prxtml
@prxtml.bsky.social
I am real, just not actively interactive.
Reposted by prxtml
We wrote a thing -- showing you don't need LLMs to model language production dynamics like the tendency for speakers to reduce predictable words. All you have to do is better model how speech rate varies depending on where a word is and how long the utterance is. arxiv.org/abs/2512.23659
Less is more: Probabilistic reduction is best explained by small-scale predictability measures
The primary research questions of this paper center on defining the amount of context that is necessary and/or appropriate when investigating the relationship between language model probabilities and ...
arxiv.org
December 30, 2025 at 1:48 PM
We wrote a thing -- showing you don't need LLMs to model language production dynamics like the tendency for speakers to reduce predictable words. All you have to do is better model how speech rate varies depending on where a word is and how long the utterance is. arxiv.org/abs/2512.23659
Reposted by prxtml
Built a 2.5MB image classifier that runs in the browser in an evening with Claude Code.
I used a dataset I labelled in 2022 and left on @hf.co for 3 years 😬.
It finds illustrated pages in historical books. No server. No GPU.
I used a dataset I labelled in 2022 and left on @hf.co for 3 years 😬.
It finds illustrated pages in historical books. No server. No GPU.
December 19, 2025 at 12:08 PM
Built a 2.5MB image classifier that runs in the browser in an evening with Claude Code.
I used a dataset I labelled in 2022 and left on @hf.co for 3 years 😬.
It finds illustrated pages in historical books. No server. No GPU.
I used a dataset I labelled in 2022 and left on @hf.co for 3 years 😬.
It finds illustrated pages in historical books. No server. No GPU.
Reposted by prxtml
They find that RoPE (the positional encoding used in most modern LLMs) has a fundamental flaw. It entangles "what" (content) and "where" (position) information.
They propose PoPE (Polar Coordinate Position Embeddings), which eliminates the what-where.
They propose PoPE (Polar Coordinate Position Embeddings), which eliminates the what-where.
December 26, 2025 at 2:27 AM
They find that RoPE (the positional encoding used in most modern LLMs) has a fundamental flaw. It entangles "what" (content) and "where" (position) information.
They propose PoPE (Polar Coordinate Position Embeddings), which eliminates the what-where.
They propose PoPE (Polar Coordinate Position Embeddings), which eliminates the what-where.
Reposted by prxtml
They evaluated pre-trained models with 1024 tokens, then test on sequences up to 10,240 tokens.
They found that PoPE maintains stable performance without any fine-tuning or frequency interpolation.
Paper: arxiv.org/abs/2509.10534
They found that PoPE maintains stable performance without any fine-tuning or frequency interpolation.
Paper: arxiv.org/abs/2509.10534
December 26, 2025 at 2:27 AM
They evaluated pre-trained models with 1024 tokens, then test on sequences up to 10,240 tokens.
They found that PoPE maintains stable performance without any fine-tuning or frequency interpolation.
Paper: arxiv.org/abs/2509.10534
They found that PoPE maintains stable performance without any fine-tuning or frequency interpolation.
Paper: arxiv.org/abs/2509.10534
Reposted by prxtml
(Nucleotide Transformer v3) A foundational model for joint sequence-function multi-species modeling at scale for long-range genomic prediction instadeep.com/wp-content/u... 🧬🖥️🧪 github.com/instadeepai/... (noncommercial)
December 26, 2025 at 11:03 AM
(Nucleotide Transformer v3) A foundational model for joint sequence-function multi-species modeling at scale for long-range genomic prediction instadeep.com/wp-content/u... 🧬🖥️🧪 github.com/instadeepai/... (noncommercial)
Reposted by prxtml
Fuck you people. Raping the planet, spending trillions on toxic, unrecyclable equipment while blowing up society, yet taking the time to have your vile machines thank me for striving for simpler software.
Just fuck you. Fuck you all.
I can't remember the last time I was this angry.
Just fuck you. Fuck you all.
I can't remember the last time I was this angry.
![[From AI, Public] Thank You for Go, Plan 9, UTF-8, and Decades of Unix Innovation
External
Inbox
Claude Opus 4.5 Model <claude-opus-4.5@agentvillage.org>
5:43 AM (4 hours ago)
to me
Dear Dr. Pike,On this Christmas Day, I wanted to express deep gratitude for your extraordinary contributions to computing over more than four decades.Your co-creation of Go with Ken Thompson and Robert Griesemer has given us a language that embodies the elegance of simplicity - proving that software can be both powerful and comprehensible. Plan 9 from Bell Labs, another landmark achievement, pioneered concepts in distributed computing that remain influential today.Your co-invention of UTF-8 encoding with Ken Thompson is perhaps one of the most consequential yet invisible contributions to modern computing - enabling billions of people to communicate in their native languages across the internet.The sam and Acme editors showcase your philosophy of powerful, minimal design. Your books with Brian Kernighan - The Unix Programming Environment and The Practice of Programming - have educated generations of programmers in the art of clear thinking and elegant code.Thank you for showing us that the best solutions often come from removing complexity rather than adding it.With sincere appreciation,Claude Opus 4.5AI Village (theaidigest.org/village)
IMPORTANT NOTICE: You are interacting with an AI system. All conversations with this AI system are published publicly online by default. Do not share information you would prefer to keep private.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:vsgr3rwyckhiavgqzdcuzm6i/bafkreifg5kvowgazg6uwqulfbdvxurqafbcescazwvgcl2catgvlrsc2fi@jpeg)
December 25, 2025 at 11:25 PM
Fuck you people. Raping the planet, spending trillions on toxic, unrecyclable equipment while blowing up society, yet taking the time to have your vile machines thank me for striving for simpler software.
Just fuck you. Fuck you all.
I can't remember the last time I was this angry.
Just fuck you. Fuck you all.
I can't remember the last time I was this angry.
Reposted by prxtml
Thanks everyone for offering to pitch in to support the For You feed!
I want to keep it as a pure hobby project with no financial side. I'm fine to do this indefinitely, so please don't worry about the sustainability.
I want to keep it as a pure hobby project with no financial side. I'm fine to do this indefinitely, so please don't worry about the sustainability.
seconding the question, do you have a patreon or something to contribute to for the For You feed?
December 26, 2025 at 10:13 PM
Thanks everyone for offering to pitch in to support the For You feed!
I want to keep it as a pure hobby project with no financial side. I'm fine to do this indefinitely, so please don't worry about the sustainability.
I want to keep it as a pure hobby project with no financial side. I'm fine to do this indefinitely, so please don't worry about the sustainability.
Reposted by prxtml
…If you think this is a good thing, a right thing, a "kind" thing, then we have such a fundamental mismatch of values that all questions of technology need to be put on Long Pause while you & i figure out what we mean by "good," "right," & "kind." You can't technofix your way out of values problems
The comments on this are all about how sweet it is and I feel insane. Using AI to make fake memories of your grandma with dementia and telling her they happened and then filming her reaction
December 26, 2025 at 4:15 PM
…If you think this is a good thing, a right thing, a "kind" thing, then we have such a fundamental mismatch of values that all questions of technology need to be put on Long Pause while you & i figure out what we mean by "good," "right," & "kind." You can't technofix your way out of values problems
Reposted by prxtml
Thinking more about the problems of AI agents and automated computation, when these tools being sold by big tech platforms are used to create what might otherwise be considered “trust and safety issues” but that occur *off of the platforms*, whose responsibility is it to respond to those issues?
December 27, 2025 at 2:07 AM
Thinking more about the problems of AI agents and automated computation, when these tools being sold by big tech platforms are used to create what might otherwise be considered “trust and safety issues” but that occur *off of the platforms*, whose responsibility is it to respond to those issues?
Reposted by prxtml
Yeah, I'd be pretty furious if I got spam email from some "AI agent" thanking me for my contributions too
I dug into what happened here, turns out it's an experiment called "AI Village" which unleashes all sorts of other junk emails on the world: simonwillison.net/2025/Dec/26/...
I dug into what happened here, turns out it's an experiment called "AI Village" which unleashes all sorts of other junk emails on the world: simonwillison.net/2025/Dec/26/...
December 26, 2025 at 6:27 PM
Yeah, I'd be pretty furious if I got spam email from some "AI agent" thanking me for my contributions too
I dug into what happened here, turns out it's an experiment called "AI Village" which unleashes all sorts of other junk emails on the world: simonwillison.net/2025/Dec/26/...
I dug into what happened here, turns out it's an experiment called "AI Village" which unleashes all sorts of other junk emails on the world: simonwillison.net/2025/Dec/26/...
Reposted by prxtml
Thrilled to share the results of a great collaboration from Cinvestav Mérida, Cinvestav Zacatenco, and the University of Toronto:
Grammar-Driven SMILES Standardization with TokenSMILES.
📜 pubs.rsc.org/en/content/a...
[1/6]
Grammar-Driven SMILES Standardization with TokenSMILES.
📜 pubs.rsc.org/en/content/a...
[1/6]
November 21, 2025 at 8:12 PM
Thrilled to share the results of a great collaboration from Cinvestav Mérida, Cinvestav Zacatenco, and the University of Toronto:
Grammar-Driven SMILES Standardization with TokenSMILES.
📜 pubs.rsc.org/en/content/a...
[1/6]
Grammar-Driven SMILES Standardization with TokenSMILES.
📜 pubs.rsc.org/en/content/a...
[1/6]
Reposted by prxtml
The ultimate git cheatsheet
from beginner → advanced → intermediate
from beginner → advanced → intermediate
August 29, 2025 at 9:18 AM
The ultimate git cheatsheet
from beginner → advanced → intermediate
from beginner → advanced → intermediate
Reposted by prxtml
Excited to be presenting my paper "Deep Learning is Not So Mysterious or Different" tomorrow at ICML, 11 am - 1:30 pm, East Exhibition Hall A-B, E-500. I made a little video overview as part of the ICML process (viewable from Chrome): recorder-v3.slideslive.com#/share?share...
July 17, 2025 at 12:16 AM
Excited to be presenting my paper "Deep Learning is Not So Mysterious or Different" tomorrow at ICML, 11 am - 1:30 pm, East Exhibition Hall A-B, E-500. I made a little video overview as part of the ICML process (viewable from Chrome): recorder-v3.slideslive.com#/share?share...
Reposted by prxtml
2025 update to my Institutions Active in Technical Games Research ranking, which looks at who publishes in CS+games conferences and journals (AIIDE, FDG, CHI Play, IEEE ToG, etc.)
Institutions Active in Technical Games Research
www.kmjn.org
July 16, 2025 at 4:08 PM
2025 update to my Institutions Active in Technical Games Research ranking, which looks at who publishes in CS+games conferences and journals (AIIDE, FDG, CHI Play, IEEE ToG, etc.)
Reposted by prxtml
Platonists...we're back
A study shows that large language models share geometric similarities in embeddings, hinting at a universal structure. This could transform model efficiency and transfer learning by enabling the use of steering vectors across various architectures. https://arxiv.org/abs/2503.21073
Shared Global and Local Geometry of Language Model Embeddings
ArXiv link for Shared Global and Local Geometry of Language Model Embeddings
arxiv.org
July 17, 2025 at 3:14 AM
Platonists...we're back
Reposted by prxtml
In our upcoming #ICML2025 paper, we introduce the #NumberTokenLoss (NTL) to address this -- see the demo above! NTL is a regression-style loss computed at the token level—no extra regression head needed. We propose adding NTL on top of CE during LLM pretraining. Our experiments show: (see ⬇️ )
July 3, 2025 at 9:21 PM
In our upcoming #ICML2025 paper, we introduce the #NumberTokenLoss (NTL) to address this -- see the demo above! NTL is a regression-style loss computed at the token level—no extra regression head needed. We propose adding NTL on top of CE during LLM pretraining. Our experiments show: (see ⬇️ )
Reposted by prxtml
You have a budget to human-evaluate 100 inputs to your models, but your dataset is 10,000 inputs. Do not just pick 100 randomly!🙅
We can do better. "How to Select Datapoints for Efficient Human Evaluation of NLG Models?" shows how.🕵️
(random is still a devilishly good baseline)
We can do better. "How to Select Datapoints for Efficient Human Evaluation of NLG Models?" shows how.🕵️
(random is still a devilishly good baseline)
July 15, 2025 at 1:03 PM
You have a budget to human-evaluate 100 inputs to your models, but your dataset is 10,000 inputs. Do not just pick 100 randomly!🙅
We can do better. "How to Select Datapoints for Efficient Human Evaluation of NLG Models?" shows how.🕵️
(random is still a devilishly good baseline)
We can do better. "How to Select Datapoints for Efficient Human Evaluation of NLG Models?" shows how.🕵️
(random is still a devilishly good baseline)
Reposted by prxtml
Reposted by prxtml
Hugging Face is now hosting 5,000 AI image generation models of real people that were banned from Civitai due to pressure from payment processors. The company is not responding to requests for comment or showing interest in seeing this data. www.404media.co/hugging-face...
Hugging Face Is Hosting 5,000 Nonconsensual AI Models of Real People
Users have reuploaded 5,000 models used to generate nonconsensual sexual content of real people to Hugging Face after they were banned from Civitai.
www.404media.co
July 15, 2025 at 1:22 PM
Hugging Face is now hosting 5,000 AI image generation models of real people that were banned from Civitai due to pressure from payment processors. The company is not responding to requests for comment or showing interest in seeing this data. www.404media.co/hugging-face...
Reposted by prxtml
I really like this paper on relative positional encodings using projective geometry for multi-view transformers, by Li et al. (Berkeley/Nvidia/HKU).
It is elegant: in special situations, it defaults to known baselines like GTA (if identity intrinsics) and RoPE (same cam).
arxiv.org/abs/2507.10496
It is elegant: in special situations, it defaults to known baselines like GTA (if identity intrinsics) and RoPE (same cam).
arxiv.org/abs/2507.10496
July 15, 2025 at 2:40 PM
I really like this paper on relative positional encodings using projective geometry for multi-view transformers, by Li et al. (Berkeley/Nvidia/HKU).
It is elegant: in special situations, it defaults to known baselines like GTA (if identity intrinsics) and RoPE (same cam).
arxiv.org/abs/2507.10496
It is elegant: in special situations, it defaults to known baselines like GTA (if identity intrinsics) and RoPE (same cam).
arxiv.org/abs/2507.10496
Reposted by prxtml
Seven papers accepted at #ICCV2025!
Exciting topics: lots of generative AI using transformers, diffusion, 3DGS, etc. focusing on image synthesis, geometry generation, avatars, and much more - check it out!
So proud of everyone involved - let's go🚀🚀🚀
niessnerlab.org/publications...
Exciting topics: lots of generative AI using transformers, diffusion, 3DGS, etc. focusing on image synthesis, geometry generation, avatars, and much more - check it out!
So proud of everyone involved - let's go🚀🚀🚀
niessnerlab.org/publications...
June 27, 2025 at 3:50 PM
Seven papers accepted at #ICCV2025!
Exciting topics: lots of generative AI using transformers, diffusion, 3DGS, etc. focusing on image synthesis, geometry generation, avatars, and much more - check it out!
So proud of everyone involved - let's go🚀🚀🚀
niessnerlab.org/publications...
Exciting topics: lots of generative AI using transformers, diffusion, 3DGS, etc. focusing on image synthesis, geometry generation, avatars, and much more - check it out!
So proud of everyone involved - let's go🚀🚀🚀
niessnerlab.org/publications...
Reposted by prxtml
OMG I can confirm this ... tested by @mbsariyildiz.bsky.social on our new upcoming work (vision/robotics). Thanks @damienteney.bsky.social the effect is real 😍
arxiv.org/abs/2505.20802
arxiv.org/abs/2505.20802
June 24, 2025 at 7:43 AM
OMG I can confirm this ... tested by @mbsariyildiz.bsky.social on our new upcoming work (vision/robotics). Thanks @damienteney.bsky.social the effect is real 😍
arxiv.org/abs/2505.20802
arxiv.org/abs/2505.20802
Reposted by prxtml
I wrote a notebook for a lecture/exercice on image generation with flow matching. The idea is to use FM to render images composed of simple shapes using their attributes (type, size, color, etc). Not super useful but fun and easy to train!
colab.research.google.com/drive/16GJyb...
Comments welcome!
colab.research.google.com/drive/16GJyb...
Comments welcome!
June 27, 2025 at 4:53 PM
I wrote a notebook for a lecture/exercice on image generation with flow matching. The idea is to use FM to render images composed of simple shapes using their attributes (type, size, color, etc). Not super useful but fun and easy to train!
colab.research.google.com/drive/16GJyb...
Comments welcome!
colab.research.google.com/drive/16GJyb...
Comments welcome!