CompanyAnthropic8 recent entries14 Oct 2026Does System One Transfer? Calibrated Typed-Decision Models, Label Budgets, and Translation for Indonesian Regional LanguagesarXiv:2610.14112v1 Announce Type: cross Abstract: Calibrated typed-decision ('System One') models return a label and a probability in a single forward pass at a small fraction of the cost of large lan→14 Oct 2026Discover AI: A Learning Guide - 51 hands-on labs for learning how AI actually works.This is an offline app with 51 hands-on labs for learning how AI actually works, from neurons to agents and more... **A bit of insight** - 51 labs in 6 groups, from the basics (what a neuron is, gradi
CompanyOpenAI8 recent entries14 Oct 2026OpenAI Employee Uses 'Unnamed Chatbot' to Spy on OpenAI, Gets Arrested by FBIOpenAI is in the news again. This time, it’s due to a recent incident involving corporate espionage. According to a statement the AI lab released on 13th October, the company discovered a “sophisticat→14 Oct 2026Introducing the largest open-source multilingual, multimodal RL environments 🌍 📄 OCR: 1M+ document pages in 22 languages 🎙️ ASR: speech i…Introducing the largest open-source multilingual, multimodal RL environments 🌍 📄 OCR: 1M+ document pages in 22 languages 🎙️ ASR: speech in 102 languages 12M+ tasks across two OpenEnv Environments, ope→14 Oct 2026I built BitRun: A standalone runner for 1-bit LLMs (100–127 t/s on Apple Silicon & 40–45 t/s on PC CPUs with zero compile)I built BitRun because I wanted to run 1-bit ternary LLMs on ordinary laptops without melting my battery, spinning up a dedicated GPU, or wrestling with complex build environments. Right now, BitRun g→14 Oct 2026I built a cheap dual 3090 rig from used parts, but why isn't it much faster?Hey everyone, I recently put together a local LLM machine using mostly second hand hardware. I wanted to experiment with local models for app development without spending a fortune on a new workstatio→14 Oct 2026Has anyone found a fix for Standard Voice Mode reading formatting, links and image data aloudI've been using ChatGPT Voice for years, particularly during my commute to work. Until recently, I've almost exclusively used Standard Voice Mode, but a recent issue has made it practically unusable. →14 Oct 2026Groundcover lets Claude and Codex hand production investigations to its own agentApplication observability startup groundcover Inc. today gave outside artificial intelligence coding agents such as Anthropic PBC’s Claude and OpenAI Group PBC’s Codex a way to hand production investi→14 Oct 2026corporate espionage they sayopenai staff are out there turning the office into a stealth game, while my biggest security threat is letting codex, claude code and sumus loose on a test branch without read only permissions enabled→14 Oct 2026AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger ProblemsarXiv:2610.16555v1 Announce Type: cross Abstract: We introduce qtBench, a benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial algorithm that explain
CompanyGoogle8 recent entries14 Oct 2026Harness^2: Recursive Agent Harnessing for an Open WorldarXiv:2610.14224v1 Announce Type: cross Abstract: LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a p→14 Oct 2026Google DeepMind and Singapore Government announce new AI tool to protect citizens against scamsGoogle DeepMind and the Singapore Government have launched a partnership to deploy an artificial‑intelligence tool designed to help citizens identify and avoid scams. Announced in May 2026, the initia→14 Oct 2026Google DeepMind and Google Cloud plan to provide up to 200 European scientific researchers with access to their frontier AI models and $3M in compute credits (Foo Yun Chee/Reuters)Foo Yun Chee / Reuters: Google DeepMind and Google Cloud plan to provide up to 200 European scientific researchers with access to their frontier AI models and $3M in compute credits — Google DeepMind →14 Oct 2026Gemini 4 TikZ unicornGemini 4 TikZ unicorn From GPT-4 to GPT-6. Sparks was a remarkably prescient paper that got a lot of pushback at the time, but absolutely sensed where the vibes were heading with LLMs based on a lot o→14 Oct 2026Gemini 4 Argon, Muse Spark 1.3, and Muse Wonder 1.0 are all really good at pdf parsing. Come check it out on OpenDocRouter! https://www.open…Gemini 4 Argon, Muse Spark 1.3, and Muse Wonder 1.0 are all really good at pdf parsing. Come check it out on OpenDocRouter! https://www.opendocrouter.ai/ Media OpenDocRouter makes it dead-simple to st→14 Oct 2026Galaxy S21 + Gemma 4 E2B Q3_K_M + Qwen3.5-0.8B Q4_K_M: same Amazon task, two different valid carts via structured browser perceptionThis continues the small-model browser experiments from the previous posts. Two standard, off-the-shelf models ran locally on the same Samsung Galaxy S21: Gemma 4 E2B, Q3_K_M as the reasoner Qwen3.5-0→14 Oct 2026Benchmarks are becoming the core competency of any company. Our company mission is to build the world’s best models for document processing.…Benchmarks are becoming the core competency of any company. Our company mission is to build the world’s best models for document processing. This also means that we have to build the world’s best benc→14 Oct 2026[AINews] AI Engineer NYC: Gemini 4 Argon, Vals AI BenchmarksGoogle’s Gemini 4 Argon is now generally available (GA), offering coding, knowledge‑work, enterprise‑workflow, and cyber‑defense features via the paid Gemini API, Google AI Pro/Ultra in the Gemini app
CompanyMeta8 recent entries14 Oct 2026b11612unicode : add opt-in NFC normalization for Unigram tokenizers (#30390) unicode : add opt-in NFC normalization for Unigram tokenizers Note: used help from Codex, Sol 6.1 Medium Fixing initial bot comme→14 Oct 2026b11609webgpu: (Fix CI) fix mul_mat_id with duplicate expert ids (#30451) Fix mm-id of webgpu in the case of ids duplication formatting fix comments to avoid breaking up sentences in comments Website: https:→14 Oct 2026b11608server : escape the special tokens without std::regex (#30243) The d1-omni and kev prompts escape '<|name|>' in the request text with std::regex_replace. libstdc++ recurses for each char of the name, →14 Oct 2026b11607chat: replace output string with parts (#30389) chat: replace output string with parts reserve first Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/5563975→14 Oct 2026Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM GenerationarXiv:2610.16041v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable success across a wide range of language tasks. At their core, autoregressive LLMs are conditional →14 Oct 2026ATTUNE: Agentic Throughput Tuning for LLM TrainingarXiv:2610.17528v1 Announce Type: cross Abstract: Training recipes are tuned by hand for one model, cluster and workload, and every new model, accelerator, framework version or dataset means tuning ag→14 Oct 2026Anthropic Executive Says Open-Source AI Models Are Higher Riskhttps://www.bloomberg.com/news/articles/2026-10-14/anthropic-executive-says-open-source-ai-models-are-higher-risk https://www.business-standard.com/technology/artificial-intelligence/open-source-ai-mo→14 Oct 2026AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger ProblemsarXiv:2610.16555v1 Announce Type: cross Abstract: We introduce qtBench, a benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial algorithm that explain
CompanyMistral8 recent entries14 Oct 2026MultiAlloc: Budget-Aware Precision Allocation for KV Cache QuantizationarXiv:2610.18642v1 Announce Type: new Abstract: The Key-Value (KV) cache constitutes a dominant source of memory consumption during large language model (LLM) inference, particularly in long-context a→14 Oct 2026Lightweight Scheduling Policies for Continuously Batched LLLM Serving Across GPU ArchitecturesarXiv:2610.15899v1 Announce Type: cross Abstract: Large language model serving is increasingly limited not only by model size and GPU speed, but also by scheduling during autoregressive decoding, wher→14 Oct 2026LIFT: Likelihood-Based Intervention Faithfulness TrainingarXiv:2509.13334v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning improves LLM accuracy on complex tasks, but CoTs are often unfaithful; that is, the model does not rely on th→14 Oct 2026GA-SVD: Generation-aware Singular Value Decomposition for LLM CompressionarXiv:2610.15398v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong generalization across a broad range of reasoning and generation tasks, but their large parameter counts →14 Oct 2026From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model EditsarXiv:2610.18098v1 Announce Type: new Abstract: Deleting singular components offers a precise way to remove a capability from a language model, yet the first-order spectral saliency used to rank compo→14 Oct 2026Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language ModelsarXiv:2610.15159v1 Announce Type: new Abstract: Existing depth-compression methods for large language models (LLMs) score layers individually or group only adjacent or contiguous layers, implicitly as→14 Oct 2026Benchmarks are becoming the core competency of any company. Our company mission is to build the world’s best models for document processing.…Benchmarks are becoming the core competency of any company. Our company mission is to build the world’s best models for document processing. This also means that we have to build the world’s best benc→14 Oct 2026Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete WorksarXiv:2607.09316v2 Announce Type: replace-cross Abstract: Thematic indexing -- the practice of assigning structured conceptual labels to sections of text -- is essential to scholarly access in large-s
CompanyxAI8 recent entries13 Oct 2026If an agent saves an engineer 2 hours to implement a feature but collectively costs the team 3 hours in alignment and review, the ROI is neg…If an agent saves an engineer 2 hours to implement a feature but collectively costs the team 3 hours in alignment and review, the ROI is negative. Isolated chats are suboptimal in team environments be→13 Oct 2026Grok @Bot rocksGrok @Bot rocks I've been using Grok @Bot as my daily driver for a few weeks now and: - it has replaced 100% of my search-like queries on chatgpt / claude - it has replaced 100% of my Hermes usage & a→13 Oct 2026Grok @Bot memory transferGrok @Bot memory transfer NEW GROK BOT! AI MEMORY TRANSFER! Your old AI knows you. Your new one shouldn't have to start from zero. 🧠➡️ Meet Memory Transfer, a @Grok @Bot that brings over what Claude o→14 Oct 2026XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement LearningarXiv:2610.16478v1 Announce Type: cross Abstract: Deep reinforcement learning has shown strong potential for vision-based autonomous driving, but policies trained in simulation often suffer severe per→14 Oct 2026Siam-ALS: An Explainable Siamese Deep Learning Framework for Early ALS Detection Using EEG and Eye-Tracking SignalsarXiv:2610.15351v1 Announce Type: new Abstract: Amyotrophic lateral sclerosis (ALS) diagnosis remains challenging due to heterogeneous symptoms and reliance on clinical assessment, underscoring the ne→14 Oct 2026Integrating Feature Understandability into Feature Selection for Human-Centred Tabular ExplanationsarXiv:2610.16627v1 Announce Type: cross Abstract: Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable ins→14 Oct 2026Discover AI: A Learning Guide - 51 hands-on labs for learning how AI actually works.This is an offline app with 51 hands-on labs for learning how AI actually works, from neurons to agents and more... **A bit of insight** - 51 labs in 6 groups, from the basics (what a neuron is, gradi→14 Oct 2026BrainAid: Efficient Brain Tumor Detection Using Lightweight CNNs and Explainable AI for Resource-Constrained EnvironmentsarXiv:2610.15077v1 Announce Type: new Abstract: A brain tumor is an unusual growth of cells in the brain that can be cancerous or not, affecting normal brain function and causing serious risk to healt
CompanyDeepSeek8 recent entries13 Oct 2026DigitalOcean Inference Router Enhancements: Performance Tuned Routing, No Rules to WriteEvery few weeks, a new model steps up and claims best-in-class at something. The launch chart makes the case, the link makes the rounds, and your team is back to the question nobody has time for: shou→13 Oct 20264x 6000 Pro for the companyHere is how i serve 40 people (10 of them developers) with local AI services. n8n for automatisation whisper and Vexa AI, a bot joins Teams and makes transcripts, n8n later extracts decisions and todo→14 Oct 2026The AI race: China's open-weight models trail US closed models by just 7 monthsSource: whatmodel.sh, an open source AI leaderboard I built (and launched here yesterday). Every point comes from published benchmark results: 22,113 of them across 987 benchmarks, from 1,011 sources,→14 Oct 2026New open source app built with Together AI! Gloss turns your saved articles, PDFs, and X bookmarks into a beautiful personal library, with l…New open source app built with Together AI! Gloss turns your saved articles, PDFs, and X bookmarks into a beautiful personal library, with lightning-fast AI answers powered by DeepSeek V4.1 Flash. Try→14 Oct 2026MultiAlloc: Budget-Aware Precision Allocation for KV Cache QuantizationarXiv:2610.18642v1 Announce Type: new Abstract: The Key-Value (KV) cache constitutes a dominant source of memory consumption during large language model (LLM) inference, particularly in long-context a→14 Oct 2026LLM Agents for Automated Post-Training via Structured Recipe OptimizationarXiv:2610.18572v1 Announce Type: cross Abstract: Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically construct→14 Oct 2026inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMsarXiv:2610.18051v1 Announce Type: new Abstract: This work investigates the application of the Membership Inference Test (MINT) to large language models (LLMs) fine-tuned with LoRA, aiming to determine→14 Oct 2026DoSA: Dots Sparse AttentionarXiv:2610.13990v1 Announce Type: new Abstract: Sparse attention visits few keys, yet finding them can still require scoring every key with every indexer head. We introduce DoSA (Dots Sparse Attention
CompanyNVIDIA8 recent entries14 Oct 2026I built a cheap dual 3090 rig from used parts, but why isn't it much faster?Hey everyone, I recently put together a local LLM machine using mostly second hand hardware. I wanted to experiment with local models for app development without spending a fortune on a new workstatio→14 Oct 2026Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language ModelsarXiv:2610.15781v1 Announce Type: new Abstract: Training-free pruning removes weights from pretrained large language models to reduce their deployment cost. However, existing approaches typically cons→14 Oct 2026Embodied Zero-Shot Task Planning via Hardware-Aware LLM-VLM Integration for Grounded Robotic ManipulationarXiv:2610.14106v1 Announce Type: new Abstract: Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded →14 Oct 2026Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on …Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited to see the community unlock more of Qwen’→14 Oct 2026CAST: Real-Time Motion Capture for Any Skeleton TopologyarXiv:2610.14856v1 Announce Type: new Abstract: This paper studies the problem of recovering motion from monocular video, even when the target skeleton topology differs from the subject observed in th→14 Oct 2026BARTER: Compact Dynamic Sparse Training with Standard Dense KernelsarXiv:2610.16147v1 Announce Type: new Abstract: Dynamic sparse training (DST) aims to reduce training costs while maintaining accuracy. Existing DST methods mask out parameters but keep matrix dimensi→14 Oct 2026AUGUstus: Autonomous Driving VLA Model with Unified Generation and UnderstandingarXiv:2610.16985v1 Announce Type: new Abstract: Vision-language-action (VLA) models show strong potential for end-to-end autonomous driving by leveraging world knowledge and understanding to excel in →14 Oct 2026Anthropic Executive Says Open-Source AI Models Are Higher Riskhttps://www.bloomberg.com/news/articles/2026-10-14/anthropic-executive-says-open-source-ai-models-are-higher-risk https://www.business-standard.com/technology/artificial-intelligence/open-source-ai-mo