as promised, phone-as-controller libraries for godot and for unity, MIT licensed! cloudflare tunnel integration so devices don't have to all be on the same network. pmc.splatterfacegames.com

We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can use these to index multimodal data with 9B, and query on device with 0.6B. This also enables you to search over PDF pages with no OCR. And scores 92.4% on MADQA, 64% on BrowseComp+. Weights available on @huggingface now.

RT @jcinjpn: My meal sharing tool became way easier to use on mobile. Check it out. mymf.app

Friendly reminder that Hermes was never built or intended to be exclusively for the "personal assistant" agent that can just read your emails and nothing else. I fully intend and have plainly stated many times that I always built hermes to be the most powerful AI Agent. "Normie" consumers can leverage that and we do what we can to make it an experience they can approach (the mobile app will be almost exclusively focused on consumer) - but they are not our only demographic. I want the scientists, the cybersecurity engineers, the developers, the knowledge workers, the creatives, and everyone else to be able to have an agent that they can leverage that is maximally useful to them too. Not just your mom. (She called btw you need to make your bed)

We shipped four things that were deemed good to great and some math proofs, but the vote is clear and the community demands a reset. I did calibrate it and it *seems* that the game is rigged in reset's favor, but such are the rules at the moment. Therefore ... the reset has been processed. Enjoy!

the privacy-first company joining forces with the privacy-last company

So I found you can instantly ~2x* your GitHub CI speed for free GH added parallel actions. But AI usually misses it since it's too new 😱 * Depends on what you're doing, just ask AI to benchmark github.blog/changelog/2026-0…

Allowing myself to drink sweet drinks while working has been the most profound performance enhancement in the past 5 years for me. For the past 2 weeks I've been outputting at +50%. Higher focus, longer. 1 Powerade at my desk per day. I am able to do 12 hour days the way I used to be able to when I was younger. I don't have any crash, I crashed much worse end of day when I was avoiding sugar. I am not sure why this is the case, it seems contrary to most of what I've read. Hypothesis 1: I burn a lot of energy working at a computer and easy fuel gets burnt off quickly, like with a runner. I was in a calorie deficit that was hurting my performance previously. Same reason chess players consume chocolate milk while playing. Hypothesis 2: I have diabetes? Any other ideas?

Two days. That's how long it took me to rebuild F-Zero X, my favourite N64 game as a kid. I played, Claude Code built, my workflows made the art, animations and vfx. Then I lost hours just racing it. Anyone can make something like this now. Play: project0.city/#383

this is ngl the kind of graphic my mother would make to try and get me to move back to perth

LMAO. Reporter tries the 'data center jobs are temporary' line on a Pennsylvania tradesman literally building one. His answer: “Every job in my field is temporary.”

In the early days of GTA1 development, the driving just wasn’t fun. Then Pat Kerr, who is handy with physics but wasn’t even on the team, dropped in some driving code that fixed it. He’s now published a playable demo using those same ideas. It’s remarkable how much it feels like GTA1—especially the handbrake (space). patkerr.co.uk/2d-vehicles/

Built a small image-search demo with Google's EmbeddingGemma 2 running locally on DGX Spark We indexed 300 photos across 30 animal categories, then tested with 20 separate photos kept out of the index. Each test photo becomes a 768-dimensional vector. We compare it against the indexed image vectors using cosine similarity and retrieve the 10 nearest matches. Animal labels are used only to check the results. Result: 165/200 retrieved images matched the query's animal category, 82.5% precision@10. Zebra, tiger, giant panda and polar bear scored 10/10. Horse and leopard were harder: 4/10 and 5/10.

Day-0 support for EmbeddingGemma 2 in llama.cpp huggingface.co/ggml-org/embe…

Ben Affleck reveals he writes Python, understands convolutional neural networks, worked extensively with GPUs, and used his celebrity status to get private looks at Google and OpenAI’s video models “I’ve always been kind of into computers since I was young. Then, when film started to move from analog film to digital, I became more interested in that aspect of it. The visual-effects workflow for many years has included machine learning, so I can write pretty shitty Python scripts and stuff like that. “With convolutional neural networks, which were the precursors to what the transformer can do, which is much more computation simultaneously, you would do things like look at what’s called a tensor. That’s the numerical translation of a visual image in numbers, like the batch number, the frame number and the red, green and blue values of each pixel in each frame. It’s just that simple. That numeric is called a tensor. “You’d use a convolutional neural network to identify patterns that reveal what’s called edge detection or feature extraction, which is identifying patterns well enough to know, this is where the window ledge is, so we can more easily take the green-screen image out and replace it with something. “That was familiar to me early on because, prior to Artists Equity, I had a small visual-effects company. I’ve worked with GPUs a lot too. The visual-effects guys said, ‘Hey, you should see. There are a couple: Google and this other company, OpenAI, are doing really interesting stuff with transformers in video.’ “I’ve learned that I can actually just call up and go, ‘Hey, it’s Ben Affleck. Can I come see what you’re doing?’ Sometimes people say yes, to my astonishment.”

Introducing EmbeddingGemma 2! 🚀 Our lightweight, multimodal embedding model maps text, code, images, video, and audio into a single, unified embedding space. Optimized for on-device use cases, it features: - 740M parameter form factor with modular encoders - Flexible dimension sizes (768dim-128dim) via Matryoshka Representation Learning (MRL) - 8K context window (4x larger than text-only EmbeddingGemma) - A commercially permissive Apache 2.0 license

Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding. • Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure. • Available to all via API today. Working with cybersecurity partners privately. Open weights release end of October.

Yesterday I got a bit roasted on X because I said my agent checks me in for my flights, so let me double down: it also helps me book basically every plane ticket. I just landed in India and they asked for one of those crazy health/immigration forms with passport info, where you’re staying, flight details, etc. I sent it to my agent, it filled everything out, great job, I went back to reading my book. A bunch of people replied: “I’m a competent adult, I know how to do this, I don’t need AI.” Which is totally fair. Do whatever works for you! I also know how to wash dishes and I love my dishwasher. I know how to write a letter, put it in an envelope and go to the post office, and yet I prefer email. I know how to do mental arithmetic and I still use a calculator. The point of technology is very rarely that humans are incapable of doing the thing. It’s that our time and attention are better spent somewhere else. Instead of spending 20 minutes fighting with a PDF, finding my passport number, hotel address and flight information in five different places, I can read my book. Instead of manually replying to three emails just to send my landlord some insurance information, an agent can handle it and I get another 20 minutes with my 18-month-old daughter, Josephine. I think people underestimate AI agents for two reasons. First, capitalism has this amazing tendency to take things that were once reserved for rich people and, through technology and scale, give them to everyone. Rich people have had executive assistants forever. Someone books their flights and restaurants, coordinates meetings, answers routine communications, fills out paperwork, reminds them what they forgot. AI is going to give some version of that to billions of people. Second, a huge amount of economic progress is simply removing friction. Coase would call a lot of this transaction costs. One form takes 15 minutes, one email takes 3 minutes, one reservation takes 10 minutes. None of these things individually feels revolutionary, but remove thousands of them over a lifetime and it compounds into something enormous. So yes, I am perfectly capable of checking myself into a flight but now I just don’t see why I should.

The serious answer to how Shazam worked is it took the peaks of a spectrogram of short clips of every song, find the peaks from the highest amplitude bits, hash it with the value being (time stamp, track id) and then the actual recognition is a hashtable lookup. We did this for a college CS project. The original paper is fantastic:

RT @nic_carter: I find these takes really confusing. you have a 150 IQ+ tireless genius living in your computer. it can use your browser…

just one more agent bro