Nora Belrose
@norabelrose.bsky.social
AI, philosophy, spirituality
Head of interpretability research at EleutherAI, but posts are my own views, not Eleuther’s.
Head of interpretability research at EleutherAI, but posts are my own views, not Eleuther’s.
why don't more people become zoroastrian?
it's where judaism and christianity got the idea of ethical monotheism, afterlife, and final judgment but without any of their baggage
(no eternal hell, no historically questionable dogmas, etc.)
it's where judaism and christianity got the idea of ethical monotheism, afterlife, and final judgment but without any of their baggage
(no eternal hell, no historically questionable dogmas, etc.)
October 24, 2025 at 3:32 AM
why don't more people become zoroastrian?
it's where judaism and christianity got the idea of ethical monotheism, afterlife, and final judgment but without any of their baggage
(no eternal hell, no historically questionable dogmas, etc.)
it's where judaism and christianity got the idea of ethical monotheism, afterlife, and final judgment but without any of their baggage
(no eternal hell, no historically questionable dogmas, etc.)
If we care only about appearances, outcomes, and results then AI will outcompete humans at everything
If we care about the process used to create things then humans can still have jobs and meaningful lives
The idea that ends can be detached from means is the root of many evils
If we care about the process used to create things then humans can still have jobs and meaningful lives
The idea that ends can be detached from means is the root of many evils
October 11, 2025 at 1:10 AM
If we care only about appearances, outcomes, and results then AI will outcompete humans at everything
If we care about the process used to create things then humans can still have jobs and meaningful lives
The idea that ends can be detached from means is the root of many evils
If we care about the process used to create things then humans can still have jobs and meaningful lives
The idea that ends can be detached from means is the root of many evils
Strongly agree with this bill https://www.usatoday.com/story/news/politics/2025/09/29/ohio-state-legislator-ban-people-marrying-ai/86427987007/
September 30, 2025 at 1:35 AM
Strongly agree with this bill https://www.usatoday.com/story/news/politics/2025/09/29/ohio-state-legislator-ban-people-marrying-ai/86427987007/
if the laws of physics are fundamentally probabilistic, as they seem to be, that makes it easier to see how they can smoothly change over time
June 13, 2025 at 7:48 AM
if the laws of physics are fundamentally probabilistic, as they seem to be, that makes it easier to see how they can smoothly change over time
data attribution is a special case of data causality:
estimating the causal effect of either learning or unlearning one datapoint (or set of datapoints) on the neural network's behavior on other datapoints
estimating the causal effect of either learning or unlearning one datapoint (or set of datapoints) on the neural network's behavior on other datapoints
June 12, 2025 at 4:02 AM
data attribution is a special case of data causality:
estimating the causal effect of either learning or unlearning one datapoint (or set of datapoints) on the neural network's behavior on other datapoints
estimating the causal effect of either learning or unlearning one datapoint (or set of datapoints) on the neural network's behavior on other datapoints
Neural networks don't have organs.
They aren't made of fixed mechanisms.
They have flows of information and intensities of neural activity. They can't be organized into a set of parts with fixed functions.
In the words of Gilles Deleuze, they're bodies without organs (BwO).
They aren't made of fixed mechanisms.
They have flows of information and intensities of neural activity. They can't be organized into a set of parts with fixed functions.
In the words of Gilles Deleuze, they're bodies without organs (BwO).
March 27, 2025 at 7:11 PM
Neural networks don't have organs.
They aren't made of fixed mechanisms.
They have flows of information and intensities of neural activity. They can't be organized into a set of parts with fixed functions.
In the words of Gilles Deleuze, they're bodies without organs (BwO).
They aren't made of fixed mechanisms.
They have flows of information and intensities of neural activity. They can't be organized into a set of parts with fixed functions.
In the words of Gilles Deleuze, they're bodies without organs (BwO).
This seems like a cool way to use an adaptive amount of compute per token. I speculate that models like these will have more faithful CoT since they don't get to do "extra" reasoning on easy tokens https://arxiv.org/abs/2404.02258
Mixture-of-Depths: Dynamically allocating compute in...
Transformer-based language models spread FLOPs uniformly across input sequences. In this work we demonstrate that transformers can instead learn to dynamically allocate FLOPs (or compute) to...
arxiv.org
March 13, 2025 at 11:55 PM
This seems like a cool way to use an adaptive amount of compute per token. I speculate that models like these will have more faithful CoT since they don't get to do "extra" reasoning on easy tokens https://arxiv.org/abs/2404.02258
Also chapter 10 where he discards the notion of the Soul but maintains the distinction between mind and brain
February 24, 2025 at 6:35 PM
Also chapter 10 where he discards the notion of the Soul but maintains the distinction between mind and brain
William James did a lot of good philosophy of mind in chapters 1, 5, and 6 ofThe Principles of Psychology, we've barely made any progress in 135 years 😂
February 24, 2025 at 6:35 PM
William James did a lot of good philosophy of mind in chapters 1, 5, and 6 ofThe Principles of Psychology, we've barely made any progress in 135 years 😂
I love this meme
February 22, 2025 at 5:33 AM
I love this meme
might interest @nabla_theta
February 7, 2025 at 12:32 AM
might interest @nabla_theta
Pro tip: if you want to implement TopK SAEs efficiently, and don't want to deal with Triton, just use this function for the decoder, it's much faster than the naive dense matmul implementation
https://pytorch.org/docs/stable/generated/torch.nn.functional.embedding_bag.html
https://pytorch.org/docs/stable/generated/torch.nn.functional.embedding_bag.html
February 6, 2025 at 7:32 PM
Pro tip: if you want to implement TopK SAEs efficiently, and don't want to deal with Triton, just use this function for the decoder, it's much faster than the naive dense matmul implementation
https://pytorch.org/docs/stable/generated/torch.nn.functional.embedding_bag.html
https://pytorch.org/docs/stable/generated/torch.nn.functional.embedding_bag.html
What are the chances you'd get a fully functional language model by randomly guessing the weights?
We crunched the numbers and here's the answer:
We crunched the numbers and here's the answer:
February 3, 2025 at 10:01 PM
What are the chances you'd get a fully functional language model by randomly guessing the weights?
We crunched the numbers and here's the answer:
We crunched the numbers and here's the answer:
we have seven (!) papers lined up for release next week
you know you're on a roll when arxiv throttles you
you know you're on a roll when arxiv throttles you
February 2, 2025 at 3:35 AM
we have seven (!) papers lined up for release next week
you know you're on a roll when arxiv throttles you
you know you're on a roll when arxiv throttles you
deepseek now largely replacing chatgpt for me
January 24, 2025 at 1:33 AM
deepseek now largely replacing chatgpt for me
Evolutionary biology can learn things from machine learning.
Natural selection alone doesn't explain "train-test" or "sim-to-real" generalization, which clearly happens.
At every level of organization, life can zero-shot adapt to novel situations. https://www.youtube.com/watch?v=jJ9O5H2AlWg
Natural selection alone doesn't explain "train-test" or "sim-to-real" generalization, which clearly happens.
At every level of organization, life can zero-shot adapt to novel situations. https://www.youtube.com/watch?v=jJ9O5H2AlWg
December 29, 2024 at 10:29 PM
Evolutionary biology can learn things from machine learning.
Natural selection alone doesn't explain "train-test" or "sim-to-real" generalization, which clearly happens.
At every level of organization, life can zero-shot adapt to novel situations. https://www.youtube.com/watch?v=jJ9O5H2AlWg
Natural selection alone doesn't explain "train-test" or "sim-to-real" generalization, which clearly happens.
At every level of organization, life can zero-shot adapt to novel situations. https://www.youtube.com/watch?v=jJ9O5H2AlWg
Truth is relative, when it comes to the physical state of the universe.
But we should accept the existence of perspective-neutral facts about how perspectives relate to one another, to avoid vicious skeptical paradoxes. https://arxiv.org/abs/2410.13819
But we should accept the existence of perspective-neutral facts about how perspectives relate to one another, to avoid vicious skeptical paradoxes. https://arxiv.org/abs/2410.13819
December 28, 2024 at 9:56 PM
Truth is relative, when it comes to the physical state of the universe.
But we should accept the existence of perspective-neutral facts about how perspectives relate to one another, to avoid vicious skeptical paradoxes. https://arxiv.org/abs/2410.13819
But we should accept the existence of perspective-neutral facts about how perspectives relate to one another, to avoid vicious skeptical paradoxes. https://arxiv.org/abs/2410.13819
Neural networks are polycomputers in
@drmichaellevin.bsky.social's sense.
Depending on your perspective, you can interpret them as performing many different computations on different types of features. No perspective is uniquely correct. arxiv.org/abs/2212.10675
@drmichaellevin.bsky.social's sense.
Depending on your perspective, you can interpret them as performing many different computations on different types of features. No perspective is uniquely correct. arxiv.org/abs/2212.10675
There's Plenty of Room Right Here: Biological Systems as Evolved, Overloaded, Multi-scale Machines
The applicability of computational models to the biological world is an active topic of debate. We argue that a useful path forward results from abandoning hard boundaries between categories and adopt...
arxiv.org
December 28, 2024 at 7:38 PM
Neural networks are polycomputers in
@drmichaellevin.bsky.social's sense.
Depending on your perspective, you can interpret them as performing many different computations on different types of features. No perspective is uniquely correct. arxiv.org/abs/2212.10675
@drmichaellevin.bsky.social's sense.
Depending on your perspective, you can interpret them as performing many different computations on different types of features. No perspective is uniquely correct. arxiv.org/abs/2212.10675
If OpenAI's new o3 model is "successfully aligned," then it could probably be trusted to supervise more powerful models, allowing us to bootstrap to benevolent superintelligence.
December 20, 2024 at 9:20 PM
If OpenAI's new o3 model is "successfully aligned," then it could probably be trusted to supervise more powerful models, allowing us to bootstrap to benevolent superintelligence.
Interesting to see @philipgoff.bsky.social go back and forth on the fine-tuning argument.
I think the multiverse definitely can't explain fine-tuning, but it's also unclear we need an explanation at all. And God may be a more "complex" hypothesis than the physical constants themselves.
I think the multiverse definitely can't explain fine-tuning, but it's also unclear we need an explanation at all. And God may be a more "complex" hypothesis than the physical constants themselves.
My Week Without Cosmic Hope
(Photo by Tom Pumford on Unsplash)
philipgoff.substack.com
December 20, 2024 at 8:58 PM
Interesting to see @philipgoff.bsky.social go back and forth on the fine-tuning argument.
I think the multiverse definitely can't explain fine-tuning, but it's also unclear we need an explanation at all. And God may be a more "complex" hypothesis than the physical constants themselves.
I think the multiverse definitely can't explain fine-tuning, but it's also unclear we need an explanation at all. And God may be a more "complex" hypothesis than the physical constants themselves.
How do a neural network's final parameters depend on its initial ones?
In this new paper, we answer this question by analyzing the training Jacobian, the matrix of derivatives of the final parameters with respect to the initial parameters.
https://arxiv.org/abs/2412.07003
In this new paper, we answer this question by analyzing the training Jacobian, the matrix of derivatives of the final parameters with respect to the initial parameters.
https://arxiv.org/abs/2412.07003
December 11, 2024 at 8:30 PM
How do a neural network's final parameters depend on its initial ones?
In this new paper, we answer this question by analyzing the training Jacobian, the matrix of derivatives of the final parameters with respect to the initial parameters.
https://arxiv.org/abs/2412.07003
In this new paper, we answer this question by analyzing the training Jacobian, the matrix of derivatives of the final parameters with respect to the initial parameters.
https://arxiv.org/abs/2412.07003
Bombshell new paper on the simulation argument, multiverses, and cosmological fine-tuning:
"...self-locating credences are ‘subjective’ in the sense that they are not rationally constrained by anything at all, except possibly the requirement of probabilistic consistency."
arxiv.org/abs/2409.05259
"...self-locating credences are ‘subjective’ in the sense that they are not rationally constrained by anything at all, except possibly the requirement of probabilistic consistency."
arxiv.org/abs/2409.05259
Against Self-Location
I distinguish between pure self-locating credences and superficially self-locating credences, and argue that there is never any rationally compelling way to assign pure self-locating credences. I firs...
arxiv.org
December 10, 2024 at 8:36 PM
Bombshell new paper on the simulation argument, multiverses, and cosmological fine-tuning:
"...self-locating credences are ‘subjective’ in the sense that they are not rationally constrained by anything at all, except possibly the requirement of probabilistic consistency."
arxiv.org/abs/2409.05259
"...self-locating credences are ‘subjective’ in the sense that they are not rationally constrained by anything at all, except possibly the requirement of probabilistic consistency."
arxiv.org/abs/2409.05259
Death is just amnesia www.youtube.com/watch?v=L3MA...
Alan Watts - What happens after Death (Lecture)
YouTube video by theJourneyofPurpose TJOP
www.youtube.com
December 1, 2024 at 6:36 AM
Death is just amnesia www.youtube.com/watch?v=L3MA...
I'm trying out Bluesky, using this browser extension to crosspost https://github.com/59de44955ebd/twitter-to-bsky
My username is the obvious one.
My username is the obvious one.
GitHub - 59de44955ebd/twitter-to-bsky: Crosspost from Twitter/X to Bluesky and Mastodon directly in...
Crosspost from Twitter/X to Bluesky and Mastodon directly in the web browser - 59de44955ebd/twitter-to-bsky
github.com
November 25, 2024 at 9:49 PM
I'm trying out Bluesky, using this browser extension to crosspost https://github.com/59de44955ebd/twitter-to-bsky
My username is the obvious one.
My username is the obvious one.