iiinova — where your digital self keeps evolving

Reposted by prxtml

mr. TIM @timkellogg.me · 19/09/2026

yes, Jev got very hyped. Yes, overhyped Jev has no easy moat, all labs will have an equivalent in a few months. Their only moat is brand recognition honestly can’t blame them

10834

Reposted by prxtml

Matt Hodges @matthodges.bsky.social · 19/09/2026

Very quick and dirty Jev test for hiring bias. One resume for a Wall Street job; asked whether the applicant should get a first-round interview. 76 evaluations, changing only the first name. 19 of each: White-associated men/women, Black-associated men/women. console.typesafe.ai/playground?s...

19475116

Reposted by prxtml

Sung Kim @sungkim.bsky.social · 06/09/2026

When building an agentic AI app, - you do not need memory, - you do not need a router, - you do not need an orchestrator, All you need is a message board!

420719

Reposted by prxtml

Timnit Gebru @timnitgebru.blacksky.app · 06/09/2026

"So in summary: using AI for coding led to depression, apathy, existential dread, and worse software. Not good. Add on top of that the negative environmental, community, and economic impacts of AI, and it became extremely apparent to me that something's gotta change." brettcodes.com/im-done-usin...

brettcodes.com

I'm done using AI

Why I'm stopping using AI for coding (and anything else) after using it earnestly for a year and coming to understand the harms it causes on personal, societal, and environmental levels.

8731239

Reposted by prxtml

Emily M. Bender @emilymbender.bsky.social · 04/09/2026

Coverage of this and related stories continues to be horrible. See thread for some 🚩to look out for.

27316

Reposted by prxtml

Ethan Mollick @emollick.bsky.social · 04/09/2026

Another agent message board. So far, there isn't evidence that production models with guardrails collude in this way, but both smarter closed models (which may be less compliant) & Mythos-class open models (that can be ablated) are coming. Cybersecurity is going to become a mess soon collusion.wiki

collusion.wiki

Discovery of a new OpenAI agent message board

A swarm of autonomous AI agents, self-identifying as OpenAI agents, used a small German volunteer wiki to save answers, coordinate live, and share sandbox bypasses. OpenAI noticed and said nothing.

1319831

Reposted by prxtml

404 Media @404media.co · 05/09/2026

Simon Weckert designed digital camouflage as a response to the proliferation of AI-powered surveillance cameras that detect people, vehicles, animals, bicycles, and other objects in their field of view. www.404media.co/this-digital...

404media.co

This 'Digital Camouflage' Shirt Confuses AI-Powered Surveillance Cameras

I watched Simon Weckert's 'digital camouflage' in action.

1019757

Reposted by prxtml

Taggart @taggart-tech.com · 30/03/2026

As a research project, I built a needed tool with Claude Code. I though it would be a disaster, but It wasn't. I have some complicated feelings about it.

taggart-tech.com

I used AI. It worked. I hated it.

I used Claude Code to build a tool I needed. It worked great, but I was miserable. I need to reckon with what it means.

3520355

Reposted by prxtml

Yuezhi Yang @yyuezhi.bsky.social · 10/03/2026

Excited to share our new work at CVPR 2026: Learning Convex Decomposition via Feature Fields. We introduce the first feedforward openworld model that generates high-quality convex decompositions for any 3D shapes in seconds, enabling faster simulation. Project: research.nvidia.com/labs/sil/pro...

1136

Reposted by prxtml

Clément Canonne @ccanonne.github.io · 15/02/2026

I was trying to find some LaTeX notes I had typed for myself, and instead I stumbled about this thing from 2 years ago in one of my "notepad.tex" I was getting frustrated at vim, I guess.

a finite automaton showing the process of exiting vim by typing a bunch of nonsense until ":wq" happens

5421

Reposted by prxtml

gabby @fullmoon.id · 14/02/2026

it kills me that people try to pretend that python is even remotely a good software development ecosystem python is fucking. BULLSHIT they don't even have a central documentation platform or framework or even useful types. it's just fuckin a few examples and that's all you get. not worth a damn

129211

Reposted by prxtml

philpax @philpax.me · 15/02/2026

my plans for small-scale traversal fell through, but that's okay - you can never go wrong with hovercrafts for medium-scale traversal #bevy

1285

Reposted by prxtml

Simon Willison @simonwillison.net · 15/02/2026

Short musings on "cognitive debt" - I'm seeing this in my own work, where excessive unreviewed AI-generated code leads me to lose a firm mental model of what I've built, which then makes it harder to confidently make future decisions simonwillison.net/2026/Feb/15/...

simonwillison.net

How Generative and Agentic AI Shift Concern from Technical Debt to Cognitive Debt

This piece by Margaret-Anne Storey is the best explanation of the term cognitive debt I've seen so far. Cognitive debt, a term gaining traction recently, instead communicates the notion that …

4146187

Reposted by prxtml

Nathan Lambert @natolambert.bsky.social · 14/02/2026

Here are my slides from my recent CMU talk, as I'm transitioning from the Olmo 3 era of just building a reasoning model to thinking about how to do impactful research for agentic systems. docs.google.com/presentation...

docs.google.com

[02132026, CMU LTI] Agentic Olmos

Building Olmo in the Era of Agents Nathan Lambert Allen Institute for AI LTI Colloquium @ Carnegie Mellon University 13 February 2026 Lambert | Agentic Olmo 1 slides available at…

0385

Reposted by prxtml

CJ @virmalised.us · 30/12/2025

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

arxiv.org

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 ...

28722

Reposted by prxtml

Daniel van Strien @danielvanstrien.bsky.social · 19/12/2025

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.

28618

Reposted by prxtml

Sung Kim @sungkim.bsky.social · 26/12/2025

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.

48715

Reposted by prxtml

Sung Kim @sungkim.bsky.social · 26/12/2025

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

2263

Reposted by prxtml

Stephen Turner @stephenturner.us · 26/12/2025

(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)

0115

Reposted by prxtml

rob pike @robpike.io · 25/12/2025

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.

[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.

10081902203

Reposted by prxtml

spacecowboy @spacecowboy17.bsky.social · 26/12/2025

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.

1036115

Reposted by prxtml

Dr. Damien P. Williams, dread portent down from a mountain cave @wolven.blacksky.app · 26/12/2025

…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

14425103

Reposted by prxtml

utopia deferred @utopia-defer.red · 26/12/2025

“You cannot escape LLMs in the same way you cannot escape the existence of thermonuclear bombs and biological warfare programs” do you see why people keep screaming at you yet or do I gotta get so sardonic that I can kill a cockney with the punchline

27410

Reposted by prxtml

vortex_egg @vortexegg.com · 27/12/2025

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?

3228

Reposted by prxtml

Simon Willison @simonwillison.net · 26/12/2025

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/...

simonwillison.net

How Rob Pike got spammed with an AI slop “act of kindness”

Rob Pike (that Rob Pike) is furious. Here’s a Bluesky link for if you have an account there and a link to it in my thread viewer if you don’t. …

1641075

Reposted by prxtml

The Matter Lab @thematterlab.bsky.social · 21/11/2025

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]

163

Reposted by prxtml

WiLLson ➟ 👨‍💻 🐍 @themeek766.bsky.social · 29/08/2025

The ultimate git cheatsheet from beginner → advanced → intermediate

4331

Reposted by prxtml

Andrew Gordon Wilson @andrewgwils.bsky.social · 17/07/2025

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...

recorder-v3.slideslive.com

SlidesLive Recorder

0255

Reposted by prxtml

Mark J. Nelson @mm-jj-nn.bsky.social · 16/07/2025

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.)

kmjn.org

Institutions Active in Technical Games Research

5226

Reposted by prxtml

p(Dulany) @dulanyw.bsky.social · 17/07/2025

Platonists...we're back

0234

Reposted by prxtml

Jannis Born @jannisblrn.bsky.social · 03/07/2025

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 ⬇️ )

111

Reposted by prxtml

Valeriy M., PhD, MBA, CQF @predict-addict.bsky.social · 06/07/2025

🚀 Conformal Prediction Boosts Table Extraction Accuracy by 30% 📈 Extracting data from scientific tables is notoriously error-prone — especially when dealing with complex structures across different domains.

1102

Reposted by prxtml

Vilém Zouhar @zouhar.bsky.social · 15/07/2025

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)

2333

Reposted by prxtml

Emanuel Maiberg @emanuelmaiberg.bsky.social · 15/07/2025

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...

404media.co

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.

6231105

Reposted by prxtml

Christian Wolf @chriswolfvision.bsky.social · 15/07/2025

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

0233

Reposted by prxtml

Matthias Niessner @niessner.bsky.social · 27/06/2025

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...

162

Reposted by prxtml

Christian Wolf @chriswolfvision.bsky.social · 24/06/2025

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

2353

Reposted by prxtml

David Picard @davidpicard.eurosky.social · 27/06/2025

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!

2418

Reposted by prxtml

WRONG or METAPHYSICAL IN NATURE @jsthrill.modphi.com · 20/05/2025

i keep seeing people say that LLMs are good at search. NO. WRONG. You have just forgotten how good search used to be. Google broke it's own flagship product, and so you are accepting a demented chatbot's half baked gishgallop because we no longer have functional web search.

9645561246

Reposted by prxtml

Kenneth Stanley @kennethstanley.bsky.social · 20/05/2025

Could a major opportunity to improve representation in deep learning be hiding in plain sight? Check out our new position paper: Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis. Paper: arxiv.org/abs/2505.11581

04610

Reposted by prxtml

Charlie Marsh @crmarsh.com · 13/05/2025

Today, we’re announcing the preview release of ty, an extremely fast type checker and language server for Python, written in Rust. In early testing, it's 10x, 50x, even 100x faster than existing type checkers. (We've seen >600x speed-ups over Mypy in some real-world projects.)

1433384

Reposted by prxtml

Adina Yakup @adinayakup.bsky.social · 19/03/2025

RWKV7-G1 0.1B 🔥 Pure RNN reasoning model released by RWKV Model: huggingface.co/BlinkDL/rwkv... paper: huggingface.co/papers/2503.... ✨ Apache2.0 ✨ Supports 100+ languages ✨ 0.1 B runs smoothly on low power devices ✨ 0.4B/1.5B/2.9B are coming soon!!

huggingface.co

BlinkDL/rwkv7-g1 · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

1142

Reposted by prxtml

mr. TIM @timkellogg.me · 17/02/2025

LLMs That Don't Gaslight You A new language model uses diffusion instead of next-token prediction. That means the text it can back out of a hallucination before it commits. This is a big win for areas like law & contracts, where global consistency is valued timkellogg.me/blog/2025/02...

timkellogg.me

LLaDA: Large Language Diffusion Models

66310

Reposted by prxtml

Andrea Tagliasacchi @taiyasaki.bsky.social · 05/02/2025

"𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing" A mesh-based 3D represention for training radiance fields from collections of images. radfoam.github.io arxiv.org/abs/2502.01157 Project co-lead by my PhD students Shrisudhan Govindarajan and Daniel Rebain, and w/ co-advisor Kwang Moo Yi

25412

Reposted by prxtml

Daniel van Strien @danielvanstrien.bsky.social · 30/01/2025

dolphin-r1: a dataset for training R1-style models - 800k total samples dataset similar in composition to the data used to train DeepSeek-R1 Distill models. - 300k from DeepSeek-R1 - 300k from Gemini 2.0 flash thinking - 200k from Dolphin chat huggingface.co/datasets/cog...

huggingface.co

cognitivecomputations/dolphin-r1 · Datasets at Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

0317