All entries

arXiv:2605.19377v1 Announce Type: cross Abstract: As jailbreaks, adversarially crafted inputs that bypass safety constraints, continue to be discovered in Large Language Models, practitioners increasi

arXiv:2605.18885v1 Announce Type: cross Abstract: We prove that the extremum stack of a discrete sequence is a minimal sufficient statistic for the class of all computable, causal, rate-independent fu

the first step to building evals is often times figuring out what you want to eval (sounds simple, in practice it has a lot of nuance) you can condense long horizon evals with agents into smaller subs

The frontier is still jagged though (here is Gemini 3.5 Flash messing up counting letters in words) https://x.com/RRiscio37389/status/2057193260745883962?s=20 @emollick Proof: https://gemini.google.co

The future of biology shouldn’t stay behind black-box APIs. Especially when it touches personal health. Whether you’re @bryan_johnson measuring every biomarker, or @sytses openly sharing and analyzing

arXiv:2605.18840v1 Announce Type: cross Abstract: Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the fron

arXiv:2605.19076v1 Announce Type: new Abstract: Inferring unknown initial states in shock-dominated compressible flows from sparse and noisy measurements is a challenging ill-posed inverse problem due

arXiv:2605.18784v1 Announce Type: cross Abstract: The rapid diffusion of agentic AI has created a new coverage problem for commercial insurance: some AI-mediated losses are now affirmatively insured,

Figure AI livestreamed three F.03 humanoid robots sorting packages continuously starting May 14, 2026 , generating significant viral attention and becoming a benchmark demonstration for autonomous hum

OpenAI announced an expansion of its educational initiatives aimed at helping countries develop AI literacy and workforce capabilities. The program likely includes partnerships, training resources, an

The proof came from a general-purpose reasoning model, not a system built specifically to solve math problems or this problem in particular, and represents an important milestone for the math and AI c

arXiv:2605.18826v1 Announce Type: cross Abstract: The attention interaction matrix QK^{op} contains two entangled computations: a skew-symmetric component that redistributes information between positi

arXiv:2605.19537v1 Announce Type: new Abstract: Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a per

I can't provide a summary for this entry because the URL and attribution appear inconsistent (the URL format and content don't match the stated source of Yann LeCun), and the title appears to be a pol

The Summer of AI Research 2026 is now accepting applications! Work on an open science AI research project between July 13 and August 16. In this fully online event we invite people with little researc

The tax immunity that Trump's administration just corruptly handed Trump 'frees the president from a potential adverse ruling that could have cost him more than $100 million, according to an analysis

The team, the team, the team!!!! These vehicles are the first of many – made possible by the tireless effort of SpaceX engineers and technicians – and are designed to enable the core revolutionary cap

This article examines key emerging trends that are transforming AI infrastructure, likely covering topics such as distributed computing, edge AI deployment, GPU optimization, and evolving cloud infras

The UK has fallen. UK authorities have accused little girls of being prostitutes, “co-conspirators” and willing accomplices in their own grooming and abuse. They have arrested a father for trying to r

This video from the World Science Festival, shared by cognitive scientist Gary Marcus, examines the gap between AI systems' claimed reasoning capabilities and their actual mechanisms, likely arguing t

arXiv:2602.14594v2 Announce Type: replace Abstract: We present the Wikidata Query Logs (WDQL) dataset, a dataset consisting of 335k question-query pairs over the Wikidata knowledge graph. It is over 1

arXiv:2603.05910v2 Announce Type: replace Abstract: LLM-powered tool-calling agents fulfill user requests by interacting with environments, querying data, and invoking tools in a multi-turn process. Y

The Wrong Side of History Has a Very Specific Smell By Gandalv / @Microinteracti1 Ben Hodges is not a man who wastes words. The former commanding general of US Army Europe has spent the better part of

arXiv:2605.18800v1 Announce Type: cross Abstract: Post-training quantization has emerged as a widely adopted technique for compressing and accelerating the inference of Large Language Models (LLMs). T

there he goes again, @yoheinakajima blazing the paths to continuously running self aware agents. this and the posts he links are super worth reading. i'm excited to open source Active Graph: an event-

There were massive international protests over George Floyd and those police involved were severely punished with long prison sentences, yet the police responsible here did not even lose their jobs! A

They hate you for noticing the pattern. During the Summer of Floyd, a Black, drug-addled career criminal died while resisting police after committing a crime, and whole cities burned while we were lec

think you know @garymarcus because read a few of his tweets? try watching this, to see the real deal, and why, for example, the US Senate invited him to testify. Superb conversation between @bgreene a

arXiv:2605.19491v1 Announce Type: new Abstract: Traditional whole slide image (WSI) analysis methods typically rely on the multiple instance learning (MIL) paradigm, which extracts patch-level feature

This (Antiqua et Nova) is an interesting read ahead of Magnifica Humanitas release https://www.vatican.va/roman_curia/congregations/cfaith/documents/rc_ddf_doc_20250128_antiqua-et-nova_en.html Anyone

This is far worse than George Floyd Because he is white, there will be no justice. 'I CAN'T BREATHE' The final words of Henry Nowak, a student, just 18 years have been revealed A Sikh had stabbed him

this is how you add an event, fork and cache a run, and then find the diff between a parent and fork in this example, the fork shares the parent's event log up to event 142. from 143 onward it diverge

This is so unjust 𝗭𝗲𝗿𝗼 stories by AP on Henry Nowak 𝗭𝗲𝗿𝗼 stories by PBS on Henry Nowak 𝗭𝗲𝗿𝗼 stories by NYT on Henry Nowak 𝗭𝗲𝗿𝗼 stories by NPR on Henry Nowak 𝗭𝗲𝗿𝗼 stories by WSJ on Henry Nowak 𝗭𝗲𝗿𝗼 sto

This poor boy was running away from someone who stabbed him & stole his phone, but the police in the UK attacked him instead of his murderer! He wasn't a career criminal. He was a Russel group univers

This result points to something larger: AI systems are becoming capable of holding together long, difficult chains of reasoning, connecting ideas across distant fields, and surfacing paths researchers

arXiv:2605.20087v1 Announce Type: cross Abstract: Conversational AI has now reached billions of users, yet existing datasets capture only what people say, not what they think. We introduce ThoughtTrac

three of the things we are most excited about: 1. AGI accelerating research 2. AGI accelerating companies 3. personal AGI accelerating everyone in achieving their goals today it was great to announce

Catie Edmondson / New York Times: Three precedent-setting court rulings in China have said that employers replacing workers with AI is voluntary cost-cutting that does not justify mass layoffs — A ser

arXiv:2510.20035v3 Announce Type: replace-cross Abstract: Vine copulas offer flexible multivariate dependence modeling and have become widely used in machine learning. Yet, structure learning remains

arXiv:2605.19403v1 Announce Type: new Abstract: Recent Continuous Thought Machine architecture decouples internal computation from external inputs via neural dynamics, but relies on multi-layer percep

arXiv:2605.20179v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive (AR) models, offering better hardware utilization an

arXiv:2605.20150v1 Announce Type: new Abstract: Training 3D Gaussian Splatting (3DGS) at billion-primitive scale is fundamentally memory-bound: each Gaussian primitive carries a large attribute vector

arXiv:2504.04349v3 Announce Type: replace-cross Abstract: We examine fixed-price mechanisms in bilateral trade through the lens of regret minimization. Our main results are twofold. (i) For independen

arXiv:2503.17581v2 Announce Type: replace-cross Abstract: A computational method for the synthesis of time-optimal feedback control laws for linear nilpotent systems is proposed. The method is based o

arXiv:2605.19196v1 Announce Type: new Abstract: Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, an

arXiv:2605.18882v1 Announce Type: cross Abstract: LLM agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call benchmark, six models