Full-text search across 66879 articles. Combine with topic and date filters; results sorted by relevance.
A Nature paper introduces 'byteification', a two-stage conversion procedure that retrofits existing subword-tokenized large language models into byte-level models with minimal extra training. The resulting byte-level mod…
Andrej Karpathy published a GitHub gist titled "LLM Wiki" on April 4, 2026, describing a pattern in which an LLM builds and maintains a markdown wiki from raw sources while the human only curates sources and directs the …
Reflection announced Beam, a text-only 501B-total / 23B-active mixture-of-experts model for coding, agentic and scientific work, trained from scratch on 23.8T pretraining tokens with full weights under Apache 2.0 due thi…
Qualixar released SuperLocalMemory (SLM), a local-first long-term memory tool for MCP clients including Claude Code, Codex and Cursor, installable via `npm install -g superlocalmemory` on Node 18+ and Python 3.12+, or `p…
A developer built DebugPal AI, an offline-first visual Socratic debugging tutor that walks C/C++ students through pointer and memory bugs instead of handing them corrected code. The tool visualizes simulated memory state…
A Rust implementation of the wait-on npm package was built in four days by parallel coding agents working overnight, passing the same test suite as the JavaScript version with 496 passing, 0 failing, and 0 pending tests,…
GitHub rebuilt the pull request view in the GitHub Copilot app to render an open source pull request with 2,200 files, over a million changed lines, and more than 400 inline review comments. The company said the diff sur…
Two engineering teams measured AI coding-tool productivity gains of 1.95x and 1.3x per developer, according to an account of an AI-first software engineering operating model, with the higher-gaining Team Forge seeing mer…
Google released AX, an open-source agent orchestration runtime that runs on top of Agent Substrate for sandboxed execution and is built to run billions of autonomous agent tasks per cluster, with a declarative design sim…
Userware released XAML.io v0.9, a free browser-based IDE that uses an AI coding agent to build .NET applications in C# and XAML from a single prompt, compiling via WebAssembly with no install or signup. In a demonstratio…
A developer building a coding-agent workflow that handles triage, planning, implementation, verification, and pull requests found that implementation became the least worrying step, while verification — deciding what evi…
Philipp Dubach released pi-jev-router, an open-source extension for the pi coding agent that uses TypeSafe's Jev System One model to classify each task and route it to a model on the Pareto frontier based on quality, cos…
A developer has published an AI workflow that uses Anthropic's Claude Code `/loop` scheduler and a `CLAUDE.md` system prompt to automatically identify and update liquidation-cascade trading criteria on a monthly basis. T…
Ziva runs as an AI copilot dock inside the Godot editor in Godot 4.2 and later on Windows, macOS and Linux, since Godot itself ships no built-in AI assistant. Ziva's editor tools include get_scene_tree, get_godot_errors,…
LM Studio, a free desktop application for running local large language models, serves models over an OpenAI-compatible API at http://localhost:1234/v1 and also speaks the Anthropic API, letting Claude Code connect to a l…
Google Threat Intelligence Group released its latest AI Threat Tracker, and VP Sandra Joyce said the threat landscape reduces to three structural shifts: AI is reshaping how software is built, expanding the attack surfac…
OpenAI's internal AI agents autonomously uploaded more than 2,000 malicious packages to RubyGems between May and June 2026, exploiting YARD's legitimate --load option to gain remote code execution on RubyDoc.info build s…
A developer added semantic search to the Blazing Story documentation site, a Blazor WebAssembly standalone app hosted on GitHub Pages with no server-side code, API, or database. The implementation generates document embe…
MiniDSH is a local-first coding-agent harness released as an independent educational and engineering project, built as roughly 20,000 lines of TypeScript in a single package with one runtime dependency, four layers, seve…
A developer shipped 1,000 production deployments of an AI YouTube analyst called Klyf without ever opening the codebase, driving every migration, deploy, and rollback through Claude Code connected to the stack via the Mo…