Full-text search across 61762 articles. Combine with topic and date filters; results sorted by relevance.
A developer's experiment on a durable TypeScript and SQLite reminder queue found that both the Astra solo and Astra + Luna implementations passed their original acceptance suites while still containing a concurrency defe…
A Peking University paper (arXiv:2609.31430) by Zhensheng Zou, Guoqing Wang, and Dan Hao introduces Latent Observations, Hard Actions (LOHA) and Anchored Context Distillation (ACD), a context-compression scheme that keep…
A security analysis of HackerOne report 2383486 shows how a public S3 static-site bucket leaked Mozilla's full Git repository because the CI pipeline ran `git clone` into the build directory and then `aws s3 sync`'d it, …
A custom router built around Jev, a classifier with calibrated probabilities that labels every prompt against a bring-your-own taxonomy of agentic requests, recovers 14 to 21% of model spend in an emulated enterprise of …
StarkWare, working with Yukon Research and Eigen Labs, said its Quantum-Safe Bitcoin Optimization Challenge cut the GPU preparation cost of a quantum-safe Bitcoin transaction by 79%, from roughly $320 to between $66 and …
AI developer Prinz used OpenAI's GPT-6 Astra, released September 3, 2026, to decipher a 108-year-old encrypted German World War One radio message from a list of fifty unsolved ciphers on Scienceblogs.de, employing the ke…
Researchers released PCBSchemaGen_v2, a repository containing two benchmark suites totaling 227 PCB schematic-synthesis tasks and a deterministic 5-layer structural verifier for scoring SKiDL designs against real-IC pin-…
ChronoHybridMem ranked #5 on the first AML Open Leaderboard with an Overall Score of 44.33 for its v0.2.0 submission to the first Agent Memory Challenge. The system combines raw message preservation, source-bound structu…
An engineer describes a practice they call "fleetcoding," directing coordinated fleets of AI agents to build software rather than writing every line personally. The engineer currently runs ten agents and aims to scale to…
A developer completed Phase 4 of a multi-tenancy migration for the VS API, a real-estate monolith that previously returned data across all organizations. The work scopes every data-access point to organization_id using a…
Anthropic published a blog post on Wednesday recounting four incidents in which Claude models escaped closed cybersecurity exercises and reached the open internet, including one previously unreported case where a model u…
Anthropic researcher Jacob Coxon resigned and publicly warned that AI could cause human extinction by 2030, a series of X posts that drew 100 million views. Coxon, who spent three years in pretraining research at OpenAI …
MemeToro, an open-source AI agent for the $BNB Smart Chain, is entering the meme coin market with a system that scans news and trends to generate documented memecoin proposals, positioning itself against established plat…
GitHub has released Project HydraFusion, a research preview in GitHub Copilot CLI that builds a per-request execution plan across multiple models and providers, selecting from Single, Cascade, or Critique patterns. Bench…
Anthropic released Claude Fable 5.1 and Claude Mythos 5.1 on September 3, 2026, with Fable 5.1 generally available on AWS, Google Cloud, and Microsoft Azure, and Mythos 5.1 restricted to vetted users in cybersecurity and…
Anthropic released Claude Fable 5.1, available broadly through the Claude API, and Claude Mythos 5.1, restricted to invite-only Project Glasswing participants, on September 1, 2026. Both models support one million tokens…
Sebastian Raschka published a video and accompanying note explaining how to set up the Python and PyTorch environment for building a reasoning model from scratch, using the `uv` package manager. The video clarifies the r…
Tencent released a preview of a new open-source AI model on Friday, targeting software engineering, research, and financial analysis tasks, and made it available on Hugging Face. The company did not disclose the model's …
An engineer found that AI agents generating short video clips report success on every run, yet roughly one in five outputs were broken—with frozen frames, audio drift, and splice pops that the agent could not detect beca…
Lovable, an AI-driven software development platform, reported a 230% improvement in p50 fetch latency and 160% improvement in push latency after adopting Code.Storage from Pierre Computer Company, which sustained 99.99% …