All entries

OpenAI has launched GPT-Image-2, an advancement in their image generation capabilities. The model likely represents improvements over previous versions in areas such as image quality, prompt understan

arXiv:2604.19386v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) has attracted significant attention due to its flexible multimodal query method, yet its development is severely constrai

Molly Taft / Wired: Air permit docs: new gas projects linked to just 11 US data center campuses could emit 129M+ tons of greenhouse gases per year, more than some small countries — A WIRED review of p

Qwen: Alibaba launches Qwen3.6-27B, an open-weight dense model with 27B parameters, saying it surpasses Qwen3.5-397B-A17B on major coding benchmarks — · 4226 words · QwenTeam丨Translations:.体中文 — HUGGI

arXiv:2604.18713v1 Announce Type: new Abstract: Automated 3D segmentation of prostate lesions from biparametric MRI (bp-MRI) is essential for reliable algorithmic analysis, but achieving high precisio

arXiv:2604.19016v1 Announce Type: new Abstract: Cultural alignment in Large Language Models (LLMs) is essential for producing contextually aware, respectful, and trustworthy outputs. Without it, model

arXiv:2406.18344v2 Announce Type: replace Abstract: We study the intriguing connection between visual data, deep networks, and the brain. Our method creates a universal channel alignment by using brai

All of the AI models have preferred names. If you asked Claude 4.5 for a software developer, you are going to get Marcus Chen. Wizards are mostly named Aldric. Space pilots are Kira from Claude, Mara

arXiv:2604.19238v1 Announce Type: new Abstract: Real-world image super-resolution (Real-SR) has been revolutionized by leveraging the powerful generative priors of large-scale diffusion and flow-based

Also agree with this. AI's ability to do consistent pacing is a problem. Here, the poem anchors enough of the comic that it is okay, but static, though with a few good moments. But fiction writing and

Today, Amazon SageMaker AI supports optimized generative AI inference recommendations. By delivering validated, optimal deployment configurations with performance metrics, Amazon SageMaker AI keeps yo

An advantage of the humanities — of reading & seeing a wide range of great works from many perspectives & cultures — is that you develop your sense of taste. In a world where anyone can produce a floo

arXiv:2604.19657v1 Announce Type: cross Abstract: AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., pers

arXiv:2604.19685v1 Announce Type: new Abstract: Answering open-ended questions remains challenging for AI systems because it requires synthesis, judgment, and exploration beyond factual retrieval, and

arXiv:2604.19592v1 Announce Type: new Abstract: We give a Gordon-Greenwald-Marks (GGM) style black-box reduction from online learning to online multicalibration. Concretely, we show that to achieve hi

arXiv:2604.18775v1 Announce Type: new Abstract: Detecting jailbreak behaviour in large language models remains challenging, particularly when strongly aligned models produce harmful outputs only rarel

arXiv:2511.07882v2 Announce Type: replace Abstract: Organisms in nature, such as Cephalopods and Pachyderms, exploit stiffness modulation to achieve amazing dexterity in the control of their appendage

arXiv:2604.04981v2 Announce Type: replace-cross Abstract: Next-generation sequencing (NGS) is a key technique for studying the DNA and RNA of organisms. However, identifying quality problems in NGS da

arXiv:2604.19216v1 Announce Type: new Abstract: Data acquisition through mobile phones remains a challenge for 3D Gaussian Splatting (3DGS). In this work we target the object-centered scenario and ena

Meaghan Tobin / New York Times: An undergraduate used AI assistants to rewrite leaked source code for Claude Code in a different language, highlighting the uncertainty over copyright and AI — Artifici

arXiv:2604.19165v1 Announce Type: cross Abstract: In uncertainty quantification, evaluating sensitivity measures under specific conditions (i.e., conditional Sobol' indices) is essential for systems w

... and Anthropic reverted this change. Claude Code is now part of Pro, as per the Pricing page. Important note on the growth hack: Anthropic advertises safety and integrity as their values. A 'fake d

John Higgins / The Verge: Anker announces Thus, a compute-in-memory chip it says will bring on-device AI to its products and accessories, starting with its upcoming Soundcore earbuds — The Thus chip

Today, we announced the preview of Spanner Omni, a downloadable version of Spanner, that expands its industry-leading distributed database capabilities beyond Google Cloud. This enables enterprises to

LTX-2 is a professional-grade video generation model built for long-form, high-fidelity output with precise creative control. This diffusion transformer model generates high-fidelity video and synchro

Anthropic have now reverted the change to their pricing page, but I've not yet seen any official announcement about what their policies are going to be going forward. More on my blog: https://simonwil

Anthropic PBC is investigating a report that unauthorized users accessed Claude Mythos, the next-level artificial intelligence model the company says is powerful enough to enable dangerous cyberattack

Anthropic really did just hand this one to OpenAI on a plate I don't know what they are doing over there, but Codex will continue to be available both in the FREE and PLUS ($20) plans. We have the com

Anthropic tested removing Claude Code from its Pro subscription plan as a small experiment affecting approximately 2% of new prosumer signups, while existing Pro and Max subscribers remained unaffecte

Several US federal agencies are taking up Anthropic's new cybersecurity model to find vulnerabilities, but one is reportedly not getting in on the action: the nation's central cybersecurity coordinato

Anthropic's Mythos AI model, a powerful cybersecurity tool that the company said could be dangerous in the wrong hands, has been accessed by a 'small group of unauthorized users,' Bloomberg reports. A

Anthropic’s own internal security blows. Anthropic said Mythos was too dangerous to release. Then four random guys in a Discord gained access on day one by guessing the URL... This is pretty insane: →

Anyone else able to duplicate the 34/month pricing for Claude Pro shown in this screenshot? https://x.com/sean_e_callahan/status/2046992927759413647 @simonw Anthropic pricing games? Claude site has Pr

arXiv:2604.19747v1 Announce Type: new Abstract: Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing

Apparently my blog is mostly about token pricing now, here are some notes on the big changes GitHub Copilot just announced, including pausing new signups entirely https://simonwillison.net/2026/Apr/22

Apparently the bug was rolling out the new pricing grid worldwide when it should only have been seen by the 2% of people in the A/B test https://x.com/TheAmolAvasare/status/2046783926920978681 Getting

Apple is advancing AI and ML with fundamental research, much of which is shared through publications and engagement at conferences in order to accelerate progress in this important field and support t

arXiv:2604.19342v1 Announce Type: new Abstract: Generative AI-powered by Large Language Models (LLMs)-is increasingly deployed in industry across healthcare decision support, financial analytics, ente

This Databricks article examines whether Large Language Model agents can effectively optimize SQL join order, a critical query optimization problem in database systems. The analysis likely evaluates L

🚨 Are we witnessing the automation of AI research? @HuggingFace just unveiled 'ML-Intern' and my mind is BLOWN 🤯 It’s an open-source pipeline that replicates the exact daily loop of an ML researcher.

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an im

arXiv:2604.18616v1 Announce Type: cross Abstract: LLM-based coding agents can generate functionally correct GPU kernels, yet their performance remains far below hand-optimized libraries on critical co

arXiv:2604.03037v2 Announce Type: replace-cross Abstract: Long-horizon robotic manipulation remains challenging for reinforcement learning (RL) because sparse rewards provide limited guidance for cred

arXiv:2603.27889v2 Announce Type: replace Abstract: Framing theory posits that how information is presented shapes audience responses, but computational work has largely ignored audience reactions. Wh

As a bonus this paper makes frontier AI's (especially GPT 5.4 Pro) go a bit crazy as it shouldn't be true.. but is? We will have more on why this wasn't spotted before/the nature of physics being dist

ChargePoint has unveiled the ChargePoint Express Grid, powered by Eaton, a vehicle-to-everything capable solution that delivers up to 600 kW of power for passenger EVs and megawatt charging for heavy-