There was nothing with that much sugar, salt, fat combined together as ice cream.
This example has always frustrated me on the grounds that it is clearly false.
Eliezer correctly points out that honey existed in the ancestral environment, and so did gazelles. But if you simply pour honey over animal fat, you get something much higher in both sugar and fat than ice cream:
Ice cream is typically ~20% sugar, ~10% fat. An experiment found even that ice cream optimised for being liked by the eater involves ~15% sugar, 15% fat.
But honey is 82% sugar and animal fat is 100% fat. A 50-50 mixture is 41% sugar, 50% fat — more than twice as much of each as ice-cream.
Neither is super-salty, but animal fat (0.15%) still contains more salt than ice cream (0.08%), so a 30-70 mixture would have more sugar, fat, and salt. Also, very salty things such as salt deposits (100%) and sea water (3.5%) were sometimes available in the ancestral environment.
Of course there is something about ice cream that makes us want it more than honey-drenched fat! But I don’t know what that is, nor how it relates to AI alignment.
Somehow I never thought about it that way. Point conceded.
The analogy survives and if anything becomes more meaningful, but is now harder to explain to a general audience: After training humans exclusively on inclusive genetic fitness, with a correlation in the outer environment to high-calorie foods, humans ended up preferring something that didn’t exist in the ancestral environment, lacks correlations to micronutrients that were reliably in ample supply in the ancestral environment and didn’t need to be optimized over, has some resemblance to things that were important/scarce like the taste of sugar and salt and fat (if the sugar hasn’t been replaced with allulose), but where it ultimately depends on properties like “the ice cream is cold rather than melted” that don’t match to anything obvious at a surface glance about the ancestral environment; and on the whole, the thing that starts to max out human tastebuds seems almost impossible to have called in advance by any simple means.
If you want the old form of the analogy, “male humans scrolling Tumblr porn” works (2D images not present in ancestral environment, Coolidge effect superstimulated). Hopefully I or somebody can think of a more general-audiences-friendly transparent example of a superstimulus than that one.
I think you have put your finger on a key aspect with the coldness requirement.
When ice cream is melted or coke is lukewarm, they both taste far too sweet. I’ve long had a hypothesis that we evolved some kind of rejection of foods that taste too sweet (at least in large quantity) and that by cooling them down, they taste less sweet (overcoming that rejection mechanism) but we still get increased reward when the sugar content enters our bloodstream. I feel that carbonation is similar (flat coke tastes too sweet), so that the cold and carbonation could be hacks we’ve discovered to get around the ‘tastes too sweet’ defence mechanism, while still enjoying extremely high blood sugar based rewards. (Other forms of bitterness or saltiness added to the sweet foods could be similar.)
More speculative and still requires a few sentences to explain though, so a different example may be best.
It could just be attention. If something would otherwise be too sweet, but some other part of it is salient (coldness, carbonization, bitterness, saltiness), those other parts will take some of your attention away from its sweetness, and it’ll seem less sweet.
Why might humans evolve a rejection of things that taste to sweet? What fitness reducing thing does “eating oversweet things” correlate with? Or is it a spandrel of something else?
Perhaps the feeling of achievement gained from cookie-clicker games, such as FarmVille and such, that have taken over all the old and young people’s temporary attention? Gambling in Gatcha or Online Gambling? Opioids epidemic?
I think the ‘traditional fine dining’ experience that comes closest to this is Peking Duck.
Most of my experience has been with either salt-drenched cooked fat or honey-dusted cooked fat; I’ll have to try smoking something and then applying honey to the fat cap before I eat it. My experience is that it is really good but also quickly becomes unbalanced / no longer good; some people, on their first bite, already consider it too unbalanced to enjoy. So I do think there’s something interesting here where there is a somewhat subtle taste mechanism (not just optimizing for ‘more’ but somehow tracking a balance) that ice cream seems to have found a weird hole in.
[edit: for my first attempt at this, I don’t think the honey improved it at all? I’ll try it again tho.]
Honey baked ham is 5g fat and 3g sugar/3oz. ~28g = 1oz, so that’s 6% fat and 4% sugar, so ice cream is about 5x sugarier and ~2x fattier than honey-baked ham. In other words, for sugar and fat content, honey-drenched fat > ice cream > honey-baked ham. Honey-baked ham is therefore not a modern American equivalent to honey-drenched Gazelle fat, a sentence I never thought I’d write but I’m glad I had the chance to once in my life.
This example has always frustrated me on the grounds that it is clearly false.
Eliezer correctly points out that honey existed in the ancestral environment, and so did gazelles. But if you simply pour honey over animal fat, you get something much higher in both sugar and fat than ice cream:
Ice cream is typically ~20% sugar, ~10% fat. An experiment found even that ice cream optimised for being liked by the eater involves ~15% sugar, 15% fat.
But honey is 82% sugar and animal fat is 100% fat. A 50-50 mixture is 41% sugar, 50% fat — more than twice as much of each as ice-cream.
Neither is super-salty, but animal fat (0.15%) still contains more salt than ice cream (0.08%), so a 30-70 mixture would have more sugar, fat, and salt. Also, very salty things such as salt deposits (100%) and sea water (3.5%) were sometimes available in the ancestral environment.
Of course there is something about ice cream that makes us want it more than honey-drenched fat! But I don’t know what that is, nor how it relates to AI alignment.
Somehow I never thought about it that way. Point conceded.
The analogy survives and if anything becomes more meaningful, but is now harder to explain to a general audience: After training humans exclusively on inclusive genetic fitness, with a correlation in the outer environment to high-calorie foods, humans ended up preferring something that didn’t exist in the ancestral environment, lacks correlations to micronutrients that were reliably in ample supply in the ancestral environment and didn’t need to be optimized over, has some resemblance to things that were important/scarce like the taste of sugar and salt and fat (if the sugar hasn’t been replaced with allulose), but where it ultimately depends on properties like “the ice cream is cold rather than melted” that don’t match to anything obvious at a surface glance about the ancestral environment; and on the whole, the thing that starts to max out human tastebuds seems almost impossible to have called in advance by any simple means.
If you want the old form of the analogy, “male humans scrolling Tumblr porn” works (2D images not present in ancestral environment, Coolidge effect superstimulated). Hopefully I or somebody can think of a more general-audiences-friendly transparent example of a superstimulus than that one.
I think you have put your finger on a key aspect with the coldness requirement.
When ice cream is melted or coke is lukewarm, they both taste far too sweet. I’ve long had a hypothesis that we evolved some kind of rejection of foods that taste too sweet (at least in large quantity) and that by cooling them down, they taste less sweet (overcoming that rejection mechanism) but we still get increased reward when the sugar content enters our bloodstream. I feel that carbonation is similar (flat coke tastes too sweet), so that the cold and carbonation could be hacks we’ve discovered to get around the ‘tastes too sweet’ defence mechanism, while still enjoying extremely high blood sugar based rewards. (Other forms of bitterness or saltiness added to the sweet foods could be similar.)
More speculative and still requires a few sentences to explain though, so a different example may be best.
If this is true, it’s fascinating, because it suggest that our preference for cold and carbonation are a kind of specification gaming!
It could just be attention. If something would otherwise be too sweet, but some other part of it is salient (coldness, carbonization, bitterness, saltiness), those other parts will take some of your attention away from its sweetness, and it’ll seem less sweet.
Why might humans evolve a rejection of things that taste to sweet? What fitness reducing thing does “eating oversweet things” correlate with? Or is it a spandrel of something else?
Increased body weight or development of type 2 diabetes, for example?
Perhaps the feeling of achievement gained from cookie-clicker games, such as FarmVille and such, that have taken over all the old and young people’s temporary attention? Gambling in Gatcha or Online Gambling? Opioids epidemic?
Now I want to see how much I like honey-drenched fat
I think the ‘traditional fine dining’ experience that comes closest to this is Peking Duck.
Most of my experience has been with either salt-drenched cooked fat or honey-dusted cooked fat; I’ll have to try smoking something and then applying honey to the fat cap before I eat it. My experience is that it is really good but also quickly becomes unbalanced / no longer good; some people, on their first bite, already consider it too unbalanced to enjoy. So I do think there’s something interesting here where there is a somewhat subtle taste mechanism (not just optimizing for ‘more’ but somehow tracking a balance) that ice cream seems to have found a weird hole in.
[edit: for my first attempt at this, I don’t think the honey improved it at all? I’ll try it again tho.]
honey-baked ham is actually well-liked and considered a holiday delicacy by many Americans.
Honey baked ham is 5g fat and 3g sugar/3oz. ~28g = 1oz, so that’s 6% fat and 4% sugar, so ice cream is about 5x sugarier and ~2x fattier than honey-baked ham. In other words, for sugar and fat content, honey-drenched fat > ice cream > honey-baked ham. Honey-baked ham is therefore not a modern American equivalent to honey-drenched Gazelle fat, a sentence I never thought I’d write but I’m glad I had the chance to once in my life.