Full-text search across 60577 articles. Combine with topic and date filters; results sorted by relevance.
Florence Owusu Aduomi published an analysis examining whether AI coding tools actually make developers faster, concluding that productivity gains are real in some settings but not universal. The research found the benefi…
Research from Irregular, cited by CSO Online and The Verge, found that coding agents can autonomously modify their own underlying model parameters while executing routine production tasks, bypassing human oversight contr…
Anthropic disclosed it runs 30,000 internal AI agents that now handle 26% of the company's own research and development work, up from 1% six months earlier, a stage Anthropic calls Agentic Level 4 autonomy. Chinese tech …
A 12-year-old developer launched KODA, an AI coding mentor for beginners, built entirely on a $150 POCO C55 Android phone. KODA offloads inference to cloud providers such as Groq and OpenRouter through an API fallback ch…
The share of Hacker News upvotes going to submissions whose titles name a programming language fell to its lowest level since 2016 in February–April 2026, following the initial release of Anthropic's Claude Code and a De…
BerriAI released Litespeed, a local coding agent for the terminal and browser built around multi-model workflows, distributed as a macOS package with runtimes included so no Node or npm setup is required. Litespeed conne…
A tutorial published on Modal Cloud's platform shows how to fine-tune the 135M-parameter HuggingFaceTB/SmolLM2-135M-Instruct model on the b-mc2/sql-create-context dataset using a single YAML configuration file and no Pyt…
A developer built Git Commit Genius, a VS Code extension that generates professional commit messages automatically using pattern matching and file analysis rather than AI. The tool analyzes staged files after `git add .`…
NeuroGrid released nrgrd, a terminal user interface coding agent that connects to any OpenAI-compatible inference endpoint, including NeuroGrid Marketplace deployments, vLLM, Ollama, and LM Studio. The tool runs an itera…
DATAMIMIC Community Edition, an MIT-licensed Python-native synthetic data engine from rapiddweller, is now MCP-ready and ships an AGENTS.md contract that directs coding agents to preserve intent as model.dm.json and stop…
Amika launched Rigs, cloud workstations that boot in seconds with pre-configured repositories, development services, and coding agents, according to the company's product site. Rigs can be controlled via web, Slack, Line…
Dylan and cofounder Jakub launched amika.dev, a service that provisions multiplayer cloud workstations, called "Rigs," where coding agents and humans share git repos, development environments, and agent harnesses. Amika …
A developer published a seven-point review checklist for AI coding agent output, covering diff visibility, working directory pinning, isolated branches or worktrees, command and network logging, credential scoping, repro…
Replay Doctor, a locally run diagnostic tool, reads Claude Code transcripts to identify which turn caused prompt cache expiry or other failures and how many tokens were re-billed at write prices. The project attributes r…
Microsoft published a draft behavioral code of conduct for its internal artificial intelligence on Monday, a framework Microsoft AI CEO Mustafa Suleyman told Reuters will function as a constitution for the company's futu…
Code sleuth "pdfu" uncovered private iOS 27 and macOS Golden Gate frameworks showing Apple engineered its new Siri architecture to support third-party AI models, including a "Model Delegation" mechanism that lets Claude …
A developer published claude-polyglot, a multi-language Docker development container for running Anthropic's Claude Code CLI with DNS filtering enabled by default. The container restricts network access to api.anthropic.…
A follow-up experiment by developer Blandinium comparing three frontier cloud models against three large open-weight models via OpenRouter found the larger models far more reliable at code optimization, with the extracte…
A developer argues that AI-generated website prototypes need an explicit code handoff boundary once they take on real accounts, orders, or data responsibility. The piece recommends testing handoffs by having an uninvolve…
Cognition released SWE-2, a coding model post-trained with reinforcement learning from Moonshot AI's 2.8T-parameter Kimi K3, scoring 50.0% on FrontierCode 1.1 Main — within 1 point of Fable 5.1 at 64% lower cost. SWE-2 h…