I used to work for Meta. I quit largely because of intense frustrations with the company. Meta has made a lot of mistakes, overlooked a lot of harms, and made a lot of short-sighted, selfish choices. Many things about…
Said company is literally in court against said government at the moment, after said government attempted to designate it too dangerous to do business with.
Approximately no one in the community thinks this. If you can go two days in a rationalist space without hearing about "Chesterton's Fence", I'll be impressed. No one thinks they're 100% rational nor that this is a…
Compare the trajectory of the US to other industrialized countries. The best charts I could find on this are from an admittedly-biased think tank, but the sources it's pulling from are well-regarded and neutral:…
https://ourworldindata.org/renewable-energy Quick stats for the US: In 2022, 11.3% of energy was generated by renewables (hydropower, solar, wind, geothermal, bioenergy, wave, and tidal). It's been growing at just under…
> His actions made perfect sense from his utilitarian Effective Altruist worldview. They don't. Everyone in EA (AFAICT) has been pretty clear about this. Lying and undermining trust and institutions does tremendous…
I will never cease to wonder at how so many people can blame so much on people trying to take a rigorous approach to world improvement, up to and including "a narcissistic con-man claimed to do trying to do X, and I can…
I am begging people to stop confusing "I was unable to get LLM X to do Y using strategy Z" with "All LLMs are categorically unable to do Y".
As the other commenter said, this is incorrect. The input was a sequence of legal moves (not even "real" moves - most of the training data was synthetically generated with "generate legal moves" as the only constraint).…
Alternatively, the prior on "this is not possible" is very low because RLHF & Friends have targeted metrics that, inadvertently or not, discourage that outcome.
Smallpox eradication
Going to be extremely hard to quantify, ransomware peddlers aren't famous for their meticulous public record-keeping. You could try to sift through all the transactions on the public blockchain and try to classify the…
Could have gone with "More Comprehensive Metrics Are All You Need"
This is a weird future.
GPT-LikeSubscribeAndRingThatBell
This is true in general but not in the use case they presented. If they had explained why a normalized distribution is useful it would have made sense - but they just describe this as pick-the-top-answer next-word…
Prediction happens at the very end (sometimes functionally earlier, but not always) - most of what happens in the model can be thought of as collecting information in vectors-derived-from-token-embeddings, performing…
It depends on the values of the vectors. (4, 4) + (3, 3) results in a new vector (7, 7) which is further away from both contributing vectors than either one was to each other originally. Additionally, negative…
The original paper is very good but I would argue it's not well optimized for pedagogy. Among other things, it's targeting a very specific application (translation) and in doing so adopts a more complicated architecture…
I endorse all of this and will further endorse (probably as a follow-up once one has a basic grasp) "A Mathematical Framework for Transformer Circuits" which builds a lot of really useful ideas for understanding how and…
That's true, but they didn't go into any other applications in this explainer and were presenting it strictly as a next-word-predictor. If they are going to include final softmax, they should explain why it's useful. It…
Thanks, that's a really useful intuition!
TIL. Man, I'm behind on my paper reading.
I am the guy asked and I endorse this guy's endorsements.
The way the article presents this is misleading. The attention mechanism builds a new vector as a linear combination of other vectors, but after the first layer these have also all been altered by passing through a…
I used to work for Meta. I quit largely because of intense frustrations with the company. Meta has made a lot of mistakes, overlooked a lot of harms, and made a lot of short-sighted, selfish choices. Many things about…
Said company is literally in court against said government at the moment, after said government attempted to designate it too dangerous to do business with.
Approximately no one in the community thinks this. If you can go two days in a rationalist space without hearing about "Chesterton's Fence", I'll be impressed. No one thinks they're 100% rational nor that this is a…
Compare the trajectory of the US to other industrialized countries. The best charts I could find on this are from an admittedly-biased think tank, but the sources it's pulling from are well-regarded and neutral:…
https://ourworldindata.org/renewable-energy Quick stats for the US: In 2022, 11.3% of energy was generated by renewables (hydropower, solar, wind, geothermal, bioenergy, wave, and tidal). It's been growing at just under…
> His actions made perfect sense from his utilitarian Effective Altruist worldview. They don't. Everyone in EA (AFAICT) has been pretty clear about this. Lying and undermining trust and institutions does tremendous…
I will never cease to wonder at how so many people can blame so much on people trying to take a rigorous approach to world improvement, up to and including "a narcissistic con-man claimed to do trying to do X, and I can…
I am begging people to stop confusing "I was unable to get LLM X to do Y using strategy Z" with "All LLMs are categorically unable to do Y".
As the other commenter said, this is incorrect. The input was a sequence of legal moves (not even "real" moves - most of the training data was synthetically generated with "generate legal moves" as the only constraint).…
Alternatively, the prior on "this is not possible" is very low because RLHF & Friends have targeted metrics that, inadvertently or not, discourage that outcome.
Smallpox eradication
Going to be extremely hard to quantify, ransomware peddlers aren't famous for their meticulous public record-keeping. You could try to sift through all the transactions on the public blockchain and try to classify the…
Could have gone with "More Comprehensive Metrics Are All You Need"
This is a weird future.
GPT-LikeSubscribeAndRingThatBell
This is true in general but not in the use case they presented. If they had explained why a normalized distribution is useful it would have made sense - but they just describe this as pick-the-top-answer next-word…
Prediction happens at the very end (sometimes functionally earlier, but not always) - most of what happens in the model can be thought of as collecting information in vectors-derived-from-token-embeddings, performing…
It depends on the values of the vectors. (4, 4) + (3, 3) results in a new vector (7, 7) which is further away from both contributing vectors than either one was to each other originally. Additionally, negative…
The original paper is very good but I would argue it's not well optimized for pedagogy. Among other things, it's targeting a very specific application (translation) and in doing so adopts a more complicated architecture…
I endorse all of this and will further endorse (probably as a follow-up once one has a basic grasp) "A Mathematical Framework for Transformer Circuits" which builds a lot of really useful ideas for understanding how and…
That's true, but they didn't go into any other applications in this explainer and were presenting it strictly as a next-word-predictor. If they are going to include final softmax, they should explain why it's useful. It…
Thanks, that's a really useful intuition!
TIL. Man, I'm behind on my paper reading.
I am the guy asked and I endorse this guy's endorsements.
The way the article presents this is misleading. The attention mechanism builds a new vector as a linear combination of other vectors, but after the first layer these have also all been altered by passing through a…