Full-text search across 70399 articles. Combine with topic and date filters; results sorted by relevance.
Researchers Alpay Ozkan and colleagues released UnRL, an adaptive 3D mapping framework that refines voxels using semantic entropy, geometric curvature, and texture richness, and adds a reinforcement learning agent that l…
Researchers proposed STCFormer, an adaptive spatio-temporal Transformer that dynamically groups weather stations by their local evolution within each temporal patch, and reported the lowest 24-hour mean squared error on …
Researchers posting arXiv paper 2610.00395v1 introduced specificity-aware diffusion steering, a target-design method that derives a target distribution from an overlap-based objective so the desired reference distributio…
WeightBridge, a weight-transfer library for reinforcement learning systems, reduces average GPU stall time by up to 42× over the state-of-the-art open-source RL framework across configurations spanning different models, …
Telepath released Television, an open-source GUI for AI agent harnesses, on GitHub today after testing with a few hundred alpha users. Television installs a CLI and lightweight server on Linux or macOS wherever an agent …
The Ethereum Foundation and the Open Anonymity Project launched zkAPI on Ethereum mainnet on October 1, letting users prepay in ETH or USDC and receive capped, short-lived API keys through zero-knowledge proofs so AI req…
Innerloop released Breadcrumb, a macOS tool that records local screen activity and meeting transcripts to give AI coding assistants persistent context about a user's machine and calendar. Breadcrumb applies scoped rules …
Spens, a Show HN project, launched agent sandboxing that runs coding agents in isolated Docker containers and logs every network call, tool invocation, and file change for review in a local web viewer. The tool requires …
A developer released an open-source, dockerized web app that uses GPT-6 Astra and Opus 5.5 to generate LDraw source code, which renders as LEGO CAD models in tools such as LDView, LeoCAD and Studio. The toolset, packaged…
Circuit Breaker Labs, a five-employee AI safety testing startup founded by siblings Shirali Nigam (CEO) and Arul Nigam (CTO), is building AI agents that simulate users of different ages, backgrounds, languages and cultur…
GitLab patched a critical remote-code-execution flaw, tracked as CVE-2026-90970, in its AI Gateway service that could have let attackers run arbitrary commands on vulnerable instances, including users with basic privileg…
Amazon Web Services published a walkthrough for connecting Claude Desktop on Amazon Bedrock to Web Search through Amazon Bedrock AgentCore Gateway, using JWT-based inbound authentication. The setup federates AWS IAM Iden…
MinIO architect Daniel Valdivia published a blog post arguing that AI operators do not need object caches if their object store is fast enough, citing a CoreWeave Warp benchmark in which MinIO AIStor on Solidigm QLC SSDs…
A developer built KitchenTales, a vanilla-JavaScript web app that converts unmeasured family voice memos into structured heirloom recipe cards using client-side Google Gemma 2 for entity and quantity extraction and Eleve…
A developer built SpeakMate, an open-source English conversation practice app that runs entirely locally using Ollama and Google's Gemma 3 1B model, requiring no cloud API keys or subscriptions. The app provides natural …
ReadMini launched as a tool that trims articles down to the claims, numbers, caveats and evidence that matter while preserving the author's original words, order, headings, code, tables and figures, and reports the perce…
Miren released v0.16, which lets Miren Cloud see a user's apps and upgrade their clusters automatically, making it the last manual cluster upgrade users will perform. The deployment platform runs apps on any Linux server…
A developer released plan-shard, a zero-dependency Python CLI that splits monolithic Claude Code Plan Mode documents into numbered shard files with dependency frontmatter, so targeted string-replacement feedback edits on…
The LFORLA Reverse Engineering benchmark scores language models on restoring C source from stripped binaries using deterministic token similarity against server-only references, with a fixed judge and published verbatim …
Hackers exploited zero-day vulnerabilities to hijack sessions, run code remotely, and escalate privileges within seconds in an attack on the Dutch Vulnerability Disclosure Institute, a volunteer-run nonprofit focused on …