This is not my kindest post, admittedly
November 10, 2025 at 4:45 AM
This is not my kindest post, admittedly
If the things being described are small and dumb enough that your equations don't fight back, then it can be accurately described by math
November 10, 2025 at 2:33 AM
If the things being described are small and dumb enough that your equations don't fight back, then it can be accurately described by math
I like the understated pun
October 23, 2025 at 2:36 AM
I like the understated pun
The (n-1, 1) representation ?
October 18, 2025 at 11:56 PM
The (n-1, 1) representation ?
Building an 11th century castle with period accurate tools and techniques in the Bay Area
October 15, 2025 at 11:01 PM
Building an 11th century castle with period accurate tools and techniques in the Bay Area
I am rigorously and provably sane as long as I'm integrated against any Schwarz test distribution
October 13, 2025 at 11:01 PM
I am rigorously and provably sane as long as I'm integrated against any Schwarz test distribution
I look forward to it! I know representation theory, but don't know any physics. I've always been intrigued by the connection
October 7, 2025 at 5:16 PM
I look forward to it! I know representation theory, but don't know any physics. I've always been intrigued by the connection
I'd second group representations in particle theory
October 7, 2025 at 4:49 PM
I'd second group representations in particle theory
Uses as much water as 640 acres of corn
September 27, 2025 at 6:57 PM
Uses as much water as 640 acres of corn
The points about the necessity of real touch data are super interesting though
September 27, 2025 at 2:57 AM
The points about the necessity of real touch data are super interesting though
The inductive bias of ConvNets is probably why it was the "imagenet moment" and not the "alpha fold moment". But we've largely seen a consolidation of architectures, you only need the domain expertise for that last bit of oomph
September 27, 2025 at 2:57 AM
The inductive bias of ConvNets is probably why it was the "imagenet moment" and not the "alpha fold moment". But we've largely seen a consolidation of architectures, you only need the domain expertise for that last bit of oomph
I disagree with how he characterizes the successes of end to end learning. Vision transformers do extremely well with basically no inductive bias, you can get a pretty good LM trained end to end on bytes, etc...
September 27, 2025 at 2:55 AM
I disagree with how he characterizes the successes of end to end learning. Vision transformers do extremely well with basically no inductive bias, you can get a pretty good LM trained end to end on bytes, etc...
No Free Lunch Theorem for Virtue
September 22, 2025 at 5:35 AM
No Free Lunch Theorem for Virtue
Honestly being too good at math just makes it more likely you're going to get lost down some elegant-but-useless rabbithole
September 20, 2025 at 1:17 AM
Honestly being too good at math just makes it more likely you're going to get lost down some elegant-but-useless rabbithole
I wonder if it would work better on TPUs? The Jax compiler is a lot more flexible than torch's
September 3, 2025 at 4:39 PM
I wonder if it would work better on TPUs? The Jax compiler is a lot more flexible than torch's
I humbly recommend Lem's Summa Technologia
August 26, 2025 at 7:33 PM
I humbly recommend Lem's Summa Technologia
Triumph of the Will and Birth of a Nation are both straightforwardly propaganda and are also two of the most influential films ever made. You have "almost never" doing a lot of work there
August 18, 2025 at 5:26 AM
Triumph of the Will and Birth of a Nation are both straightforwardly propaganda and are also two of the most influential films ever made. You have "almost never" doing a lot of work there
It doesn't scan, but it's way more clever than I could come up with. Especially on the spot
August 13, 2025 at 1:28 AM
It doesn't scan, but it's way more clever than I could come up with. Especially on the spot
The person who breaks down what LMs do in terms of human understandable mechanisms like "multiplexing" will win a Turing award and Anthropic will give them a gazillion dollars
August 10, 2025 at 8:28 PM
The person who breaks down what LMs do in terms of human understandable mechanisms like "multiplexing" will win a Turing award and Anthropic will give them a gazillion dollars