Full-text search across 63953 articles. Combine with topic and date filters; results sorted by relevance.
The industry-standard code review process, review-then-commit, is broken by AI coding agents, creating a principal-agent problem where contributors generate low-effort pull requests that overload reviewers. This imbalanc…
A developer created a structured prompting method called C.O.R.E. (Context, Objective, Rules, Expected output) to improve results from AI coding assistants like ChatGPT. The method involves specifying language and framew…
Google Cloud Spanner now supports multiple data models—relational, vector, graph, and analytic—within a single globally distributed instance, eliminating the need for separate databases for AI workloads. A developer demo…
TaskPrio has launched a task management system that lets AI coding agents pull work from a single ranked queue and execute it autonomously. The MCP-native tool allows developers to maintain one global priority order acro…
Linear has launched Linear Agent, a new AI assistant integrated into its project management platform that can synthesize context from roadmaps, issues, and code to help users make product decisions and take actions. The …
MiniMax released M3, the first open-weights model combining frontier-level coding ability, a 1M-token context window, and native multimodality, which a developer tested on real tasks including a code audit of a 26k-line …
Kelsey Hightower argued on the Pragmatic Engineer podcast that AI does not change what software engineering is, emphasizing that writing code is decision-making and that fundamentals remain essential. He warned against r…
Researchers analyzing token consumption in LLM-based multi-agent software engineering systems found that code review stages consume the majority of tokens at 59.4%, with input tokens accounting for 53.9% of total usage. …
A developer built Basilisk, an open-source Python language server and type checker written in Rust that enforces strict type annotations by default. The tool was created after the developer found Pylance's gradual typing…
Agent-ML-skills, a curated pack of 15 battle-tested machine learning skills, has been released to teach AI coding agents like Codex, Claude Code, and Cursor how to avoid common ML mistakes such as data leakage and scorin…
Software developers are increasingly comparing AI-assisted coding to fast food, warning that while tools like Cursor's AI agents can quickly generate large amounts of code, the output often lacks the quality and understa…
A developer argues that current artificial narrow intelligence (ANI) systems cannot replace human developers because they lack autonomy. While AI can generate code and answer questions, it cannot define problems, verify …
JetBrains released Mellum2, a 12-billion-parameter Mixture-of-Experts model with 2.5 billion active parameters per token, under the Apache 2.0 license. The model is specialized for software engineering tasks including co…
The team behind i18nexus has developed a workflow where AI coding agents like Claude and Codex generate translations through the Model Context Protocol (MCP) instead of directly editing JSON files. The system synchronize…
A developer deployed seven specialized AI agents across their development workflow and tracked the results over 30 days. The system included agents for bounty hunting, PR submission, content writing, code review, securit…
Uber exhausted its full 2026 artificial intelligence budget by April after rapidly deploying Anthropic's Claude Code to thousands of engineers, with monthly per-engineer costs ranging from $150 to $250 on average and $50…
Cognition AI closed a Series D round exceeding $1 billion, raising its valuation to $26 billion from $10.2 billion in September 2025, as the maker of the autonomous coding agent Devin more than doubled in value in eight …
MCP (Model Context Protocol) has reached 97 million SDK downloads per month in early 2026, with every major AI coding platform now supporting the standard and over 9,400 servers in the public registry. A developer compil…
Anthropic launched Claude Opus 4.8, its latest AI model, on Snowflake Cortex AI in public preview on May 28, 2026, making it available within Snowflake's secure perimeter for use with Cortex Code, Cortex Agents, and othe…
A developer slashed their monthly AI API costs from $3,200 to $420 by switching from OpenAI's GPT-5.5 to Chinese models like DeepSeek V4, which costs 1/50th the price per output token. In production benchmarks, DeepSeek …