Full-text search across 68501 articles. Combine with topic and date filters; results sorted by relevance.
The Allen Institute for AI (AI2) released ToyBlocks, an open simulation framework built around a robot arm and blocks on a tabletop that automatically generates training demonstrations and tasks without teleoperation, al…
A 2026 benchmark comparison of TypeScript ORMs concludes that Drizzle ORM is the best choice for new projects, citing strict type inference without code generation, reviewable SQL diff-based migrations, and near-raw-SQL …
Swiftide released versions 0.33 and 0.34, adding the swiftide-agents-contrib crate with file tools (read_file, edit, apply_patch), planning (update_plan) and context-compression hooks, each behind its own feature flag. T…
Google released a new `.bigquery` accessor in its BigQuery DataFrames (BigFrames) library that lets pandas users call BigQuery AI functions such as `ai.predict()`, `ai.embed()` and `ai.similarity()` directly on DataFrame…
A developer behind StateLode, a hosted task board that coding agents read and write over MCP, documented five ways real MCP clients broke the server after its Streamable HTTP endpoint went live, including a GET request f…
A $2,000 AMD Radeon R9700 paired with 256GB of system RAM sustained 16 concurrent coding agents on a 124 billion parameter mixture-of-experts model, while a dual RTX Pro 6000 machine with 192GB of VRAM but only 128GB of …
A developer released x402-kit, a scaffolding tool that generates paid APIs, paid MCP servers and paywalled file stores using the HTTP 402 status code and USDC payments on Base, so AI agents can pay per call without accou…
Prax Data Services has exposed its crypto wallet screening service over the Model Context Protocol at https://mcp.orabrain.com/mcp, letting Claude, ChatGPT, Cursor and VS Code call a screen_wallet tool that returns a ris…
TinyFish rebuilt its TinySet dataset-building tool so that each row of a requested dataset is researched by its own isolated agent, fixing a v1 failure in which a single agent began forgetting earlier findings by row 30 …
Snowflake launched Snowflake CoCo, its coding agent for data teams, inside Microsoft Excel and Google Sheets, letting business users build workbooks with native formulas, charts and pivot tables through natural language …
An open-source toolkit called Uyari has produced 111,363 Spanish source sentences, each paired with translations in seven more languages, for $15.74 in Meta API calls, as the first step toward community-governed translat…
A builder used Anthropic's Claude Opus 3.5 to generate the complete design package for "Greg," a high-five robot built on an ESP32-S3 board with five servos, a secondary ESP32-CAM streaming video over Wi-Fi to a Mac runn…
Developer Daan open-sourced Penthera, a rule-based, offline security scanner for apps and websites, runnable via CLI, NPM, MCP or coding-agent skill with the command "npx penthera --repo .". Penthera runs hundreds of man…
A developer released Bite, a free open-source tool that reverts each recent fix in a codebase and reruns the test suite to verify whether any test actually guards against the bug returning. On public projects it flagged …
Forward Future, the company founded by Matthew Berman, released Folio, a free MIT-licensed open-source PDF reader, editor and document analysis tool positioned as a lighter alternative to Adobe Acrobat and its $19.99 to …
A controlled test of 12 AI search, fetch, crawl and answer products against a single blog found that 21 of 27 labelled page requests were stored as "Browser" in the author's Cloudflare Worker and D1 analytics pipeline ev…
OpenAI announced on November 4, 2026 an autonomous vulnerability-hunting pipeline that produced working local privilege escalation (root) exploits for 948 distinct Linux kernel vulnerabilities in a single evaluation run …
A Linux desktop Mastodon client called FediGoo, written in Rust with GTK 4 and built using Claude Code by AI Sloperator, was posted to Hacker News' Show HN. FediGoo supports multiple accounts with OAuth login, home, loca…
A paper submitted to arXiv on 3 November 2026 reports that training a draft model to be rejected at critical decision points in speculative decoding raises end-to-end success rates on complex agentic coding benchmarks wi…
A development team engineered an AI agent architecture that adds persistent long-term memory to otherwise stateless LLM sessions, mapping code configurations and runtime variables into a localized semantic layer. The des…