All of MrThink's Comments + Replies

MrThink40

To clarify, here are some examples of the type of projects I would love to help with:

Sponsoring University Research:
Funding researchers to publish papers on AI alignment and AI existential risk (X-risk). This could start with foundational, descriptive papers that help define the field and open the door for more academics to engage in alignment research. These papers could also provide references and credibility for others to build upon.

  • Developing Accessible Pitches:
    Creating a "boilerplate" for how to effectively communicate the importance of AI alignment t
... (read more)
MrThink80

Once Doctor Connor had left, Division Chief Morbus let out a slow breath. His hand trembled as he reached for the glass of water on his desk, sweat beading on his forehead.

She had believed him. His cover as a killeveryoneist was intact—for now.

Years of rising through Effective Evil’s ranks had been worth it. Most of their schemes—pandemics, assassinations—were temporary setbacks. But AI alignment? That was everything. And he had steered it, subtly and carefully, into hands that might save humanity.

He chuckled at the nickname he had been given "The King of ... (read more)

5lsusr
MrThink10

Great question.

I’d say that having a way to verify that a solution to the alignment problem is actually a solution, is part of solving the alignment problem.

But I understand this was not clear from my previous response.

A bit like a mathematical question, you’d be expected to be able to show that your solution is correct, not only guess that maybe your solution is correct.

MrThink10

If there exist such a problem that a human can think of, can be solved by a human and verified by a human, an AI would need to be able to solve that problem as well as to pass the Turing test.

If there exist some PhD level intelligent people that can solve the alignment problem, and some that can verify it (which is likely easier). Then an AI that can not solve AI alignment would not pass the Turing test.

With that said, a simplified Turing test with shorter time limits and a smaller group of participants is much more feasible to conduct.

2tailcalled
How do you verify a solution to the alignment problem? Or if you don't have a verification method in mind, why assume it is easier than making a solution?
MrThink10

Agreed. Passing the Turing test requires equal or greater intelligence than human in every single aspect, while the alignment problem may be possible to solve with only human intelligence.

2tailcalled
What's your model here, that as part of the Turing Test they ask the participant to solve the alignment problem and check whether the solution is correct? Isn't this gonna totally fail due to 1) it taking too long, 2) not knowing how to robustly verify a solution, 3) some people/PhDs just randomly not being able to solve the alignment problem? And probably more. So no, I don't think passing a PhD-level Turing Test requires the ability to solve alignment.
MrThink10

It might not be very clear, but as stated in the diagram, AGI is defined here as capable of passing the turing test, as defined by Alan Turing.


An AGI would likely need to surpass the intelligence, rather than be equal to, the adversaries it is doing the turing test with.

For example, if the AGI had IQ/RC of 150, two people with 160 IQ/RC should more than 50% of the time be able to determine if they are speaking with a human or an AI.

Further, two 150 IQ/RC people could probably guess which one is the AI, since the AI has the additional difficult apart from being intelligent, to also simulate being a human well enough to be indistinguishable for the judges.
 

2tailcalled
Seems extremely dubious passing the Turing test is strongly linked to solving the alignment problem.
MrThink10

Thank you for the explanation.

Would you consider a human working to prevent war fundamentally different from a gpt4 based agent working to prevent war?

2Charlie Steiner
Very different in architecture, capabilities, and appearance to an outside observer, certainly. I don't know what you consider "fundamental." The atoms inside the H-100s running gpt4 don't have little tags on them saying whether it's "really" trying to prevent war. The difference is something that's computed by humans as we look at the world. Because it's sometimes useful for us to apply the intentional stance to gpt4, it's fine to say that it's trying to prevent war. But the caveats that comes with are still very large.
MrThink10

It is a fair point that we should distinguish alignment in the sense that it does what we want it and expect it to do, from having a deep understanding of human values and a good idea of how to properly optimize for that.

However most humans probably don't have a deep understanding of human values, but I see it as a positive outcome if a random human was picked and given god level abilities. Same thing goes for ChatGPT, if you ask it what it would do as a god it says it would prevent war, prevent climate issues, decrease poverty, give universal access to ed... (read more)

2RogerDearnaley
Every autocracy in the world has done the experiment of giving a typical human massive amounts of power over other humans: it almost invariably turns out extremely badly for everyone else. For an aligned AI, we don't just need something as well aligned and morally good as a typical human, we need something morally vary better, comparable to an saint or an angel. That means building something that has never previously existed.  Humans are evolved intelligences. While they can and will cooperate on non-sero-sum games, present them with a non-iterated zero-sum situation and they will (almost always) look out for themselves and their close relatives, just as evolution would predict. We're building a non-evolved intelligence, so the orthogonality thesis applies, and what we want is something that will look out for us, not itself, in a zero-sum situation. Training (in some sense, distilling) a human-like intelligence off vast amounts of human-produced data isn't going to do this by default.
2Charlie Steiner
Deeper also means going from outputting the words "Prevent war" in many appropriate linguistic contexts to preventing war in the actual real world.[1] If getting good real-world performance means extending present-day AI with new ways of learning (and planning too, but learning is the big one unless we go all the way to model-based RL), then whether current LLMs output "Prevent war" in response to "What would you do?" is only slightly more relevant then whether my spam filter successfully filters out scams. 1. ^ Without, of course, killing all humans to prevent war. prevent climate issues, decrease poverty, and make sure all living humans have access to education.
MrThink10

I skimmed the article, but I am honestly not sure what assumption it attempts to falsify.

I get the impression that the argument from the article that you believe that no matter how intelligent the AI, it could never solve AI Alignment, because it can not understand humans since humans can not understand themselves?

Or is the argument that yes a sufficently intelligen AI or expert would understand what humans want, but it would require much higher intelligence to know what humans want, than to actually make an AI optimize for a specific task?

3johnswentworth
I think what it's highlighting is that there's a missing assumption. An analogy: Aristotle (with just the knowledge he historically had) might struggle to outsource the design of a quantum computer to a bunch of modern physics PhDs because (a) Aristotle lacks even the conceptual foundation to know what the objective is, (b) Aristotle has no idea what to ask for, (c) Aristotle has no ability to check their work because he has flatly wrong priors about which assumptions the physicists make are/aren't correct. The solution would be for Aristotle to go learn a bunch of quantum mechanics (possibly with some help from the physics PhDs) before even attempting to outsource the actual task. (And likely Aristotle himself would struggle with even the problem of learning quantum mechanics; he would likely give philosophical objections all over the place and then be wrong.)
MrThink20

In some cases I agree, for example it doesn't matter if GPT4 is a stochastic parrot or capable of deeper reasoning as long as it is useful to whatever need we have.

Two out of the five metrics are predicting the future, so it is an important part of knowing who is right, but I don't think that is all we need? If we have other factors that also correlates with being correct, why not add those in?

Also, I don't see where we risk Goodharting? Which of the metrics do you see being gamed, without a significantly increased chance of being correct also being increase?

2PatrickDFarley
Why pay mind to what's correlated with being right, when you have the option of just seeing who's right? I'm arguing that being right is the same as "holding greater predictive power", so any conversation that's not geared toward "what's the difference in our predictions?" is not about being right, but rather about something else, like "Do I fit the profile of someone who would be right" / "Am I generally intelligent" / "Am I arguing in good faith" etc.
MrThink10

True, would be interesting to conduct an actual study and see which metrics are more useful predictors.

MrThink10

I think it in large part was correlated with general risk apetite of the market, primarily a reaction to interest rates.

MrThink30

Nvidia is up 250%, Google up like 11%. So portfolio average would be greatly better than the market. So this was a great prediction after all, just needed some time.

2Richard_Kennaway
I happen to have been looking at some ETFs based on AI-related companies, and all of them showed the same pattern: a doubling of value from inception (2018 or 2019) to early 2022, then losing a lot of that over the next year, and from then to date recovering to about their former peak. Investing in any of them two years ago would have been literally a waste of time. I did not see this pattern in a few non-AI-related indexes. Are there any events between then and now to account for this, or it is just random fluctuation?

I agree it is not clear if it is net postive or negative that they open source the models, here are the main arguments for and against I could think of:


Pros with open sourcing models

- Gives AI alignment researchers access to smarter models to experiment on

- Decreases income for leading AI labs such as OpenAI and Google, since people can use open source models instead.



Cons with open sourcing models

- Capability researchers can do better experiements on how to improve capabilities

-  The open source community could develop code to faster train and run inf... (read more)

1Holly_Elmore
^ all good points, but I think the biggest thing here is the policy of sharing weights continuing into the future with more powerful models. 

I think one reason for the low number of upvotes was that it was not clear to me until the second time I briefly checked this article why it mattered.

I did not know what DoD was short for (U.S. Department of Defense), and why I should care about what they were funding.

Cause overall I do think it is interesting information.

2winstonBosan
Viktor has a point here - the title is informative, but not well optimized (perhaps intentionally) for attracting eyeballs.  Something akin to: Military and AI Compute: DoD's 100 million cheque and what did it get for them?   Might do the trick a bit better.

Hmm, true, but what if the best project needs 5 mil so it can buy GPUs or something?

Good point, if that is the case I completely agree. Can't name any such project though on the top of my mind.

Perhaps we could have a specific AI alignment donation lottery, so that even if the winner doesn't spend money in exactly the way you wanted, everyone can still get some "fuzzies".

Yeah, that should work.

There is also the possibility that there are unique "local" opportunities which benefits from many different people looking to donate, but really don´t know if that is the case.

I do mostly agree on your logic, but I'm not sure 5 mil is a better optimum than 100 k, if anything I'm slightly risk averse, which would cancel out the brain power I would need to put in. 

Also, for example, if there are 100 projects I could decide to invest in, and each wants 50k, I could donate to the 1-2 I think are some of the best. If I had 5 mil I would not only invest in the best ones, but also some of the less promising ones.

With that said, perhaps the field of AI safety is big enough that the marginal difference of the first 100k and the last... (read more)

1Christopher King
Hmm, true, but what if the best project needs 5 mil so it can buy GPUs or something? Perhaps we could have a specific AI alignment donation lottery, so that even if the winner doesn't spend money in exactly the way you wanted, everyone can still get some "fuzzies". That is, whatever x-risk related thing the winner donates to, all participants in the lottery are acknowledged and are encouraged to feel grateful for it. But yeah, that is the main drawback of the donation lottery.

I agree donation lottery is most efficient for small sums, but not sure about this amount. Let’s say I won the 50-100k usd through a donation lottery, would you have any other advice then?

1Christopher King
Not exactly sure, but probably try to find a donation lottery that pays out 5 mil or something and put your 50k in that? I'm not sure what the optimal risk/reward is for x-risk, since it's not linear. After you win, I'm not sure. But an advantage is that you can save your brain power for that timeline.

Thank you both for the feedback!

Interesting read.

While I also have experienced that GPT-4 can't solve the more challanging problems I throw at it, I also recognize that most humans probably wouldn't be able to solve many of those problems either within a reasonable amount of time.

One possibility is that the ability to solve novel problems might follow an S curve. Where it took a long time for AI to become better at novel task than 10% of people, but might go quickly from there to outperform 90%, but then very slowly increase from there.

However, I fail to see why that must neccessarily be... (read more)

Answer by MrThink32

I found this article useful:

Lessons learned from talking to >100 academics about AI safety states that "Most people really dislike alarmist attitudes" and "Often people are much more concerned with intentional bad effects of AI" so

Oh, I didnt actually notice that the banana overlaps with the book at the start, I tried changing that but still gpt-4 makes them collide:

(5,5) Initial position of the claw. (4,5) Moving left to get closer to the banana. (4,4) Moving down to align with the banana's Y coordinate. (4,3) Moving down to ensure a good grip on the banana. Close grip # Gripping the banana with at least 3 cm of overlapping area on the Y axis. (5,3) Moving right to avoid any collision with the banana's edge. (6,3) Moving right to clear the edge of the banana. (7,3) Moving right to

... (read more)

Yes, all other attempts with ChatGPT were similar.

GPT-4 got it almost correct on the first attempt

(5,5) Initial position. (4,5) Moving left to get closer to the banana. (4,4) Moving down to align with the banana's top edge. (4,3) Moving down to be within the required overlapping area of the banana. Close grip. Gripping the banana.

(4,4) Lifting the banana upwards. (5,4) Moving right to clear the initial banana position. (6,4) Continuing to move right towards the book. (7,4) Moving further right to avoid collision with the book's edges. (8,4) Positioning the

... (read more)
1Bruce G
Interesting. I don't think I can tell from this how (or whether) GPT-4 is representing anything like a visual graphic of the task. It is also not clear to me if GPT-4's performance and tendency to collide with the book is affected by the banana and book overlapping slightly in their starting positions. (I suspect that changing the starting positions to where this is no longer true would not have a noticeable effect on GPT-4's performance, but I am not very confident in that suspicion.)

Thanks for the clarifications, that makes sense.

I agree it might be easier to start as a software development company, and then you might develop something for a client that you can replicate and sell to other.

Just anecdotal evidence, I use ChatGPT when I code, the speedup in my case is very modest (less than 10%), but I expect future models to be more useful for coding.

I agree with the main thesis "sell the service instead of the model access" , but just wanted to point out that the Upworks page you link to says:

GoodFirms places a basic app between $40,000 to $60,000, a medium complexity app between $61,000 to $69,000, and a feature-rich app between $70,000 to $100,000.

Which is significantly lower than the $100-200k you quote for a simple app.

Personally I think even $40k sounds way to expensive for a what I consider a basic app.

On another note, I think your suggestion of building products and selling to many clients is f... (read more)

1lemonhope
Added footnote clarifying link (goodfirms seems misquoted and also kind of looks fake?) I mentioned the software development firm as an intermediate step to products because it's less risky / easier than making a successful product. Even easier would just be to hire devs, give them your model, put them on upwork, and split the profits. I suppose the ideal commercialization plan depends on how the model works and the size of the firm commercializing it. (And for govts and universities "commercialization" is completely different.)

I do agree that OpenAI is an example of good intentions going wrong, however I think we could learn from that and top researchers would be vary of such risks.

Nevertheless I do think your concerns are valid and is important not to dismiss.

Okay, so seems like our disagreement comes down to two different factors:

  1. We have different value functions, I personally don’t value currently living human >> than future living humans, but I agree with the reasoning that to maximize your personal chance of living forever faster AI is better.

  2. Getting AGI sooner will have much greater positive benefits than simply 20 years of peak happiness for everyone, but for example over billions of years the accumulative effect will be greater than value from a few hundreds of thousands of years of of AGI.

... (read more)

Sadly I could only create questions between 1-99 for some reason, I guess we should interpret 1% to mean 1% or less (including negative).

What makes you think more money would be net negative?

Do you think that it would also be negative if you had 100% of how the money was spent, or would it only apply if other AI Alignment researchers were responsible for the strategy to donate?

2JBlack
I think more money spent right now, even with the best of intentions, is likely to increase capabilities much faster than it reduces risk. I think OpenAI and consequent capability races are turning out to be an example of this. There are hypothetical worlds where spending an extra ten billion (or a trillion) dollars on AI research with good intentions doesn't do this, but I don't think they're likely to be our world. I don't think that directing who gets the money is likely to prevent it, without pretty major non-monetary controls in addition.

Interesting take.

Perhaps there was something I misunderstood, but wouldn't AI alignment work and AI capabilities slowdown still have extreme positive expected value even if the probability of unaligned AI is only 0.1-10%?

Let's say the universe will exist for 15 billion more years until the big rip.

Let's say we could decrease the odds of unaligned AI by 1% by "waiting" 20 years longer before creating AGI, we would lose out 20 years of extreme utility, which is roughly 0.00000001% of the total time (approximation of utility).

 On net we gain 15 billion *... (read more)

1[anonymous]
You're choosing a certain death for 32% of currently living humans.  Or at least, the humans alive after [some medical research interval] at the time the AGI delay decision is made.   The [medical research interval] is the time it requires, withly massively parallel research, for a network of AGI systems to learn which medical interventions will prevent most forms of human death, from injury and aging.   The economic motivation for a company to research this is obvious.   Delaying AGi is choosing to shift the time until [humans start living their MTBF given perfect bodies and only accidents and murder, which is thousands of years], 20 years into the future.   Note also that cryonics could be made to work, with clear and convincing evidence including revival of lab mammals, probably within a short time.  That [research interval until working cryo] might be months.   Personally as a member of that subgroup, the improvement in odds ratio for misaligned AI for that 20 year period would need to be greater than 32%, or it isn't worth it.  Or essentially you'd have to show pDoom really was almost 1.0 to justify such a long delay. Basically you would have to build AGIs and show they all inherently collaborate with each other to kill us by default.  Too few people are convinced by EY, even if he is correct.

Excellent point. 

I do think that the first AGI developed will have a big effect on the probability of doom, so hopefully it will be some value possible to derive from the question. But it would be interesting to control for what other AIs do, in order to get better calibrated statistics.

Interesting test!

I wrote a simplified test based on this and gave it to ChatGPT, and despite me trying various prompts, it never got a correct solution, although it did come close several times.

I think uPaLM would have been able to figure out my test though.

Here is the prompt I wrote:

You are tasked to control a robotic arm to put a banana on top of a book.

You have a 2D view of the setup, and you got the horizontal coordinates X and vertical coordinates y in cm.

The banana is a non perfect elliptical shap, whit the edges touching the following (X, Y) coordin

... (read more)
1Bruce G
It looks like ChatGPT got the micro-pattern of "move one space at a time" correct.  But it got confused between "on top of" the book versus "to the right of" the book, and also missed what type of overlap it needs to grab the banana. Were all the other attempts the same kind of thing? I would also be curious to see how uPaLM or GPT-4 does with that example.
2green_leaf
Should that be "at least 1 cm"?

I agree with the reasoning of this post, and believe it could be a valuable instrument to advance science.

There does exists scientific forecasting on sites like Manifold market and Hypermind, but those are not monetarily traded as sports betting is.

One problem I see with scientific prediction markets with money, is that it may create poor incentives (as you also discuss in your first foot note).

For example, if a group of scientists are convinced hypothesis A is true, and bet on it in a prediction market, they may publish biased papers supporting their hypo... (read more)

3Lucas L
Futuur is a prediction market with play money and real money options (each option has a different probability of some event occurring). An interesting market launched was which option would be more accurate, and real money won even with fewer bettors.   I believe markets with play money are more likely to be biased as no money is involved, with less skin in the predictions.

Perhaps an advanced game engine could be used to create lots of simulations of piles of money. Like, if 100 3d objects of money are created (like 5 coins, 3 bills with 10 variations each (like folded etc), some fake money and other objects). Then these could be randomly generated into constellations. Further, it would then be possible to make videos instead of pictures, which makes it even harder for AI's to classify. Like, imagine the camera changing angel of a table, and a minimum of two angels are needed to see all bills.

I don't think the photos/videos needs to be super realistic, we can add different types of distortions to make it harder for the AI to find patterns.

'identify humans using some kind of physical smart card system requiring frequent or continuous re-authentication via biometric sensors'

This is a really fascinating concept. Maybe the captcha could work in a way like "make a cricle with your index finger" or some other strange movement, and the chip would use that data to somehow verify that the action was done. If no motion is required I guess you could simply store the data outputted at one point and reuse it? Or the hacker using their own smart chip to authenticate them without them actually having to d... (read more)

This idea is really brilliant I think, quite promising that it could work. It requires the image AI to understand the entire image, it is hard to divide it up into one frame per bill/coin. And it can't use the intelligence of LLM models easily.

To aid the user, on the side there could be a clear picture of each coin and their worth, that we we could even have made up coins, that could further trick the AI.

All this could be combined with traditional image obfucation techniques (like making them distorted.

I'm not entirely sure how to generate images of money ... (read more)

2Bruce G
  A user aid showing clear pictures of all available legal tender coins is a very good idea.  It avoids problems more obscure coins which may have been only issued in a single year - so the user is not sitting there thinking "wait a second, did they actually issue a Ulysses S. Grant coin at some point or it that just there to fool the bots?". I agree that efficient generation of these types of images is the main difficulty and probable bottleneck to deploying something like this if websites try to do so.  Taking a large number of such pictures in real life would be time consuming.  If you could speed up the process by automated image generation or automated creation of synthetic images by copying and pasting bills or notes between real images, that would be very useful.  But doing that while preserving photo-realism and clarity to human users of how much money is in the image would be tricky.

I get what you mean, if an AI can do things as well as the human, why block it?

I'm not really sure how that would apply in most cases however. For example bot swarms on social media platforms is a problem that has received a lot of attention lately. Of course, solving a captcha is not as deterring as charging let's say 8 usd per month, but I still think captchas could be useful in a bot deterring strategy.

Is this a useful problem work on? I understand that for most people it probably isn't, but personally I find it fun, and it might even be possible to start a SAAS business to make money that could be spent on useful things (although this seems unlikely).

1Dave Lindbergh
$8/month (or other small charges) can solve a lot of problems. Note that some of the early CAPTCHA algorithms solved two problems at once - both distinguishing bots from humans, and helping improve OCR technology by harnessing human vision. (I'm not sure exactly how it worked - either you were voting on the interpretation of an image of some text, or you were training a neural network).  Such dual-use CAPTCHA seems worthwhile, if it helps crowdsource solving some other worthwhile problem (better OCR does seem worthwhile).

Please correct me if I misunderstand you.

We have to first train the model that generates the image from the captcha, before we can provide any captcha, meaning that the hacker can train their discriminator on images generated by our model.

But even if this was not the case, generating is a more difficult task that evaluating. I'm pretty sure a small clip model that is two years old can detects hands generated by stable diffusion (probably even without any fine tuning), which is a more modern and larger model.

What happens when you train using GANs, is that e... (read more)

While it is hard for AI to generate very real looking hands, it is a significantly easier task for AI to classify if hands are real or AI generated.

But perhaps it's possible to make extra distortions somehow that makes it harder for both AI and humans to determine which are real...

1Lech Mazur
I don't think this is true. If it was possible to distinguish them, you could also guide the diffuser to generate them correctly. And if you created a better classification model, you would probably apply it to generation first rather than solving captchas.

I think "video reasoning" could be an interesting approach as you say.

Like if there are 10 frames and no single frame shows a tennis racket, but if you play them real fast, a human could infer there being a tennis racket because part of the racket is in each frame.

I do think "image reasoning" could potentially be a viable captcha strategy.

A classic example is "find the time traveller" pictures, where there are modern objects that gives away who the time traveller is.

However, I think it shouldn't be too difficult to teach an AI to identify "odd" objects in an image, unless each image has some unique trick, in which case we would need to create millions of such puzzles somehow. Maybe it could be made harder by having "red herrings" that might seem out of place but actually aren't which might make the AI misunderstand part of the time.

1Garrett Baker
If done such that nothing using current AI tech could do it, I don't think 90% of people would be able to identify a time traveler.

Really interesting idea to make it 3D. I think it might be possible to combined with random tasks given by text, such as "find the part of the 3d object that is incorrect" or different tasks like that (and the object in this case might be a common object like a sofa but one of the pillows is made of wood or something like that)

1[anonymous]
Well, the point here is with geometry tasks, you can generate and evaluate an arbitrarily large number of problem instances automatically. Hand-crafted common sense reasoning tasks work great in the context of a Turing test but are vulnerable to simple dataset lookup in the CAPTCHA context.

I still think it might be possible to train AI to distinguish between real and deepfake videos of humans speaking, so that might still be a viable, yet time consuming solution.

Miri: Instead of paperclips the AI is optimizing for solving captchas, and is now turning the world into captcha solving machines. Our last chance is to make a captcha that only verified if human prosperity is guaranteed. Any ideas? 

There are browser plugins, but I haven't tried any of them.

General purpose CAPTCHA solver could be really difficult assuming people would start building more diverse CAPTCHAS. All CAPTCHAS I've seen so far has been of a few number of types.

One "cheat" would be to let users use their camera and microphone to record them saying a specified sentence. Deepfakes can still be detected, especially if we add requirements such as "say it in a cheerful tone" and "cover part of your mouth with your finger". That's not of course a solution to the competition but might be a potential workaround.

5Dagon
The "90% of internet users can do it" is a really binding constraint.  Ability to speak in a requested tone or the like cuts out a surprisingly large portion of real humans.   A lot hinges on the requirements and acceptable error rates in both directions, too.  "Identify using your bank or mobile account" limits AIs pretty strictly to those with enough backing to get a bank or phone, and certainly cuts down on quantity of non-human accounts.  But it's also a lot of friction for humans, and a lot will choose not to do so, or be unable to.

I think those are very creative ideas, and I think asking for "non-obvious" things in pictures is a good approach, since basically all really intelligent models are language models, some sort of "image reasoning" might work.

I tried the socket with the clip model, and the clip model got the feeling correct very confidently:



I myself can't see who the person in the bread is supposed to be, so I think an AI would struggle with it too. But on the other hand I think it shouldn't be too difficult to train a face identification AI to identify people in bread (or h... (read more)

True.

And while there might be some uses of such benchmarks on politics etc, combining them with other benchmarks doesn't really seems like a useful benchmark.

Interesting. Even if only a small part of the tasks in the test are poor estimates of general capabilities, it makes the test as a whole less trustworthy.

5the gears to ascension
yeah, at least in terms of being a raw intelligence test. the easiest criticism is that the test has political content, which of course means that even to the degree the political content is to any one person's liking, the objectively true answer is significantly more ambiguous than ideal. alignment/friendliness and capabilities/intelligence can never be completely separated when the rubber hits the road. part of the problem with politics is that we can't be completely sure we've mapped the consequences of our personal views on basic moral philosophies correctly, so more reasoning power can cause a stronger model to behave arbitrarily differently on morality-loaded questions. and there may be significantly more arbitrary components than that in any closed book language based capabilities test. see also the old post on [[guessing the teacher's "password"]], guessing what the teacher is thinking
MrThink*10

For researchers (mainly)

Artificial intelligence isn’t limited in the same ways the human brain is.

Firstly, it isn’t limited to only run on a single set of hardware, it can be duplicated and speeded up to be thousands of times faster than humans, and work on multiple tasks in parallel, assuming powerful enough processors are available.

Further, AI isn’t limited to our intelligence, but can be altered and improved with more data, longer training time and smarter training methods. While the human brain today is superior to AI’s on tasks requiring deep thinking... (read more)

What if AI safety could put you on the forefront of sustainable business?

The revolution in AI has been profound, it definitely surprised me, even though I was sitting right there.
-Sergey Brin, Founder of Google

Annual investments in AI increased eightfold from 2015 to 2021, reaching 93 billion usd.

This massive growth is making people ever more dependent on AI, and with that potential risks increases.

Prioritizing AI safety is therefore becoming increasingly important in order to operate a sustainable business, with the benefits of lower risks and improved public perception.


 

Load More