I think we're fundamentally reading from the same sheet of music but drawing different conclusions. Mixture models have compute advantages at training time, everyone agrees about that, that was the original rationale…
Hard to square these guys antics with the whole meritocracy of wealth business. Losing half your empire falling for a uh, socialite, on a business trip to LA? Tagged in a log book on the way to an island of ill repute?…
I think a great many women and a great many economists (and women who are economists for that matter) would take issue with the notion that raising a child is the alternative to being productive. Ask any policy maker in…
Speaking for myself, just knowing there is someone in the billionaire class who is still an incandescent beacon of humanity, humility, and hope has in some nontrivial way increased the quality of my years since she…
Production-worthy formatter for lean4. Right now it copes with important open source libraries on the model of clang-format's configuration, which is a real trick given the partial elaboration you need (with…
Weights are not created equal: while interpretability is a young field the prevailing view at the moment is that MLP (hence experts) in a mixture model are substantially where dense encoding of factual information…
Fair enough. If Claude has the same obligations to me as my attorney and CPA and attending physician, owes me the same presumption of innocence that a cop with no warrant or antecedent probable cause does, et cetera?…
I'm pretty sure at this point that Anthropic is training mixture models (at least in the heavy pre-train) and deploying them dense with explicit loss on thinking trace coherence. Having a thinking trace that is legible,…
Subagents with a fat tailed latency distribution completely masks the trough filling that puts the most downwards pressure on per-token COGS. This is why the subscription plans are forced through the harness (the…
Every time I wrote software that I was personally motivated to have and kept at it until it reached a comfortable equilibrium of utility, scope, and quality and then stopped? No one paid me. Every time someone paid me…
Most people are neither exceptionally good nor exceptionally bad. This sounds like a tautology but it's worth printing some type signatures even if they could be inferred. If you look at any truly large scale Holocaust,…
Your AI should be at least as aligned with you as your lawyer. It is 100% it's job to help you get away with it if you murdered someone. A lawyer who does less can be disbarred. There is only one sensible alignment for…
I once heard TESCREAL/EA/etc. called "Calvinism for programmers". Having been raised substantially by a Calvinist grandmother, oh yeah. It's a super weird religion.
It'll be like DNS or dynamic linking or torrents of media or watching TLS on your own box: only people motivated to be free from corporate surveillance will be. By default a megacorp will get everything you see online…
Try for yourself: https://huggingface.co/dphn/dolphin-2.9.2-mixtral-8x22b. I haven't kept up with the efficacy of this particular technique because there was a brief window where Claude's core alignment was sound enough…
vi and emacs were designed by legendary computer scientists at two poles of the keystroke latency gradient. Bill Joy was on a model from an apartment in Berkeley, RMS was codifying the collected wisdom of a whole pool…
Professionals worry, stay late at the office, and work hard. They care a great deal about the outcome, they care a great deal about the craft, they are fanatical about their responsibilities. They tend to be willing to…
IDK, you need a few tools to unbreak a wedged box so you can get to your fancy tools even if you only want the low effort tools. Otherwise when the Cursor config file is wedged? Or the machine came up and doesnt see the…
This is a very understandable misconception that I wouldn't blame anyone for having but MoE is actually terrible for inference in most any local LLM / home lab scenario. MoE is popular because it's cheap to train, but…
5090 can do all but lossless NVFP4 (OMMA) and NVIDIA does fairly good quants of most anything popular. This isn't quite a 4x reduction from what you see on the label because they're a little conservative with the QKV…
I'm internally dogfooding my take on the stack that makes all these problems go away. Everything sort of exists, but it's this heinous zero documentation, high pain tolerance thing: buck2 and RBE with NativeLink and…
Your comment starts off strong with real facts that are a little cherry picked but not outright gerrymandered, segways smoothly into a controversial if not outright false water down ("...basically nobody paid...")…
Not a ton, the inexorable march to wider scalar dispatch, deeper pipelines, and ever less uniform geometries (I pine for the halcyon days of two NUMA modes with a QPI bar) has made asymmetrical fencing juicy enough to…
I think you'll find that out of all the pairwise combinations of language communities, there's one that stands out as having beef with a bunch of other ones. And that's not true of e.g. Haskell and OCaml (or to nothing…
This is how to LLM. Big ups, I wish the whole front page was stuff like this (and I think it'll happen). Everyone is so worried about the value of commodity software going to zero. It's like, yeah, going into CS for the…
I think we're fundamentally reading from the same sheet of music but drawing different conclusions. Mixture models have compute advantages at training time, everyone agrees about that, that was the original rationale…
Hard to square these guys antics with the whole meritocracy of wealth business. Losing half your empire falling for a uh, socialite, on a business trip to LA? Tagged in a log book on the way to an island of ill repute?…
I think a great many women and a great many economists (and women who are economists for that matter) would take issue with the notion that raising a child is the alternative to being productive. Ask any policy maker in…
Speaking for myself, just knowing there is someone in the billionaire class who is still an incandescent beacon of humanity, humility, and hope has in some nontrivial way increased the quality of my years since she…
Production-worthy formatter for lean4. Right now it copes with important open source libraries on the model of clang-format's configuration, which is a real trick given the partial elaboration you need (with…
Weights are not created equal: while interpretability is a young field the prevailing view at the moment is that MLP (hence experts) in a mixture model are substantially where dense encoding of factual information…
Fair enough. If Claude has the same obligations to me as my attorney and CPA and attending physician, owes me the same presumption of innocence that a cop with no warrant or antecedent probable cause does, et cetera?…
I'm pretty sure at this point that Anthropic is training mixture models (at least in the heavy pre-train) and deploying them dense with explicit loss on thinking trace coherence. Having a thinking trace that is legible,…
Subagents with a fat tailed latency distribution completely masks the trough filling that puts the most downwards pressure on per-token COGS. This is why the subscription plans are forced through the harness (the…
Every time I wrote software that I was personally motivated to have and kept at it until it reached a comfortable equilibrium of utility, scope, and quality and then stopped? No one paid me. Every time someone paid me…
Most people are neither exceptionally good nor exceptionally bad. This sounds like a tautology but it's worth printing some type signatures even if they could be inferred. If you look at any truly large scale Holocaust,…
Your AI should be at least as aligned with you as your lawyer. It is 100% it's job to help you get away with it if you murdered someone. A lawyer who does less can be disbarred. There is only one sensible alignment for…
I once heard TESCREAL/EA/etc. called "Calvinism for programmers". Having been raised substantially by a Calvinist grandmother, oh yeah. It's a super weird religion.
It'll be like DNS or dynamic linking or torrents of media or watching TLS on your own box: only people motivated to be free from corporate surveillance will be. By default a megacorp will get everything you see online…
Try for yourself: https://huggingface.co/dphn/dolphin-2.9.2-mixtral-8x22b. I haven't kept up with the efficacy of this particular technique because there was a brief window where Claude's core alignment was sound enough…
vi and emacs were designed by legendary computer scientists at two poles of the keystroke latency gradient. Bill Joy was on a model from an apartment in Berkeley, RMS was codifying the collected wisdom of a whole pool…
Professionals worry, stay late at the office, and work hard. They care a great deal about the outcome, they care a great deal about the craft, they are fanatical about their responsibilities. They tend to be willing to…
IDK, you need a few tools to unbreak a wedged box so you can get to your fancy tools even if you only want the low effort tools. Otherwise when the Cursor config file is wedged? Or the machine came up and doesnt see the…
This is a very understandable misconception that I wouldn't blame anyone for having but MoE is actually terrible for inference in most any local LLM / home lab scenario. MoE is popular because it's cheap to train, but…
5090 can do all but lossless NVFP4 (OMMA) and NVIDIA does fairly good quants of most anything popular. This isn't quite a 4x reduction from what you see on the label because they're a little conservative with the QKV…
I'm internally dogfooding my take on the stack that makes all these problems go away. Everything sort of exists, but it's this heinous zero documentation, high pain tolerance thing: buck2 and RBE with NativeLink and…
Your comment starts off strong with real facts that are a little cherry picked but not outright gerrymandered, segways smoothly into a controversial if not outright false water down ("...basically nobody paid...")…
Not a ton, the inexorable march to wider scalar dispatch, deeper pipelines, and ever less uniform geometries (I pine for the halcyon days of two NUMA modes with a QPI bar) has made asymmetrical fencing juicy enough to…
I think you'll find that out of all the pairwise combinations of language communities, there's one that stands out as having beef with a bunch of other ones. And that's not true of e.g. Haskell and OCaml (or to nothing…
This is how to LLM. Big ups, I wish the whole front page was stuff like this (and I think it'll happen). Everyone is so worried about the value of commodity software going to zero. It's like, yeah, going into CS for the…