Knowledge catalogue
arXiv:2606.00545v1 Announce Type: new Abstract: Post-trained language models can recognize their own outputs from a sentence or two out of context. In a companion paper itep{jack2026twomodes} we showe
arXiv:2606.01189v1 Announce Type: new Abstract: We argue that the AI community is now ready to move beyond benchmarking and consolidate scattered efforts in model analysis into a systematic discipline
arXiv:2606.00376v1 Announce Type: new Abstract: Extended chain-of-thought reasoning can degrade performance on deterministic state-tracking tasks, not due to preference biases, but limits rooted in th
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. How small businesses can leverage AI From accounting to design
Fine-tuning isn't dead, but the way most teams iterate on AI products has split in two. A tiny fraction run continuous RL against their own environments; everyone else has moved the iteration loop out
arXiv:2602.09651v2 Announce Type: replace-cross Abstract: Diffusion models do not recover semantic structure uniformly over time. Instead, samples transition from semantic ambiguity to class commitmen
The everything apps still look a lot like hybrids between chatbots and IDEs, rather than something built for general knowledge work. Too much assuming linearity & that final outputs are the only goal,
The execution across Elon Musk’s companies right now is operating at an unprecedented scale • SpaceX — The largest IPO in history expected around June 12 • xAI — Grok V9 (1.5T parameters) launching mi
The future of design doesn’t interrupt your process. @NousResearch Hermes keeps designers in creative flow - Rhino → ComfyUI → @Blender in one seamless agent workflow. No context switching. Just visio
arXiv:2511.01938v3 Announce Type: replace-cross Abstract: Grokking is a puzzling phenomenon in neural networks where full generalization occurs only after a substantial delay following the complete me
arXiv:2606.02184v1 Announce Type: cross Abstract: These names do not exist. Elena Vasquez and Marcus Chen have appeared as volcano experts, astronauts, thriller protagonists, podcast hosts, and academ
arXiv:2606.00261v1 Announce Type: new Abstract: Police-reported crash statistics remain the standard input for urban road-safety assessment, but their incompleteness and reporting lag limit their usef
the Henry Nowak murder sounds like a completely outrageous parody of the british criminal justice system. it's hard to believe it's real. - native Britons can't legally carry a breadknife - for some r
arXiv:2606.01901v1 Announce Type: cross Abstract: We introduce the Image Reconstruction Game, a fully automated benchmark in which a vision-language model issues corrective instructions to an image ge
arXiv:2606.00048v1 Announce Type: cross Abstract: Prior research has established that instruction-tuned large language models exhibit left-of-center political bias, measured exclusively through abstra
The Economist: The IPOs of SpaceX, Anthropic, and OpenAI could add up to 4T to US stock market value within months, fueling concerns they could trigger more capital-raising — They promise to be the bi
arXiv:2606.01847v1 Announce Type: cross Abstract: Diffusion-based Vision-Language-Action policies achieve remarkable success in robotic manipulation, yet commit a fundamental geometric error we term t
arXiv:2606.00182v1 Announce Type: cross Abstract: Human-AI collaboration is considered the most promising way to incorporate AI in the workplace. What remains unexplored are the experiential consequen
The next evolution of Hermes Agent is here! Introducing Hermes Desktop: everything you love about Hermes, now native on your machine. First demoed in Jensen's GTC keynote, it's now in public preview.
arXiv:2606.00674v1 Announce Type: cross Abstract: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high perfo
The persistent and possibly industry-funded campaign to discredit me begins with a fundamental misunderstanding of my work. It’s worth taking the time to understand the issues, if you want to understa
The persistent campaign to discredit me begins with a fundamental misunderstanding of my work. It is worth taking the time to understand the issues, if you want to understand a lot of what is driving
Public opinion has shifted dramatically against data centers over a nine-month period, with a 49-point swing in unfavorable sentiment, reflecting growing political concern about these facilities. This
The Quarq agent is constructed using LangGraph, a framework that simplifies the development of complex memory systems. Quarq has achieved a top ranking on the LongMemEval benchmark, demonstrating the
arXiv:2605.05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.e., a model may over-refuse benign prompts while still complying with harmful ones. We audit both f
arXiv:2606.00291v1 Announce Type: cross Abstract: In RLHF, each training example contains a prompt x and two candidate responses y,y', and annotators provide pairwise preferences between these respons
arXiv:2606.00829v1 Announce Type: new Abstract: EgoCross evaluates multimodal large language models on egocentric video question answering under substantial domain shift, where test videos come from s
arXiv:2606.02093v1 Announce Type: cross Abstract: The task of Error Prediction, namely predicting whether a model output is correct, is commonly tackled with Uncertainty Quantification (UQ). However,
arXiv:2606.00344v1 Announce Type: new Abstract: Neural collapse is a structural property of the last-hidden-layer activations in neural network classification models, when trained beyond a zero classi
arXiv:2606.01202v1 Announce Type: new Abstract: Language models do not simply choose an answer at the output layer. In a 9,000-trajectory MMLU study across Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct,
arXiv:2510.10943v2 Announce Type: replace-cross Abstract: Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups.
Gavin Finch / Reuters: The US sanctions Nobitex, Iran's largest crypto exchange, accusing it of helping Iran's government and blacklisted state institutions evade Western sanctions — The United States
arXiv:2606.01002v1 Announce Type: cross Abstract: Engression is a recently proposed and effective framework for conditional distribution learning. Its multi-step Reverse Markov extension further impro
There's never been anything like the Henry Nowak case where the victim is non-white and the assailant is white, and the police respond the way they did. That whole combination of events could really o
Things are so chaotic in AI right now that @axios had to specify *which* AI backlash they were referring to! Anthropic faces AI spending backlash before IPO https://www.axios.com/2026/06/02/anthropic-
arXiv:2606.01168v1 Announce Type: new Abstract: Chain-of-Thought (CoT) has significantly enhanced LLM reasoning, yet often incurs substantial computational overhead due to 'overthinking': generating e
arXiv:2606.02580v1 Announce Type: new Abstract: Inverse graphics is a longstanding and highly underconstrained problem that seeks to reconstruct images as editable 3D scenes which can be rendered, rel
arXiv:2606.01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer. That
This is actually one of the main advantages startups have over frontier labs, as long as there's a healthy spectrum of open-weight to closed-weight models on the cost-performance curve. Building a mod
This post discusses dynamic workflows in Claude Code, enabling flexible task automation and execution patterns. The content is available on the official Claude Blog and addresses how Claude can be har
🌞This is big Local AI news! A new open-source Computer-Use LLM has just launched. Holo 3.1 is H Company’s (🇫🇷) new local computer-use agent model that beats Qwen3.5-397B, Kimi-K2.5, and Sonnet 4.6! Si
This is disaster from Meta AI. Imagine being able to hack high profile accounts like White House, the U.S. Space Force, and Sephora simply by chatting with a support bot. why would an AI chatbot be al
This post likely references the popular 'This is Fine' meme featuring a dog in a burning room, often used to comment on problematic situations being accepted or ignored. Without access to the specific
This Thursday: Idea → Money. @raymmar and I are taking a real project live, all the way from prototype to monetized: 1. Prototype the idea into a working build 2. Build in the monetization 3. Set up t
arXiv:2606.01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordinatio
arXiv:2606.00966v1 Announce Type: new Abstract: Vision-Language Action (VLA) models continue to face challenges such as slow inference speed and difficulty performing fine-grained motion adjustments,
arXiv:2606.00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) infer
Anna Tong / Forbes: Thrive Holdings, a spinoff of Thrive Capital, commits $1B to acquire local accounting firms through its subsidiary, Current, and use AI to automate them — In Thrive Holdings' live-
arXiv:2606.00592v1 Announce Type: new Abstract: Effective visual communication stems from the harmony of multiple design principles, such as readability, contrast, alignment, overlap, and coherence, w
arXiv:2606.02058v1 Announce Type: new Abstract: Event cameras emit asynchronous events in response to environmental appearance changes. The scarcity of real-world event datasets makes simulation essen
arXiv:2606.00232v1 Announce Type: new Abstract: We study fact-level repair for multimodal generation, where a fluent output may contain specific facts that are not supported by the input. Existing inf
arXiv:2606.01670v1 Announce Type: cross Abstract: Recently, Generative Recommenders (GRs) have emerged as a transformative recommendation paradigm by replacing traditional item IDs with semantic indic
arXiv:2606.01169v1 Announce Type: cross Abstract: Spacecraft collision avoidance for low-thrust satellites often requires determining not only how to maneuver, but also how late a maneuver can begin w
arXiv:2606.02142v1 Announce Type: new Abstract: The ongoing digitization has led to a proliferation of time-series data streams that monitor a variety of processes, from which valuable insights may be
arXiv:2606.01498v1 Announce Type: cross Abstract: Time series data inform critical decisions across many real-world domains. While large language model (LLM) agents can analyze data through natural la
arXiv:2606.00895v1 Announce Type: cross Abstract: This paper presents a fast, recursive neural solver for the J2-perturbed Lambert problem based on Tiny Recursive Models (TRM), termed the TRM-Perturbe
title undersells it - this @workos talk is doing v well and is the first to seriously challenge @mattpocockuk in weeks. team is ab testing My talk from AIE Europe is up! Come learn the lessons I learn
arXiv:2606.01591v1 Announce Type: new Abstract: The TimeLogic Challenge evaluates formal temporal-logic reasoning over video - 16 operators (before, after, until, since, always, co-occur, ordering, ..
arXiv:2606.01540v1 Announce Type: cross Abstract: Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation inv
🚨 Today is a milestone in US AI policy, and an unbelievable moment for me, personally. 🚨 Here’s what I told @senjohnkennedy was the most important policy to implement, at the US Senate in May 2023, an