Knowledge catalogue
arXiv:2605.00631v1 Announce Type: new Abstract: We present H-RAG, our submission to SemEval-2026 Task 8 (MTRAGEval), addressing both Task A (Retrieval) and Task C (Generation with Retrieved Passages).
had a couple ppl ask what made me want to invest (i am lucky they welcomed me), here’s what i answered Announcing Cofounder 2: Run an entire company with agents. It's the infrastructure for the one pe
Hey filthy rich AI warlords who have alienated most of the population, don’t say I didn’t try to warn you.🤷♂️ “Bubble or not, the AI backlash is validating what one researcher and critic has been say
hi, i'm a sole proprietor/founder in Austria and i earn many many multiples of what i'd earn as an employee, despite 'predatory income tax'. in fact, i opt out of the many tax optimizations i could us
arXiv:2605.00529v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical in
arXiv:2605.00281v1 Announce Type: new Abstract: We study high-probability (HP) convergence guarantees in decentralized stochastic optimization, where multiple agents collaborate to jointly train a mod
arXiv:2605.00496v1 Announce Type: new Abstract: Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar
Hilarious (and maybe a little bit scary) that even in 2026 Marc Andreessen still hasn’t learned that LLMs don’t know how to reliably follow system prompts. don't feel bad, guys, the techno-optimist ma
Peter Loftus / Wall Street Journal: How AI is transforming the pharma industry, with most gains so far from back-office streamlining and faster manufacturing rather than breakthrough drug research — D
Choe Sang-Hun / New York Times: How AI tools such as Naver's Talking Buddy and SuperBrain are helping South Korea's elderly ease loneliness, detect emergencies, and slow cognitive decline — In the wor
Ellen Cushing / The Atlantic: How “emotion AI”, the use of facial and sentiment analysis tools to track workers' moods, is seeping into white-collar jobs amid concerns over privacy and bias — The good
arXiv:2605.00113v1 Announce Type: new Abstract: We examine if frontier chat-based large language models (LLMs) adjust their outputs based on neurodivergence (ND) context in system prompts and describe
General Intelligence built their agent platform using AI agents themselves, leveraging Vercel's infrastructure and deployment capabilities. The approach demonstrates how autonomous agents can be used
This post documents a 10-day project to build a local AI system using open-source tools and models, specifically combining Ollama (a local LLM framework), Gemma 4 (a language model), Claude Cowork 3P,
arXiv:2605.00269v1 Announce Type: new Abstract: Recent white-box OOD detection methods for LLMs -- including CED, RAUQ, and WildGuard confidence scores -- appear effective, but we show they are struct
OpenAI describes its technical approach to delivering real-time voice AI services with minimal latency across large user bases, likely covering infrastructure optimization, model serving strategies, a
arXiv:2507.01955v3 Announce Type: replace Abstract: Multimodal foundation models (MFMs), such as GPT-4o, have recently made remarkable progress. However, their detailed visual understanding beyond que
This link directs to Nous Research's subscription management portal where users can view, modify, or cancel their subscription settings and billing information. The associated X post likely announces
arXiv:2605.00068v1 Announce Type: new Abstract: Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively hi
arXiv:2605.00820v1 Announce Type: cross Abstract: We introduce HyCOP, a modular framework that learns parametric PDE solution operators by composing simple modules (advection, diffusion, learned closu
arXiv:2605.00351v1 Announce Type: new Abstract: Root cause localization in cloud native microservice systems requires modeling complex service dependencies, irregular temporal dynamics, and heterogene
arXiv:2605.00082v1 Announce Type: new Abstract: The Forward-Forward (FF) algorithm presents a compelling, bio-inspired alternative to backpropagation. However, while efficient in training, it has a co
I had Claude Code for web build me this WebAssembly playground for trying out the new Redis array commands https://tools.simonwillison.net/redis-array More notes here: https://simonwillison.net/2026/M
I have a ~200mb sqlite DB of the entire history of SF criminal court cases for the last 4 years that I want to make publicly accessible for anyone to query with AI. It includes roughly 77k cases, 319k
i love the recent explosion of interactive data visualizations. more plz Who actually shapes AI policy in the U.S.? We mapped 1,812 entities: 745 people, 918 organizations, 2,925 relationships. Fronti
I think I can say Runway is among the platforms with the most user-friendly interface and navigation. Pretty sure I can say that, it's my opinion. But, Runway interface and combined models really do e
I think the fact that GPT-4o and Llama 3.3-80B did no significant harm is just as important as whether AI helped. If older (less accurate & more sycophantic) chatbots essentially did nothing for peopl
i thought on device ai was stupid but now my local voice model turns 4x faster on my corporate m4 max laptop than my m2 max personal laptop now i want to have a beefier computer to run the transcripti
I tried running the same 'Generate an SVG of a pelican riding a bicycle' prompt against 21 different quantized variants of the same IBM Granite 4.1 3B model - the results weren't as interesting as I h
I want to tell you the story of a young woman who you have probably never heard of. Her name is Mary Anne. She was born on a remote island in Scotland, where life was harsh and unforgiving. On May 2,
I wrote Deep Learning with Python to be the definitive guide to how deep learning works and how to best make use of it. Tens of thousands of people got their career start via this book. 120,000 copies
arXiv:2605.00526v1 Announce Type: new Abstract: Suspect face generation remains a technical challenge in crime investigations. Traditional sketch-drawing workflows suffer from low efficiency and quali
This post presents a philosophical argument questioning the logical coherence of rights categories like 'women's rights' and 'gay rights,' suggesting they are either redundant if equal rights already
If you have two minutes to watch something today, watch this Sincitium is finally here. We are pleased to present our latest piece: a concept trailer created specifically for the @runwayml Big Pitch C
If you need proof of why AI output can't be trusted by default watch that page for more than 1 minute for any given LLM that produces output in there. An amazing time capsule of the unevenness of curr
i'll be speaking in NYC this thursday on memory for agents! i'll be talking about filesystem backed memory, owning memory with an open harness, background memory consolidation, and more! https://luma.
arXiv:2408.11349v2 Announce Type: replace Abstract: Mercari is the largest C2C e-commerce marketplace in Japan, having more than 20 million active monthly users. Search being the fundamental way to di
arXiv:2605.00436v1 Announce Type: new Abstract: Concerns with the safety and reliability of applying large-language models (LLMs) in unpredictable real-world applications motivate this study, which ex
This newsletter entry discusses advancements in automating AI research and development processes, exploring how artificial intelligence systems are becoming capable of autonomously designing and impro
arXiv:2509.20098v2 Announce Type: replace Abstract: Learning physical dynamics from data is a fundamental challenge in machine learning and scientific modeling. Real-world observational data are inher
Mike Wheatley / SiliconANGLE: Inference cloud startup DeepInfra raised a 107M Series B co-led by 500 Global and Georges Harik; it currently supports more than 190 open models — Dedicated inference clo
A meta-analysis claiming ChatGPT has positive effects on students' learning performance, perception, and higher-order thinking was retracted on April 22, 2026 . The retraction highlighted that 'educat
arXiv:2605.00250v1 Announce Type: cross Abstract: Standard diffusion models for graph generation typically rely on uniform time-stepping, an approach that overlooks the non-homogeneous dynamics of dis
arXiv:2605.00064v1 Announce Type: new Abstract: Information-theoretic generalization bounds analyze stochastic optimization by relating expected generalization error to the mutual information between
arXiv:2605.00664v1 Announce Type: new Abstract: We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework,
Alex Bronzini-Vender / New York Magazine: Inside Palantir Foundation's Atlantic and Pacific Forum at Yale for invited students: State Dept. and Palantir staff share a vision of mixing AI and state pow
arXiv:2510.16450v2 Announce Type: replace Abstract: Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biologi
Ionut Arghire / SecurityWeek: Instructure reported a data breach on April 30; ShinyHunters added Instructure to its victims list and claims it has 3.65TB of data from ~9K institutions — Hackers disrup
Dylan Martin / CRN: Intel taps Alex Katouzian, an ex-Qualcomm EVP, to lead Client Computing & Physical AI group, and names Pushkar Ranade as CTO, after serving on an interim basis — With the hiring of
arXiv:2605.00324v1 Announce Type: cross Abstract: Large-scale ranking systems depend on thousands of features derived from user behavior across multiple time horizons. Typically requires model retrain
arXiv:2508.07630v2 Announce Type: replace Abstract: We introduce InterChart, a diagnostic benchmark that evaluates how well vision-language models (VLMs) reason across multiple related charts, a task
arXiv:2605.00591v1 Announce Type: new Abstract: Contrastive vision-language models like CLIP exhibit remarkable zero-shot generalization. However, prompt tuning remains highly sensitive to label noise
Generate recommendations from production traces, validate them with batch evaluation and A/B testing, and ship with confidence. AI agents that perform well at launch don’t stay that way. As models evo
In this post, you learn how to get started with Dataset Q&A, explore real-world use cases with hands-on examples, and discover advanced capabilities like auto-discovery across all your data assets and
Deepsec is a security tool introduced by Vercel designed to identify and help remediate vulnerabilities within codebases. The tool functions as a security harness that automates vulnerability detectio
Introducing nanowhale 🐳! A tiny DeepSeek model fully pretrained by an agent. Inspired by @karpathy's nanochat, we gave ml-intern the task of training a tiny MoE with all the architectural advancements
Introducing Pinecone Nexus. A knowledge engine for agents. The bottleneck for production agents isn't the model. It's the per-query work of searching, stitching, parsing tables, normalizing labels. Ne
Generate recommendations from production traces, validate them with batch evaluation and A/B testing, and ship with confidence. AI agents that perform well at launch don’t stay that way. As models evo
Generate recommendations from production traces, validate them with batch evaluation and A/B testing, and ship with confidence. AI agents that perform well at launch don’t stay that way. As models evo
arXiv:2605.00184v1 Announce Type: new Abstract: With the growing integration of human-computer interaction into everyday life, advances in machine learning have enabled systems to better perceive and