Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Misalignment Museum

niche-museums.com

Post reply on HN
Print view View original

51–60 of 64 posts

Re: Misalignment Museum

#51

Post by blincoln »

simonw wrote: post #35
Pamar wrote: post #16

Earlier quoted context omitted.

Is there a way to add entries to this collection, or do you only list museums you have been personally been at? I ask because I tried look for listings of places I know well (e.g. Turin, Italy or Budapest, Hungary) and found that the closest entry was hundreds of miles away. Turin has, for example, this: http://www.museodellafrutta.it/en/ which is pretty niche, imho. Budapest has a chocolate museum: https://www.csoko…

I accept tips of where I should go next, but the site is exclusively museums I've been to myself - it's a really rewarding hobby.

I see you've been to several aviation museums, but if you're ever anywhere near Ohio, may I suggest the Air Force museum? There are so many aircraft there that one can't see anywhere else, like the only remaining XB-70.

Some other personal favourites:

* Molson, Washington - it's a preserved ghost town, somewhat like Bodie, California, but one can go inside nearly all of the structures, and there is an actual museum set up in the three-story former town school.

* Not sure this counts, because The Met isn't a niche museum overall, but their Egyptian wing is the only place I've been to where one can walk through two more or less complete ancient Egyptian structures without going to Egypt.

Re: Misalignment Museum

#52

Post by DonHopkins »

debesyla wrote: post #29
simonw wrote: post #2

Wow, didn't expect my https://www.niche-museums.com/ website to show up on Hacker News! It's actually running on a templated instance of Datasette - try the "Use my location" button on the homepage to see tiny museums near you that I've been to.

I have one suggestion too! :-D The Devil Museum in Kaunas, Lithuania ( https://ciurlionis.lt/activity/permanent-exhibitions/velniu-... ). It has few hundred wooden devil statues, most of them made in traditional methods.

How does one traditionally make devils?

Re: Misalignment Museum

#53

Post by brchr »

ahepp wrote: post #11

This actually brings to mind a conversation I've been having with my buddies recently. Has there ever been a case of harm from AI misalignment? Not some kind of speculative art exhibit, but real harm?

Author of "The Alignment Problem" here, to say: Of course this question depends on your semantics of "harm," "AI," and "alignment," but by most definitions (and certainly by mine) the answer is overwhelmingly yes, many.

These harms can be diffuse at massive scale, and acute at small scale.

One example of each: (1) https://www.science.org/doi/abs/10.1126/science.aax2342 One of USA’s largest health insurers builds ML system for patient triage. It optimizes for a proxy metric of health need (namely, cost) rather than health need itself; consequently it deprioritizes and systematically excludes millions of people from access to health care.

(2) https://en.wikipedia.org/wiki/Death_of_Elaine_Herzberg Autonomous Uber car builds their braking system on top of a vision model that optimizes for object classification accuracy using categories of {"pedestrian", "cyclist", "vehicle", "debris"}; consequently it fails to determine how to classify a woman walking a bicycle across the street, as a result killing her.

In both cases, optimizing for a naively sensible proxy metric of the thing that was truly desired turned out to be catastrophic.

Re: Misalignment Museum

#54

Post by pixl97 »

tsukikage wrote: post #30
ahepp wrote: post #18

Earlier quoted context omitted.

I guess maybe one could make that argument, but the majority of AI alignment concerns seem more along the lines of skynet level scenarios. The paperclip optimizer could be called a "bug" I guess. But the comparison to Tesla autopilot is interesting. First, is anyone calling that an AI? Second, when an objective baseline comparison to human drivers is possible, shouldn't that determine whether the AI is a net benefit…

Misalignment is not malice. The paperclip optimizer isn't malicious. The risk isn't software going evil on us. The risk is software doing exactly what we made it do. A software bug is generally what we call the situation where software does exactly what its creator asked it to do, but that thing is not a thing its creator actually intended or wanted. The creator did not correctly express their request, and/or did not…

>When we interact with a general AI, we are programming a computer system, in English.

I agree with what you're saying in your post, but I want to further refine the part of your statement 'in English'....

LLMs are far beyond that... We're not just interacting in English, we're interacting in all languages the model was trained on. The key word here is language because for the average human this entails the primary language they grew up with. But for many people that are bilingual they realize the complexity of language potential is far greater than a person that speaks a single language, some languages can contain concepts that don't exist in another language. Now extent that ever further. Programming languages are not much different from human spoken language, just more formalized. Mathematics is a language that contains formal language.

And it can extend even further than that... That 802.11 signal in the air is a language, along with all of our other wireless signals. Yes, people have used deep learning to decode wireless.

I brought all this up because as models become more multi-modal us humans are going to get stuck in thinking that what we say/type to the AI might be what it is interpreting when the actual model may be working on a far larger and richer dataset then we are giving it credit for. As you said above, this would cause us to incorrectly interpret the capabilities of the model, likely significantly underestimating its ability in places where humans are incapable without additional tooling.

Re: Misalignment Museum

#55

Post by pixl97 »

chrisco255 wrote: post #32
rollo wrote: post #21

Earlier quoted context omitted.

Corporations can be regarded as AI agents with misaligned goals. In a bit over a century this has resulted in damage to the climate and Earth's ecosystem that is threatening the survival of our civilization. And that's just slow, badly optimized paperclippers so far.

It's really not though is it, that's just your programming thinking for you. Human deaths from weather and climate related events are near all time lows, while overall population is indeed at all time highs. We have better crop yields (3) and productivity thanks to both technology and indeed, CO2 fertilization of the atmosphere (4), which is driven by photosynthesis, a process which is optimized at thousands of ppm f…

Huge amount of monocultures are not the sign of a healthy environment, but one that is at the precipice of collapse.

This behavior is seen in animal populations quite often. A series of 'good' events happen allowing the population to expand beyond the mean population capacity. If the good times are excessively long or excessively good you can see a rapid overshoot in total population. When this occurs the population is screwed. Even if 'bad' times do not come just reducing resources to what the mean population can support means that a large dying off will occur, that die off will typically kill almost all the population of said animal because of consumption of almost all available food. You then get a drastic reduction in total population far below the mean carrying capacity. If the environment switches from 'good' times, say high water availability into extreme extended drought you can get species extinction.

Re: Misalignment Museum

#56

Post by otippat »

jeisc wrote: post #20

to kill humanity first it must already exist in my opinion our efforts at being humane have not yet risen to our ability to imagine humanity I do not think that AI will help in our efforts to create humanity but will rather enhance the negative aspects of our already harsh nature

You don't think that the use of that word in this context simply refers to humankind?

Re: Misalignment Museum

#57

Post by michael_nielsen »

ahepp wrote: post #18
ajuc wrote: post #13

Earlier quoted context omitted.

The problem with that is - until we have "true AGI" about which everybody agree it's "true AGI" - you can always dismiss deaths caused by software as "just a bug, not an AI safety problem". For example when Tesla autopilot kills someone (which has happened). https://impakter.com/tesla-autopilot-crashes-with-at-least-a...

I guess maybe one could make that argument, but the majority of AI alignment concerns seem more along the lines of skynet level scenarios. The paperclip optimizer could be called a "bug" I guess. But the comparison to Tesla autopilot is interesting. First, is anyone calling that an AI? Second, when an objective baseline comparison to human drivers is possible, shouldn't that determine whether the AI is a net benefit…

You asked for examples of existing harms from AI misalignment, and now seem to define AI misalignment so that, by definition, it excludes all current systems. So tautologically the answer to your question will be "no".

Brian Christian's book "The Alignment Problem" contains many examples of harms from systems which people plausibly see as being based on precursor technology.

Re: Misalignment Museum

#58

Post by ajuc »

chrisco255 wrote: post #45
ajuc wrote: post #44

Earlier quoted context omitted.

Diversity vs biomass. If AI prefers biomass over diversity we're pretty much fucked ;) If it prefers diversity - at least some of us will remain in ZOOs ;)

The conditions necessary for biomass expansion are also conducive to biodiversity. Indeed, the vast majority of biological diversity is in the tropical region of earth. Species of life seem to have a very hard time in the arctic regions. As for AIs, I see no reason why they should prefer any characteristic of ecology at all, if all of their needs can be met from silicon and electricity. (1) https://www.researchgate.n…

> The conditions necessary for biomass expansion are also conducive to biodiversity.

It might be the case in general, but currently we're experiencing biodiversity loss on the global scale. [1] [2]

[1] https://en.wikipedia.org/wiki/Biodiversity_loss [2] https://en.wikipedia.org/wiki/Holocene_extinction

Re: Misalignment Museum

#59

Post by yamtaddle »

meindnoch wrote: post #31

Oh. I thought it would be a museum of slightly misaligned things. It would be a fun place to visit for OCD-type people.

Yeah, I was expecting something like the exact opposite of that "things fitting perfectly in other things" Tumblr (at least, I think it was a Tumblr).

Re: Misalignment Museum

#60

Post by debesyla »

DonHopkins wrote: post #52
debesyla wrote: post #29

Earlier quoted context omitted.

I have one suggestion too! :-D The Devil Museum in Kaunas, Lithuania ( https://ciurlionis.lt/activity/permanent-exhibitions/velniu-... ). It has few hundred wooden devil statues, most of them made in traditional methods.

How does one traditionally make devils?

I meant in lithuanian folk art traditions - mostly woodcarvings with various paints, but sometimes using other materials too. I guess forms and colors can also be included in definition of "traditional" :thinking_emoji:

Anyway, I am not an art expert or anything, I just find Devil museum interesting, haha. I managed to find a virtual tour of it too: https://3dtour.1001pikselis.lt/tour/velniu-muziejus

Post reply on HN