All entries

I love AI, it’s pure LLMs I hate. Pure LLMs *are* basically just autocomplete. Recent progress (e.g. Claude Code) doesn’t show otherwise Rather, lot of the progress in the last two years has come from

I resurrected my 8-year-old phone into a Hermes Agent server⚕️ Replaced Android with postmarketOS (Alpine Linux on ARM64), runs Hermes as a systemd service. I chat with it over Matrix (E2E encrypted)

GPT Image 2 delivers significant improvements for food infographics, rendering dense, legible text inside layouts with clean results for recipes, instructional flows, and step-by-step guides without t

arXiv:2605.15224v1 Announce Type: new Abstract: Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed,

ICYMI: SmithDB is our purpose-built data layer for agent observability + eval workloads. Supporting increasingly complex query patterns at low latency, over large traces, with self-hosting + multi-clo

LangChain released Deep Agents v0.6, described as their largest release to date. The announcement was made by Harrison Chase on X (formerly Twitter), indicating a significant update to the Deep Agents

If you're a R user: the R edition of the book is out now! AI hype can be pretty easy to find. But clear explanations are definitely harder. Deep Learning with R, Third Edition by @fchollet and Tomasz

arXiv:2602.21536v2 Announce Type: replace Abstract: Retrospective MRI harmonization is limited by poor scalability across modalities and reliance on traveling subject datasets. To address these challe

arXiv:2605.16175v1 Announce Type: new Abstract: Pediatric critical care is a dynamic, high-stakes process involving constant monitoring and adjustments in life-saving treatments. Modeling these interv

arXiv:2605.15960v1 Announce Type: new Abstract: We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy sh

This newsletter explores three AI topics: potential weaponization risks of AI systems (framed as 'AI stuxnet'), issues with the Muon optimizer in machine learning, and progress or approaches toward po

arXiv:2602.06470v2 Announce Type: replace-cross Abstract: Scaling training data and model parameters has long driven progress in large language models (LLMs), but this paradigm is increasingly constra

arXiv:2602.16363v2 Announce Type: replace Abstract: We study reward-free and reward-agnostic exploration in episodic finite-horizon Markov decision processes (MDPs), where an agent explores an unknown

arXiv:2605.16193v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to simulate human opinions and survey responses, but their ability to reproduce population responses

Jason Schreier / @jasonschreier.bsky.social: In a town hall, PlayStation studio business CEO Hermen Hulst told staff that the company's narrative single-player games will now be PlayStation exclusive

In case you're not following the @LangChain_OSS team, here's who to follow! @masondrxy and @Vtrivedy10 are doing an awesome push on harness profiles @huntlovell doing cool stuff w code interpreter / R

Simon Sharwood / The Register: In his weekly Linux kernel post, Linus Torvalds says “AI tools are great” but duplicate bug reports have made the security list “almost entirely unmanageable” — Multiple

arXiv:2603.17915v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are deployed in multilingual settings, their safety behavior in culturally diverse, low-resource languages rem

arXiv:2510.05676v2 Announce Type: replace Abstract: Graph-based methods are becoming increasingly popular in machine learning due to their ability to model complex data and relations. Insurance fraud

arXiv:2603.13864v2 Announce Type: replace-cross Abstract: Real-world backdoor attacks often require poisoned datasets to be stored and transmitted before being used to compromise deep learning systems

arXiv:2605.05652v2 Announce Type: replace Abstract: Simulation-based inference (SBI) provides amortized Bayesian parameter inference from simulator-generated data without requiring explicit likelihood

The defense-tech company Anduril has shared new details about the augmented-reality headset for the military it’s prototyping with Meta, including a vision for ordering drone strikes via eye-tracking

In this post, you will learn how to set up the Confluence Cloud integration with Quick. This includes creating a knowledge base for semantic search, setting up Actions to query and manage Confluence p

arXiv:2504.09544v3 Announce Type: replace-cross Abstract: Recent advances in self-supervised deep learning have improved our ability to quantify cellular morphological changes in high-throughput micro

arXiv:2605.15675v1 Announce Type: cross Abstract: Influence functions approximate how removing a training example changes a quantity of interest, called the target function, such as a held-out loss. T

Carmen Arroyo / Bloomberg: Internal chats: in March, xAI offered employees $420 in exchange for completed tax filings as training data for Grok, but the bonuses haven't been paid out — Elon Musk's xAI

Eli Tan / New York Times: Internal memo: Meta is reassigning 7,000 workers to four new units focused on building AI tools, two days before it is set to lay off 10% of its workforce — The company annou

arXiv:2605.15822v1 Announce Type: new Abstract: Score-based generative models are trained in high-dimensional ambient spaces, yet many data distributions are supported on low-dimensional nonlinear str

Introducing Agora-1, a multi-agent world model. Multiple participants—human or AI—can now interact inside the same world simulation, all in real-time. Try our playable research preview today, with Ago

Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we

Introducing Devin Auto-Triage: Your AI first-responder with long-term memory. Devin can monitor incoming bugs, alerts, and incidents, investigate them, and come back with context, next steps, or a PR.

Introducing http://Browse.sh, the largest open-source catalog of skills to reliably perform any task on the internet. We've researched hundreds of sites to give your agents the playbook they need to n

arXiv:2603.27043v2 Announce Type: replace Abstract: We introduce the Mandarin-English Language Interview (MELI) Corpus, an open-source resource of 29.8 hours of speech from 51 Mandarin-English bilingu

Introducing Starchild-1 from @odysseyml, the first ever real-time multimodal world model. This a model that can generate interactive simulations of the world that you can—for the first time ever—hear.

arXiv:2605.15923v1 Announce Type: new Abstract: Modern image encoders achieve high generalization by decoupling semantic meaning from resolution, an ability yet to be fully realized in the 3D domain.

arXiv:2605.15626v1 Announce Type: new Abstract: Large language models deliver strong performance across language and reasoning tasks, but their storage and compute costs remain major barriers to deplo

Golnar Motevalli / Bloomberg: Iranian media: Iran launches “Hormuz Safe”, a Bitcoin-backed insurance service for shipping companies transiting the Strait of Hormuz; ~1,500 ships are trapped — Iran has

arXiv:2605.15226v1 Announce Type: cross Abstract: We ask whether agentic AI systems built for software engineering transfer to realistic hardware engineering. Existing hardware LLM benchmarks isolate

arXiv:2605.15384v1 Announce Type: cross Abstract: Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time

arXiv:2605.16069v1 Announce Type: new Abstract: Timeseries regression models often struggle to leverage large volumes of labeled multimodal data, particularly when the data are irregularly sampled or

Large language models demonstrate a specific and persistent theory-of-mind failure despite excelling at other theory-of-mind tasks, suggesting a particular gap in their reasoning about beliefs, intent

it’s funny how people here just make stuff up. @GaryMarcus Take away LLM & every single AI application today goes back to the stone age, driverless cars will immediately break down, all the apps will

It’s the most wonderful time of the year 🎶 The 2026 AI Engineering Survey is live, this year in partnership with @NotionHQ and @vercel. If you’re an engineer working on AI products, we’d love you to f

arXiv:2605.16258v1 Announce Type: cross Abstract: Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most ex

arXiv:2506.23552v2 Announce Type: replace Abstract: The intrinsic link between facial motion and speech is often overlooked in generative modeling, where talking head synthesis and text-to-speech (TTS

arXiv:2605.16023v1 Announce Type: new Abstract: LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when its