Two pugilists circle in the warehouse ring. That’s my man there. Blue Shorts.
There is a pause to the beat of violence and both men seem to freeze glistening under the cheap lamps. An explosion of movement from Blue. Watch closely, this is a textbook One-Two.
One. The jab. Blue snaps throws his left arm forward.
Two. Blue twists his body around and the throws a cross. A solid connection that is audible over the crowd.
His adversary drops like a doll.
Ding.
Another warehouse, another match. This time we’re looking at Red Shorts. And things are looking grim.
See Red has a very different strategy to Boy Blue. He correctly noticed that the part of the One-Two that actually knocks your opponent out is the Two. Hence, why not just throw the Two. Inspired by his favourite anime, he’s done nothing but train One Punch.
One. There is no one.
Two. He wildly swings with incredible force.
His opponent throws a counter.
The next thing Red can remember he is pulling himself up off the canvas, and trying to collect his teeth.
*** Check out the first few clips of this if you don’t know what a one-two combo is.
In boxing, the jab is a punch thrown with your leading hand. It can serve to soften your opponents defences but most importantly it helps you to “range-find” ensuring you have a feel for exactly how far away your target is.
The cross is the power move. Usually thrown with the dominant hand. The punch is backed up with momentum from your entire body. Your hips twist around, pivoting your hips and throwing If you imagine an old illustration of a “boxer” standing side on, this is a punch thrown from the hand furthest from his opponent.
The jab is “The Hard Problem”. It’s us coming up with an actual strategy to prevent AGI from causing catastrophic harm and developing enough theory to allow us to generalise to tomorrows problems.
The two is us having the technical “oomf” to actually pull it off. The expertise in contemporary AI and computation power to actually follow through with whatever the strategy is. Both of these are deeply important areas of research.
To train cross? I can immediately find resources to help me (such as Neel Nanda’s great series). And my skills are highly transferable if I decide to leave alignment. You will have to work extremely hard, but you at least know what you’re trying to do.
Contrast this with trying to train the jab. There is no guide by the nature of what preparadigmatic means. Many of the guides that do exist, may just be wrong or based on outdated assumptions. An actual attempt at solving the hard problem will appear worthless to anyone outside the alignment community.
The fact that the majority of “alignment” organisations getting money are focused prosaic alignment does not mean they have bad intentions or that individuals working on these approaches are misled. However, we should all be very concerned if there is a chance that alignment research directions are being influenced by financial interests.
I certainly think some research to produce alignment assistant AI falls under this umbrella, unless someone can explain to me such technology won’t be immediately fine-tuned and used for other purposes.
The Research Community As An Arrogant Boxer
***
Ding.
Two pugilists circle in the warehouse ring. That’s my man there. Blue Shorts.
There is a pause to the beat of violence and both men seem to freeze glistening under the cheap lamps. An explosion of movement from Blue. Watch closely, this is a textbook One-Two.
One. The jab. Blue snaps throws his left arm forward.
Two. Blue twists his body around and the throws a cross. A solid connection that is audible over the crowd.
His adversary drops like a doll.
Ding.
Another warehouse, another match. This time we’re looking at Red Shorts. And things are looking grim.
See Red has a very different strategy to Boy Blue. He correctly noticed that the part of the One-Two that actually knocks your opponent out is the Two. Hence, why not just throw the Two. Inspired by his favourite anime, he’s done nothing but train One Punch.
One. There is no one.
Two. He wildly swings with incredible force.
His opponent throws a counter.
The next thing Red can remember he is pulling himself up off the canvas, and trying to collect his teeth.
***
Check out the first few clips of this if you don’t know what a one-two combo is.
In boxing, the jab is a punch thrown with your leading hand. It can serve to soften your opponents defences but most importantly it helps you to “range-find” ensuring you have a feel for exactly how far away your target is.
The cross is the power move. Usually thrown with the dominant hand. The punch is backed up with momentum from your entire body. Your hips twist around, pivoting your hips and throwing If you imagine an old illustration of a “boxer” standing side on, this is a punch thrown from the hand furthest from his opponent.
If you’re struggling to visualise this, check out this compilation of boxers throwing one-twos https://www.youtube.com/watch?v=KN9NGbIK2q8
***
Alignment, as I see it, is a one-two.
The jab is “The Hard Problem”. It’s us coming up with an actual strategy to prevent AGI from causing catastrophic harm and developing enough theory to allow us to generalise to tomorrows problems.
The two is us having the technical “oomf” to actually pull it off. The expertise in contemporary AI and computation power to actually follow through with whatever the strategy is. Both of these are deeply important areas of research.
To train cross? I can immediately find resources to help me (such as Neel Nanda’s great series). And my skills are highly transferable if I decide to leave alignment. You will have to work extremely hard, but you at least know what you’re trying to do.
Contrast this with trying to train the jab. There is no guide by the nature of what preparadigmatic means. Many of the guides that do exist, may just be wrong or based on outdated assumptions. An actual attempt at solving the hard problem will appear worthless to anyone outside the alignment community.
The fact that the majority of “alignment” organisations getting money are focused prosaic alignment does not mean they have bad intentions or that individuals working on these approaches are misled. However, we should all be very concerned if there is a chance that alignment research directions are being influenced by financial interests.
I certainly think some research to produce alignment assistant AI falls under this umbrella, unless someone can explain to me such technology won’t be immediately fine-tuned and used for other purposes.
Lets stop neglecting our jab.
***