Knowledge catalogue
Wild 24 hours for AI and lots of different proposals have been made. TLDR; the only *tangible* new fact is that OpenAI and Anthropic are going to have embedded 3rd party evaluators from unknown organi
Terence Tao / What's new: A group of 25 Fields Medal recipients says AI companies' push to solve mathematical problems as a benchmark is detrimental to the science of mathematics — I am proud to be am
arXiv:2609.09875v1 Announce Type: new Abstract: Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), r
arXiv:2609.11870v1 Announce Type: new Abstract: A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Au
Datasette 1.0a39 and 0.65.4 security releases Today we're releasing two new security patch versions of Datasette: 1.0a39 and 0.65.4 - one for the current alpha series and one for the stable 0.65.x fam
arXiv:2609.10421v1 Announce Type: cross Abstract: Background: Emergency Department (ED) return visits are commonly reviewed for quality assurance, but are often limited (e.g., to revisits within 48-72
arXiv:2603.17094v2 Announce Type: replace Abstract: Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. This
arXiv:2603.15617v2 Announce Type: replace Abstract: Can AI make progress on important, unsolved mathematical problems? Large language models are now capable of sophisticated mathematical and scientifi
arXiv:2609.08861v1 Announce Type: new Abstract: Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assump
arXiv:2609.10144v1 Announce Type: cross Abstract: AI systems become more useful when they can adapt to the people using them, but in multi-agent systems, useful context learned by one agent often rema
arXiv:2609.10016v1 Announce Type: cross Abstract: We introduce MetroLLM-Bench, a 955-case benchmark for testing language models as the policy layer of a transit kiosk. It covers six real metro systems
This model is insane at landing pages. I asked DeepSeek V4.1 Flash & Claude Fable 5 to build me a landing page for a movie theater. Fable cost $1.21 while V4.1 Flash cost 2.6 cents, making it more tha
arXiv:2609.09949v1 Announce Type: cross Abstract: Real-world detectors must often interpret functional or ambiguous prompts, yet conventional models such as YOLO remain restricted to fixed class lists
arXiv:2609.08279v1 Announce Type: cross Abstract: Agent memory systems must discard stored information when their history exceeds a fixed token budget. Existing budget-accuracy frontiers quantify the
arXiv:2609.05441v1 Announce Type: new Abstract: Long-term memory for LLM agents is evaluated today by conversational recall benchmarks (LoCoMo, LongMemEval), which measure question answering over dial
Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaP
arXiv:2609.06341v1 Announce Type: new Abstract: Linear algebra provides the framework of concepts (matrix rank, singular value decomposition (SVD), and eigendecomposition) that modern artificial intel
Automated lint: 12 errors, 53990 warnings, 3 info
arXiv:2609.05911v1 Announce Type: cross Abstract: Long-horizon LLM agents interact with untrusted content, persistent memory, external state, and sensitive tools. Existing analyses often characterize
arXiv:2609.08040v1 Announce Type: cross Abstract: The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing de
What is Astra actually supposed to be better at, Because if the answer is “everything,” then I genuinely do not understand what kind of testing was done for writing-heavy use cases. My biggest issue i
Tae Kim / Key Context: Astra working with Blender via computer use feels like magic, showing computer use could be the fourth demand wave after chatbots, reasoning, and agentic coding — AI computer to
arXiv:2609.04895v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models activate only a small subset of experts per token, but the full expert set often exceeds GPU memory, causing repeated we
I've built and open-sourced ParaRNN, a PyTorch/Triton library that parallelizes the training of non-linear recurrent architectures across time using Newton-Raphson iterations mapped to associative pre
Really strong benchmark paper on coding agents. Claude Opus 5 running under Claude Code passes 23.9% of the evaluations. An expert human reference scores 82.2%. Here is what the task actually is. The
arXiv:2609.05232v1 Announce Type: new Abstract: Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine w
arXiv:2609.04453v1 Announce Type: cross Abstract: Expert pruning reduces the memory and serving cost of Mixture-of-Experts (MoE) models by removing low-importance experts identified by the router, ass
Hi everybody, I am in a tricky situation. My grandfather + grandmother live in a remote village in asia, and were visiting us in the city. My grandfather has absolutely fallen in love with AI, and it
“The expected value of a fully LLM-generated, non-human-reviewed patch is a net-negative by a considerable margin.” 🦔AI can only fix security vulnerabilities 26% of the time. Researchers at 1Password
Yet another win for Neurosymbolic AI! Fermat! Anthropic says its first Fermat runs failed not on math, but because dozens of Claude agents lost track of shared project state. They only succeeded after
TIL: Using Blender with coding agents on macOS I've been having fun with Blender in ChatGPT Codex on my Mac recently. Getting it to work with coding agents is really easy: install the full Mac applica
Does Astra have human-like continual learning capability over long periods? If not, it's not AGI. Even a system that could pass @demishassabis's new 'Turing test' where it has to independently discove
Celia Ford / Transformer: OpenAI says it can't read all of Astra's reasoning and admits covert sandbagging would likely go uncaught, yet still calls it the world's most aligned model — OpenAI is haili
Very important paper accelerating research around AI discovery. https://x.com/omarsar0/status/2095858839534862664?s=20 New benchmark from @Apodex_AI worth digging into. TRACES scores AI systems on dis
arXiv:2609.03254v1 Announce Type: new Abstract: Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in conversation. A challenge here i
Access to Astra is rolling out over the coming days. Starting today, enterprise customers in OpenAI's Daybreak Program can get access to Astra. Read more on our blog: https://devin.ai/blog/gpt-6-astra
OpenAI’s new language‑model system **Astra** has achieved state‑of‑the‑art performance on three key workflow benchmarks: the Agents’ Last Exam, AutomationBench, and ScreenSpot Pro. These suites evalua
OpenAI announced that its latest model, **Astra**, is their most aligned AI to date, reporting sizable gains in the ability to understand user intent. The tweet was posted on September 3, 2026 at 7:32
I tested Astra early. What I would want EVERY business professional to know about the brand-new model from OpenAI: 1) Computer use and browser use are just incredible. I'm confident that pretty much a
arXiv:2603.03072v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures
arXiv:2609.02067v1 Announce Type: new Abstract: Scientific benchmarks are commonly built by domain experts who write tasks and cross-check one another's work, or who adapt existing material from textb
zai earnings transcript was a really good read, a list of interesting points (mostly verbatim from the transcript): * Chat → Coding → Agent → Cowork → Autonomous AI * What truly matters is who can con
A lot of hype around OpenAI's Astra model here on my timeline today. Apparently, this goes back to a new article from The Information, which said Astra is a 'recurrent depth or looped transformer'. It
arXiv:2603.29093v3 Announce Type: replace-cross Abstract: LLM agents rerun full reasoning for every task, even one they solved moments earlier. We introduce extbf{APEX-EM}, a non-parametric experience
arXiv:2609.00524v1 Announce Type: cross Abstract: Computer-use agents are emerging as a paradigm for agentic human-AI interaction, combining language reasoning with multi-modal interface grounding to
arXiv:2412.12144v5 Announce Type: replace-cross Abstract: Personality assessment through situational judgment tests (SJTs) offers unique advantages over traditional Likert-type self-report scales, yet
arXiv:2609.01111v1 Announce Type: new Abstract: Clinical LLM assistants must reason over multi-visit patient trajectories, yet whether the compact history representations used to scale them---retrieva
arXiv:2609.00067v1 Announce Type: cross Abstract: External text can override conflicting image evidence in multimodal large language models, a failure we call multimodal contextual sycophancy. We intr
arXiv:2609.01409v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong performance in generating scientific figures from text or images. However, producing publication-ready f
arXiv:2609.00487v1 Announce Type: cross Abstract: Frontier language models that refuse harmful single-turn prompts often comply when the same intent is reached gradually over many turns, making multi-
Fable 5.1 didn't come with document OCR benchmarks, so we benchmarked it on ParseBench: a comprehensive parsing benchmark that's comprised of 2k+ real-world documents across finance, legal, insurance,
arXiv:2609.00344v1 Announce Type: new Abstract: Translation students need to learn both how to use translation technologies and how to judge the choices those technologies make available. This article
arXiv:2609.00844v1 Announce Type: new Abstract: Customer-service QA in an AI contact center (AICC) runs under deployment constraints that benchmark QA misses: tight voice-hotline latency and a high co
arXiv:2608.29347v1 Announce Type: new Abstract: Operators remain essential to Remotely Operated Vehicle (ROV) operation, yet often suffer from low situational awareness and high workload, both of whic
arXiv:2603.16138v2 Announce Type: replace-cross Abstract: Generative search systems are increasingly replacing link-based retrieval with AI-generated summaries, yet little is known about how these sys
arXiv:2608.29464v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness
Claude Fable 5.1 tops the Artificial Analysis Intelligence Index but costs 20% more per task than Fable 5 despite a 75% cache read price cut We supported @AnthropicAI with pre-release evaluation of Cl
arXiv:2608.28986v1 Announce Type: new Abstract: LLMs often struggle with modern Korean poetry, producing outputs that resemble 'line-broken prose.' We address two coupled tasks: detecting whether a Ko
arXiv:2608.30893v1 Announce Type: new Abstract: Electrocardiogram (ECG) interpretation requires knowledge of cardiology, electrophysiology, clinical diagnosis, ECG waveforms, signal acquisition, and i
arXiv:2608.29028v1 Announce Type: new Abstract: Multi-agent LLM systems often coordinate by compressing an upstream interaction into a handoff artifact that downstream agents treat as shared state. We