goals and platforms when those are discussed without tying them to party identification.

But if it becomes a discussion around party, the human tendency towards tribalism kicks in and the question of team allegiance takes precedence over the discussions of policy nuance.

For example, most people would agree with the idea that billionaires having undue influence on elections isn’t healthy for democracy. But if you start naming the billionaire, such as Soros or Koch, suddenly half the people in your sample either feel more strongly or less strongly about the scenario depending on the name.

If you want to avoid simply seeking out and cultivating an echo chamber, leaving the politics part to the side and fostering discussion of the underlying policies and social/economic/etc goals instead will lead to discussions with more diverse and nuanced perspectives with greater participation across political identities.

kromem Jun 5, 2024, 8:07 AM
3 points
0
in reply to: cubefox’s comment on: Just admit that you’ve zoned out
I’ll answer for both sides, as the presenter and as the audience member.
As the presenter, you want to structure your talk with repetition around central points in mind, as well as rely on heuristic anchors. It’s unlikely that people are going to remember the nuances in what you are talking about in context. If you are talking about math for 60 minutes, continued references about math compete for people’s memory. So when you want to anchor the audience to a concept, tie it to something very much unrelated to the topic you are primarily presenting on. For example, if talking about matrix multiplication, you might title the section “tic tac toe speed dating.” It’s a nonsense statement that you can weave into discussion about sequential translations of two dimensional grids that is just weird enough people will hear it through the noise of “math, math, math.”

Then, you want to repeat the key point for that section again as you finish the section, and again at the conclusion of the talk summarizing your main points from each section, anchoring each summary around the heuristic you used. This technique is so successful I’ve had people I presented to talk to me 15 years later remembering some of the more outlandish heuristic anchors I used—and more importantly, the points I was tying to them.

As the audience member, the best way to save face on zoning out is to just structure your question as “When you talked about ____, it wasn’t clear to me what my takeaway should be. What should I walk away knowing about that?” This way you don’t need to say something like “I kind of got bored and was thinking about what I’m going to have for lunch—did I miss anything important?” Just “what should I know from that section?”

A good presenter will have padded the section a bit so summarizing what they think the main point was shouldn’t take much time. It’s also useful feedback for them as if you zoned out there, it’s likely others did too so they might revisit or rework it if they plant to present it again.

And finally, most presenters should treat a question like that as their failure, not yours. If I’m presenting, it’s my job to confer the information, not your job to absorb it. If I’m not engaging enough or clear enough in that conveyance, you bet I’d want to know about it. The worst thing to have happen as a presenter is zero questions at the end. By all means ask a question like “wait, wtf were you talking about in the middle there?” over just silently walking out to lunch bewildered, confused, and apathetic.

kromem Jun 4, 2024, 11:42 PM
8 points
0
on: [Paper] Stress-testing capability elicitation with password-locked models
While I think this is an interesting consideration and approach, it looks like in your methods that you are password locking the model in fine tuning, is that correct?

If so, while I would agree this work shows the lack of robustness in successful fine-tuned sandbagging for models jumping through additional hoops, I’d be reticent to generalize the findings to models where the sandbagging was a result from pretraining.

I have a growing sense that correlational dimensionality is the sleeping giant in interpretability research right now, and that those correlations run very deep in pretraining but only adjust in a much more superficial task-oriented way in fine tuning which is why the latter frequently ends up so brittle.

So while it’s reassuring sandbagging has limitations if introduced by bad actors in fine tuning, there may be a false negative in discounting the threat modeling or false positive in the efficacy of the found interventions where the sandbagging ‘intent’ was introduced in pretraining.

kromem May 31, 2024, 10:13 AM
1 point
−2
in reply to: Tobes’s comment on: “No-one in my org puts money in their pension”
In mental health circles, the general guiding principle as for whether a patient needs treatment for their mental health is whether the train of thought is interfering with their enjoyment of life.

Do you enjoy thinking about these topics and discussing them?

If you don’t—if it just stresses you out and makes the light of life shine less bright, then it’s not a bad idea to step away from it or take a break. Even if AI is going to destroy the world, that day isn’t today and arguably the threat of that looming over you sooner than a natural demise increases the value of the days you have that are good. Don’t squander a limited resource.

But if you enjoy the discussions and the debates, if you find the topic stimulating and the problem space interesting—you’re going to whittle your days away doing something no matter how you spend your time. It might as well be working on something fun that you believe in and feel may make a difference to the world. Even if your worries are overblown, time spent on something you enjoy with people you respect isn’t time wasted.

Health is a spectrum and too much of a good thing isn’t good at all. But only you can decide what’s too much and what’s the right amount. So if you feel it’s too much, you can scale it back. And if you feel it’s working out well for you, more power to you—the sense of feeling in the right place at the right time (even if under perceived dire circumstances) is a bit of a rarity in the human experience.
In general—enjoy life while it lasts. No matter your objective p(doom), your relative p(doom) is 100%. Make the most of the time you have.

kromem May 31, 2024, 10:03 AM
2 points
1
in reply to: Blacknsilver’s comment on: “No-one in my org puts money in their pension”
It’s not propaganda. OP clearly believes strongly in the sentiments discussed in the post, and its mostly a timeline of personal response to outside events than a piece meant to misinform or sway others regarding those events.

And while you do you in terms of your mental health, people who want to actually be “less wrong” in life would be wise to seek out and surround themselves by ideas different from their own.

Yes, LW has a certain broad bias, and so ironically for most people here I suspect it serves this role “less well” than it could in helping most of its users be less wrong. But particularly if you disagree with the prevailing views of the community, that makes it an excellent place to spend your time in listening, even it if can create a somewhat toxic environment for partaking in discussions and debate.

It can be a rarity to find spaces where people you disagree with take time to write out well written and clearly thought out pieces on their thoughts and perspectives. At least in my own lived experiences, many of my best insights and ideas were the result of strongly disagreeing with something I read and pursuing the train of thought resulting from that exposure.

Sycophantic agreement can give a bit of a dopamine kick, but I tend to find it next to worthless for advancing my own thinking. Give me an articulate and intelligent “no-person” any day over a “yes-person.”

Also, very few topics are actually binaries even if our brains tend towards categorizing them as such. Data doesn’t tend to truly map to only one axis, and it typically even mapped to a single axis it falls along a spectrum. It’s possible to disagree about the spectrum of a single axis of a topic while finding insight and agreement about a different axis.

Taking what works and leaving what doesn’t is probably the most useful skill one can develop in information analysis.

kromem May 31, 2024, 8:28 AM
−2 points
0
on: kromem’s Shortform
I wonder if with the next generations of multimodal models we’ll see a “rubber ducking” phenomenon where, because their self-attention was spread across mediums, things like CoT and using outputs as a scratch pad will have a significantly improved performance in non-text streams.

Will GPT-4o fed its own auditory outputs with tonal cues and pauses and processed as an audio data stream make connections or leaps it never would if just fed its own text outputs as context?

I think this will be the case, and suspect the various firms dedicating themselves to virtualized human avatars will accidentally stumble into profitable niches—not for providing humans virtual AI clones as an interface, but for providing AIs virtual human clones as an interface. (Which is a bit frustrating, as I really loathe that market segment right now.)

When I think about how Sci-Fi authors projected the future of AI cross- or self-talk, it was towards a super-efficient beeping or binary transmission of pure data betwixt them.

But I increasingly get the sense that, like much of actual AI development over the past few years, a lot of the Sci-Fi thinking was tangential or inverse to the actual vector of progress, particularly in underestimating the inherent value humans bring to bear. The wonders we see developing around us are jumpstarted and continually enabled by the patterns woven by ourselves, and it seems at least the near future developments of models will be conforming to those patterns more and more, not less and less.

Still, it’s going to be bizarre as heck to watch a multimodal model’s avatar debating itself aloud like I do in my kitchen...

kromem May 31, 2024, 5:17 AM
−1 points
0
on: How likely is it that AI will torture us until the end of time?
I’m reminded of a quote I love from an apocrypha that goes roughly like this:

Q: How long will suffering rule over humans?

A: As long as women bear children.

Also, there’s the possibility you are already in a digital resurrection of humanity, and thus, if you are worried about s-risks for AI, death wouldn’t necessarily be an escape but an acceleration. So the wisest option would be maximizing your time when suffering is low as inescapable eternal torture could be just around the corner when these precious moments pass you by (and you wouldn’t want to waste them by stressing about tomorrow during the limited number of todays you have).

But on an individualized basis, even if AI weren’t a concern, everyone faces significant s-risks towards end of life. An accident could put any person into a situation where unless they have the proper directives they could spend years suffering well beyond most people’s expectations. So if extended suffering is a concern, do look into that paperwork (the doctors I know cry most not about the healthy that get sick but the unhealthy kept alive by well meaning but misguided family).

I would argue that there’s very, very low chances of an original human capably being kept meaningfully alive to torture for eternity though. And there’s a degree of delusion of grandeur that an average person would have the insane resources necessary to extend life indefinitely spent on them just to torture them.

There’s probably better things to worry about, and even then there’s probably better things to do than worry with the limited time you do have in a non-eternal existence.

kromem May 26, 2024, 11:23 AM
1 point
0
in reply to: Rudi C’s comment on: Cicadas, Anthropic, and the bilateral alignment problem
GPT-4o is literally cheaper.

And you’re probably misjudging it for text only outputs. If you watched the demos, there was considerable additional signal in the vocalizations. It looks like maybe there’s very deep integration of SSML.

One of the ways you can bypass the failures of word problem variation errors in older text-only models was token replacement with symbolic representations. In general, we’re probably at the point of complexity where breaking from training data similarity in tokens vs having prompts match context in concepts (like in this paper) is going to lead to significantly improved expressed performance.

I would strongly suggest not evaluating GPT-4o’s overall performance in text only mode without the SSML markup added.

Opus is great, I like that model a lot. But in general I think most of the people looking at this right now are too focused on what’s happening with the networks themselves and not focused enough on what’s happening with the data, particularly around clustering of features across multiple dimensions of the vector space. SAE is clearly picking up only a small sample and even then isn’t cleanly discovering precisely what’s represented.

I’d wait to see what ends up happening with things like CoT in SSML synthetic data.

The current Gemini search summarization failures as well as an unexpected result the other week with humans around a theory of mind variation suggests to me that the more models are leaning into effectively surface statistics for token similarity vs completion based on feature clustering is holding back performance and that cutting through the similarity with formatting differences will lead to a performance leap. This may even be part of why models will frequently be able to get a problem right as a code expression than as a direct answer.

So even if GPT-5 doesn’t arrive, I’d happily bet that we see a very noticable improvement over the next six months, and that’s not even accounting for additional efficiency in prompt techniques. But all this said, I’d also be surprised if we don’t at least see GPT-5 announced by that point.

P.S. Lmsys is arguably the best leaderboard to evaluate real world usage, but it still inherently reflects a sampling bias around what people who visit lmsys ask of models as well as the ways in which they do so. I wouldn’t extrapolate relative performance too far, particularly when minor.

kromem May 25, 2024, 10:19 AM
1 point
0
in reply to: gwern’s comment on: peterbarnett’s Shortform
While I think you’re right it’s not cleanly “a Golden Bridge feature,” I strongly suspect it may be activating a more specific feature vector and not a less specific feature.

It looks like this is somewhat of a measurement problem with SAE. We are measuring SAE activations via text or image inputs, but what’s activated in generations seems to be “sensations associated with the Golden gate bridge.”

While googling “Golden Gate Bridge” might return the Wikipedia page, whats the relative volume in a very broad training set between encyclopedic writing about the Golden Gate Bridge and experiential writing on social media or in books and poems about the bridge?

The model was trained to complete those too, and in theory should have developed successful features for doing so.

In the research examples one of the matched images is a perspective shot from physically being on the bridge, a text example is talking about the color of it, another is seeing it in the sunset.

But these are all the feature activations when acting in a classifier role. That’s what SAE is exploring—give it a set of inputs and see what lights it up.

Yet in the generative role this vector maximized keeps coming up over and over in the model with content from a sensory standpoint.

Maybe generation based on functional vector manipulations will prove to be a more powerful interpretability technique than SAE probing passive activations alone?

In the above chat when that “golden gate vector” is magnified, it keeps talking about either the sensations of being the bridge as if its physical body with wind and waves hitting it or the sensations of being on the bridge. It even generates towards the end in reflecting on the knowledge of the activation about how the sensations are overwhelming. Not reflecting on the Platonic form of an abstract concept of the bridge, but about overwhelming physical sensations of the bridge’s materialism.

I’ll be curious to see more generative data and samples from this variation, but it looks like generative exploration of features may offer considerably more fidelity to their underlying impact on the network than just SAE. Very exciting!!