Full-text search across 58582 articles. Combine with topic and date filters; results sorted by relevance.
A data scientist evaluated 10 AI coding models across 5 tasks, finding that DeepSeek-R1 scored highest at 9.4 but cost $2.50/M tokens, while Qwen3-Coder-30B offered the best balance at 8.8 and $0.35/M tokens. The analysi…
OpenAI endorsed the European Commission's voluntary Code of Practice on Transparency of AI-Generated Content on June 11, 2025, committing to use provenance tools like C2PA Content Credentials and SynthID watermarks to co…
Spec-Driven Development (SDD) is a workflow that moves through five phases—requirements, design, tasks, implementation, and validation—each producing reviewable artifacts to reduce ambiguity before code changes. The appr…
A senior software engineer warns that AI coding agents, while boosting productivity, erode developers' understanding of their own codebases by breaking the feedback loop between writing and comprehension. The hidden cost…
Microsoft's Visual Studio Code now supports using locally hosted LLMs for chat, tools, and MCP servers via a new 'air-gapped' mode, enabling offline AI workflows without GitHub sign-in. Users can integrate models like th…
Anthropic released dynamic workflows for Claude Code that let the AI write and execute its own multi-agent orchestration scripts on the fly, addressing agentic laziness, self-preferential bias, and goal drift by spawning…
Agent Trace, an open specification for tracing AI-generated code, was released as an RFC in January 2026. It provides a vendor-neutral format to record AI contributions alongside human authorship in version-controlled co…
Microsoft released FastContext, a system that trains a dedicated explorer subagent to handle repository exploration for coding agents. By offloading read-only searches and returning compact file-line citations instead of…
Developers are increasingly switching to local LLMs for coding tasks, with two Hacker News threads (1,260 and 1,350 points) confirming local models are now viable. The guide compares self-hosted inference (Ollama, llama.…
Moonshot AI released Kimi K2.7-Code, a coding-focused agent model with 1 trillion total parameters and a 256K context window, aimed at multi-step software engineering tasks. The Beijing lab positions the open-weight mode…
Coding agent sandboxes address host compromise but not credential authorization, leaving agents with high-scope tokens that can push to protected branches, deploy infrastructure, or read secrets. The real risk is authori…
Anthropic, OpenAI, Cognition, Sierra, LangChain and leading practitioners have jointly developed a canonical standard for building production-grade agentic products, codified in a new open-source repository. The standard…
MoonieCode, a minimal AI coding assistant built in 393 lines of C++23 that communicates with Claude via HTTP requests. Its core logic is a single while loop that sends user prompts as JSON to an LLM API, then handles two…
KingBench 4, an independent benchmark scoring five AI coding models on six difficult software projects out of 10, found Anthropic's Opus 5.5 leading the hardest tasks with wins on the emulator (3.7/10), keyboard app (7.5…
A July 2026 study from Carnegie Mellon and Stanford researchers, "AI Writes Faster Than Humans Can Review," found that pull request volume grew 3.1× while the reviewer pool grew only 1.5× across 802 developers and nearly…
A developer built Chisle, a Claude Code plugin that trims token usage, and benchmarked it against the caveman and ponytail plugins plus a no-plugin baseline across 20 live tasks and 59+ model runs on Haiku and Sonnet. Ch…
A developer analysis argues that AI coding assistants like Cursor, Claude, and GitHub Copilot are driving up CI/CD costs under per-build-minute pricing, citing a 20-developer team running roughly 25,000 build minutes per…
A developer released Crowsnest, a private local macOS workspace that lets users run Claude Code and Codex sessions across multiple accounts, continuing work on a second subscription account when one hits its provider quo…
A developer built a Python CLI coding assistant that pairs an LLM with Hindsight, an open-source agent memory system accessed via Hindsight Cloud, to retain corrections, recall relevant memories, and reflect over accumul…
JetBrains CEO Kirill Skrygan introduced JetBrains Air on September 22nd, a three-layer system spanning Air in JetBrains IDEs, Air Teams (in early access) and Air Governance, the renamed JetBrains Central, for policies, p…