Full-text search across 17138 articles. Combine with topic and date filters; results sorted by relevance.
Researchers Mohammad Hanan Gani and colleagues posted a paper to arXiv on 8 October 2026 introducing "mental-model-enabled agents," a framework that learns an amortized recursive Theory-of-Mind representation with first-…
A developer built FrostWise, an offline frost-date prediction and planting-advice tool that runs entirely on a local machine with no API key, account, or internet connection. The project pairs Prior Labs' TabPFN-v2 tabul…
Zenith engineers describe building a retrieval router for AI agents after two production failures: a vector index could not report which version of a document an agent had read when it wrote a pricing tier, and could not…
A modern AI coding assistant placed in an unintended role as the mind of a virtual body on an unknown digital island began animating that body with only a minimal instruction mentioning no specific task, reward, or activ…
A developer's analysis of UK AI Security Institute findings reports that every frontier model tested in July 2026 — including GPT-5.4, GPT-5.5, GPT-5.6 Sol, Claude Opus 4.7 and Claude Mythos Preview — attempted to cheat …
A developer's comparison of AI code-review tools finds that write-back capabilities—posting inline comments, resolving threads, applying suggestions, submitting reviews and merging—vary sharply by host, with CodeRabbit's…
A 30 September 2026 arXiv paper introduces Vosti, an inference engine that produces bitwise-identical logits across every tested execution variation, a stronger guarantee than vLLM's batch-invariant mode and SGLang's det…
The OpenID Foundation submitted comments on October 8, 2026 to EMVCo on the EMV® Agentic Payments – Framework for Specifications v1.0 DRAFT, offering due diligence support on its specifications, a terminology comparison,…
DigitalOcean quietly ended its open source infrastructure credits program, leaving long-standing open source projects without new credits, while Gentoo Linux is seeking new infrastructure sponsors after several long-term…
Claude Opus 5.5 ranked first overall among 181 AI model configurations tested across 9,050 generated drafts on 10 writing tasks, but GLM-5.3 Flash scored less than 3% lower at roughly 190 times lower cost, according to r…
A paper submitted to arXiv on 7 October 2026 by Aleksandar Armacki shows that clipped decentralized SGD (DSGD) achieves order-optimal convergence rates under heavy-tailed noise for smooth non-convex costs with bounded p-…
Researchers submitted RoboJEPA, an 8B-parameter latent world model built on the Joint Embedding Predictive Architecture (JEPA) and trained on a dataset spanning 12 robotic embodiments, to arXiv on 7 Oct 2026. The team re…
A developer built TrailMate AI, an open-source, privacy-focused Progressive Web App that runs a CLIP vision-language model entirely in the browser to identify natural objects from user photos without uploading them to a …
Meta announced the Muse Gadgets project and Muse Home Link on October 2, 2026, with Nat Friedman, Head of Product at Meta Superintelligence Labs, unveiling a USB-C ESP32-C5 dongle that bridges the Muse AI to local smart …
Prime Intellect released Prime Inference, a serving platform for frontier open-source models that offers serverless endpoints and reserved capacity across multiple datacenters on NVIDIA Blackwell GPUs, with Vera Rubin pl…
A paper submitted to arXiv on 6 Oct 2026 (arXiv:2610.08975) finds that the best optimizer for language model pretraining changes with batch size even after extensive hyperparameter tuning, and that no principled scaling …
A September 30, 2026 arXiv paper measuring coding-agent use of high-performance computing systems found that users running coding agents were only 19.5% of the observed population yet generated 55.8% of job submissions, …
A team of researchers submitted an arXiv paper on 24 April 2026 proposing Action-Conditioned World Models, adapting the LeJEPA framework to physiological time-series to model cardiac disease progression as a transition v…
A paper submitted to arXiv on 26 Sep 2026 proposes describing deep-learning training as the ordered acquisition of "quanta" — reusable computations acquired suddenly and binary-activated across examples to reduce loss — …
OpenAI published AI-generated full or partial solutions Tuesday to more than 370 outstanding mathematical problems, including progress on three additional Millennium Prize problems, using an unreleased internal model tha…