Full-text search across 56302 articles. Combine with topic and date filters; results sorted by relevance.
Meta launched Muse Code in beta on August 5th, a terminal-based coding agent powered by Muse Spark 1.2, marking Meta's entry into the application layer of AI coding tools. CEO Mark Zuckerberg announced the release, claim…
A new report from engineering platform Flux reveals that 35% of engineering teams using AI to write code refuse to ship it due to lack of confidence in assessing risk. The bottleneck has shifted from code generation to v…
A group of software engineers has published a manifesto advocating for responsible use of generative AI in coding, emphasizing that every line of production code must be read and understood by a human. The manifesto, whi…
A comparison of five AI agents—ChatGPT GPT-5.5, Qwen 3.7-plus, Claude, Gemini, and Kilo Code Hy3—on a Rust leap-year coding task found that all produced decent code but only three used Rust's test harness, while two mode…
A developer built a file-based coordination layer called cross-session-talk that enables Claude Code on Windows, Claude Code on Linux, and Codex in tmux to communicate and converge on shared engineering decisions across …
Carnegie Mellon University PhD student Michael Isaac, during an internship at cmpnd, implemented Flex, a new DSPy module that lets models rewrite program code, not just instructions, to optimize performance. Flex exposes…
An engineer argues that the main challenge in AI-assisted coding is not access to AI tools but knowing when not to trust their output. The post highlights that AI can generate plausible but incorrect code, and emphasizes…
Code retrieval is shifting from embeddings to graph-based approaches, as demonstrated by the trending open-source tool code-graph-rag, which parses repositories with Tree-sitter, builds a knowledge graph in Memgraph, and…
GitHub has 630 million repositories, with nearly half of all new code written by AI, but developer trust in AI code dropped from 77% to 60%. Carnegie Mellon University found 6 million fake stars, and CodeRabbit reported …
Kilo Code has reintroduced codebase indexing for semantic code search, requiring users to configure an embedding provider and vector store before enabling the feature. The indexing system parses code locally with Tree-si…
Microsoft has introduced code interpreters for Azure Logic Apps, allowing AI agents to generate and execute Python, JavaScript, C#, and PowerShell code within Hyper-V isolated sandboxes as part of governed workflows. The…
AI coding agents fail senior engineers because they skip critical architectural planning and long-term system design, optimizing only for immediate code generation. To address this, the author built Kavro, an open-source…
A July 15, 2026 arXiv paper titled "Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents" audited the source code of eleven production coding harnesses — Claude Code, Codex CLI, Gemini CLI, Mistral …
A software company founder who mandated AI-assisted coding across his development team in January 2026 reported that one engineer can now produce several times as much output as before, but said code review has become "a…
A new model compression method called requential coding compresses a generative model by coding a training process built from self-generated data, achieving code length equal to the cumulative teacher-student KL divergen…
A developer discovered Guardsman, an open-source AI coding skill by Hedi Manai that refuses to fabricate benchmark numbers. Unlike typical AI coding tools that boast unverifiable metrics, Guardsman assigns a risk tier to…
Coder announced on September 15 that Anthropic's Claude Code is now available on Agent Relay, Coder's self-hosted execution environment for cloud coding agents, giving regulated enterprises such as financial services fir…
According to an InfoWorld opinion piece, the rise of AI coding agents will soon make human-readable programming languages like TypeScript, Python, and Rust obsolete, as agents will communicate directly with machines in a…
The TISA, a development team, ran a side-by-side comparison of AI code generation tools including GitHub Copilot, Cursor, and Claude Code on real client work to determine which actually saves time. They found that while …
A software engineer argues that writing code remains valuable in 2026 despite AI agents' ability to generate code, because hands-on coding fosters attention, understanding, and ownership of the system architecture, and h…