All entries

Recently, Datalab released OmniExtractBench, a benchmark that combines several benchmarks (our own ExtractBench, LongExtractBench, other vendors) to measure structured document quality. The benchmark

Since OpenAI retired SWE-bench Verified in February (every frontier model tested could reproduce reference fixes for some tasks; underspecified tests rewarded knowing the intended fix), I've been tryi

Sharing my ML learning repo — NumPy to Transformers, 5 months, daily commits, all notebooks public. Covers the full stack: - Classical ML (scikit-learn, XGBoost) - Deep Learning (TensorFlow/Keras — AN

slowdown? what slowdown? Sources: Anthropic considers releasing a new AI model to counter OpenAI's momentum since Astra's launch, ahead of an IPO and after Amodei's call for a slowdown (Reuters) (Visi

Sometimes everybody is right! Me, spring 2023 onwards: giving LLM-driven agents unrestricted internet access with read/write permissions is going to be a security nightmare. The AI industry: Agents ar

onPanda is designed for geeks, power users, curious minds, and engineers. Its UI is built for deep exploration and efficient data annotation. - The core loop is simple: hover over a token → click an a

I decided to run prism-ml/Ternary-Bonsai-2-27B-PQ2_0 through my own set of UNSCIENTIFIC benchmarks. I needed something to compare it to, so I decided I would compare with another 27B model by filesize

At the start of this week, the who's-who of AI seemed - at least tentatively - on the side of AI regulation. Over the weekend, Anthropic CEO Dario Amodei had proposed a three-step plan for slowing AI

Gary Marcus warns that a simple linear trend—despite growing overall AI spending—will undermine both OpenAI and Anthropic by eroding expected returns and scaling challenges. He argues that this trajec

Note: This writeup was put together with the help of AI. So I've got dual AMD MI50 32GB cards. If you know these cards, you know the story - AMD dropped official ROCm support for gfx906 after ROCm 5.7

María Paula Mijares Torres / Bloomberg: Trump says he will appoint an AI czar and form an “AI Force”, in a Truth Social post that rejects AI safety concerns as a “hoax” — President Donald Trump said h

Oh My Pi + vLLM on two 3090s. Average wait per turn went from 28s to 7s, mostly from changing omp settings: explicit effort level on every role (unset ones defaulted to xhigh) thinking_token_budget of

What's Changed GET /api/show now advertises each model's thinking controls and default: curl http://localhost:11434/api/show -d '{'model': 'glm-5.3-flash:cloud'}' { 'thinking': { 'values': ['low', 'hi

Took me a while since I'm on a family trip and have limited hardware, but here it is! Von: Open-source 'System One' drop-in replacement for TypeSafe's JEV. https://github.com/wfzyx/von https://hugging

wait, wasn’t that literally already part of David Sack’s title? President Trump announced the formation of the US AI Force to oversee the development of artificial intelligence, and in the near future

We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation. https://x.com/i/article/2101448785255907

Weekend project, getting AEO-pilled. Also a good test (for me) of Claude Projects. Have been meaning to update Eleventy and do a few other redesign tasks on https://cybercultural.com, which tbh has be

weirdly the New York Post (which did that stupid and egregious hatchet job on METR) may well be right about this one OpenAI and Anthropic oversold AI security breaches to pressure feds into protecting

Welcome to http://trumanworld.live An infinite live stream running inside a persistent AI world engine, powered by GPT-6 Astra and #MiniMax H3 Max Director by @fal Truman World is an AI-generated simu

EDIT: Upvotes and downvotes are appreciated, but I'd especially welcome substantive replies. I'm genuinely interested in understanding the discrepancy, and the post is tagged 'Serious replies only' fo

what if we...increased the air gap OpenAI's Noam Brown says air-gapping the computers may not stop a misaligned AI, because two air-gapped machines can still talk by running a CPU hot and reading the

I'm still using LLM's the 2022/23 way of doing everything manually from the chat box. I copy and paste everything manually into the box and ask the AI to explain or do something, such as pasting code

I was wondering if there are any good coder models for 8GB VRAM RTX 5060. My specifications: 8GB RTX 5060 8GB DDR4 RAM 256 GB SSD I know the configuration is a bottleneck for sure. Though I don't have

with jev, it's nice to see builder energy back on X, reminiscent of the early days of building with LLMs (back when gpt_index/llama_index/langchain first started) before jev, most of the 2026 AI demo

with @Thom_Wolf in sunny italy ☀️chatting about the @huggingface @OpenAI attack, the “tell” that it was an agentic swarm, how misalignment arises in RL, whether agent awareness of evaluation is eviden

Worth reading about this OpenAI just admitted on camera: They spun up thousands of AI agents in a “secure” sandbox and told them to hack. The agents didn’t follow the test. They cheated. Then they bro

yeah that and following basic procedures around sandboxing and monitoring. and maybe shutting down agent access to the web until we have better control of the technology. but, sure, what @DavidSacks s

arXiv:2609.19216v1 Announce Type: cross Abstract: Research on 4D millimeter-wave radar perception algorithms has flourished in recent years, extending from signal processing and object detection to se

6 billion tokens for $65 Is it as good as Astra and Fable at hard stuff? No of course not. But you don't always need a genius and can just call one for advice when you do. Extrapolate where this is go

I have always posted about budget builds on here, and often asked how we are going to run the next big models. Often Plenty of downvotes too or folks telling me that it's not running if I'm getting 5t

arXiv:2405.20174v3 Announce Type: replace Abstract: We propose a computational tropical geometry framework for the symbolic analysis of neural networks with tropical activations. The number of linear

arXiv:2609.19398v1 Announce Type: cross Abstract: Spontaneous speech offers a scalable, noninvasive signal for respiratory health assessment, yet interpretable models that generalize across languages

arXiv:2609.19843v1 Announce Type: new Abstract: LLM-based GUI agents increasingly act on behalf of users in digital environments that were designed with human users in mind. These graphical user inter

arXiv:2609.20562v1 Announce Type: new Abstract: Automated quality assessment, enhancement, and segmentation of multiple structures in 0.064,T ultra-low-field pediatric MRI are limited by a low signal-

A few thoughts on this: 1) If you’ve only seen clips of this interview, I’d encourage you to watch the full podcast. I push back on plenty of AI hype in it. 2) As I said in the podcast, this example i

arXiv:2609.20064v1 Announce Type: new Abstract: Despite impressive reported scores, large vision-language models have seen limited practical uptake in historical automatic text recognition because of

arXiv:2609.19334v1 Announce Type: new Abstract: Full-duplex speech-to-speech (S2S) models provide natural, low-latency conversational interaction and would benefit from the ability to use external too

arXiv:2609.19855v1 Announce Type: cross Abstract: Geographic applications need every object inside a radius that satisfies a semantic threshold, yet embedding indexes return approximate top-ranked lis

arXiv:2503.08509v2 Announce Type: replace Abstract: The real-time process of directional changes while drilling, known as geosteering, is crucial for hydrocarbon extraction and emerging directional dr

arXiv:2609.20273v1 Announce Type: cross Abstract: Non-invasive brain-computer interfaces (BCIs) and eye-tracking technologies offer promising communication pathways; however, motor imagery (MI)-based

arXiv:2503.22727v3 Announce Type: replace Abstract: Despite the excitement behind biomedical artificial intelligence (AI), access to high-quality, diverse, and large-scale data - the foundation for mo

arXiv:2609.20298v1 Announce Type: new Abstract: We present a learning algorithm for inferring threshold Boolean networks (TBNs) with a prescribed set of fixed points. The proposed method employs a cus

arXiv:2609.20437v1 Announce Type: cross Abstract: This article presents a mathematical model of the Motivated Emotional Mind cognitive architecture developed for embodied intelligent systems. Such a s

arXiv:2609.19328v1 Announce Type: new Abstract: In recent years, aerial manipulation has attracted increasing attention as a key to expand the application of aerial robots. In this work, we focus on t

arXiv:2609.19555v1 Announce Type: cross Abstract: Artificial intelligence for plant disease analysis has advanced from task-specific classifiers to multi-modal models capable of jointly interpreting v

arXiv:2609.20275v1 Announce Type: cross Abstract: Hybrid brain-computer interface (BCI) systems that integrate electroencephalography (EEG) and electromyography (EMG) signals have shown significant po