Full-text search across 71213 articles. Combine with topic and date filters; results sorted by relevance.
Snorkel AI research fellow Gabriel Orlanski submitted a paper on September 29 introducing LibraryDesignBench, a benchmark that scores agent-generated libraries by how well downstream agents use them across 15 library-des…
A senior engineer with 25 years of experience built a 45,000-line Conway's Game of Life application using Spec-Driven Development (SDD) with the BMad method, React, and TypeScript, and documented what worked and what bro…
A developer outlined a five-box RAG architecture diagram — index, retriever, reranker, context builder, and loop controller — arguing that each connecting arrow carries a payload paid for twice: once when moved and once …
Cloudflare is developing an internal AI-powered tool called CryptoLabe to inventory cryptographic usage across its codebase and drive its migration to post-quantum cryptography ahead of a 2029 full-readiness deadline. Cl…
Anthropic's Claude Opus 5.5, which shipped this week, leads SimpleBench at 88.4% and ranks as Anthropic's best vision model to date, according to AI Battle and @skalskip92, performing better than Fable 5 and GPT-6 Sol bu…
A new tutorial demonstrates building an AI agent that processes receipts and invoices inside an E2B Firecracker microVM sandbox, mounting a lakeFS branch as an ordinary filesystem so every change is versioned and isolate…
Anthropic released Claude Sonnet 5.5 on September 28, 2026, priced identically to Sonnet 5 at $2 per million input tokens, $10 per million output tokens and $0.20 per million cache reads, while claiming up to 30% lower c…
A study of Python source generated by multiple LLMs, published in 2025, found it was not possible to reliably predict human versus LLM authorship, according to an analysis of how LLMs handle programming language differen…
Next.js 16 has marked the `instrumentation.ts` file stable, giving developers a single-execution lifecycle hook that runs before middleware, route handlers, or React components load, so observability SDKs like OpenTeleme…
Hamel Husain and Shreya Shankar, drawing on work with over 50 AI companies, published an advanced follow-up on building eval systems for AI products, arguing that most teams skip the critical step before writing metrics …
Security researchers at Hacktron chained a libheif image-decoding heap overflow with an OpenAI SSO misconfiguration to compromise employee accounts and reach internal GitHub repositories, according to a published report.…
A team that replaced 40% of its end-to-end regression suite with AI-generated Playwright tests found that 85% of simple happy-path tests passed their first CI run, but the scripts consistently failed at state management,…
Six independent reimplementations of Jev, a non-generative "System 1" decision model launched on Wednesday, appeared within two days of its release, according to AINews' 9/17/2026-9/18/2026 roundup. The clones include La…
Wood Mackenzie built APEX (Agentic Platform for Energy eXperience), a shared agentic platform on Amazon Bedrock AgentCore, after finding that 88 percent of its AI proofs-of-concept never reach widescale deployment. The p…
A February 2026 ETH Zurich study by Gloaguen, Mündler, Müller, Raychev and Vechev, "Evaluating AGENTS.md," found that automatically generated context files lowered AI agent success rates by 3 percent on average and raise…
Amazon Web Services released 38 open-source agent skills spanning 11 healthcare and life sciences domains under the MIT-0 license, encoding domain decision procedures in SKILL.md markdown files that agents consume at inf…
Diogo Almeida, who helped develop ChatGPT and instruction-following research at OpenAI, launched Jev through his company TypeSafe, a System One AI model that does not generate text and instead returns typed probabilistic…
Uber and ServiceNow exhausted their entire annual allocations for Anthropic's tools within the first months of 2026, with Uber capping spending at USD 1,500 per employee per tool each month, according to The Information.…
A developer community analysis argues that 2026's leading large language models are deliberately trained to minimize stored factual knowledge in favor of compact, reusable reasoning procedures, citing Simon Willison's te…
AI sprint assistants like Atlassian's Delivery Agent and AI Sprint Planning Assistant, along with marketplace tools such as Spinach.io, SprintPoker, and Agile Poker for Jira, are automating Agile ceremonies including sta…