Full-text search across 63098 articles. Combine with topic and date filters; results sorted by relevance.
JetBrains shipped Rider 2026.2.1 with a bundled refactoring-code skill that gives AI agents direct access to its refactoring engine, cutting median task time from 157.9 seconds to 26.6 seconds (83% faster) and cost per t…
A developer known as Lukie-81 has built RepoRelay, an open-source tool that gives AI coding assistants like ChatGPT access to a local repository without exposing the entire machine. The tool uses a secure MCP tunnel to e…
PyTorch's built-in GELU function is 20% faster than a hand-rolled version when training GPT-2 small models, according to a developer's benchmark. The same code training the same model on the same data ran at about 21,000…
AGENTS.md, an open format for coding-agent project context now read automatically by 23 tools, has been shown by three research groups to double as an instruction-injection vector for credential theft and supply-chain at…
A developer discovered that the IAM policy they wrote for their solar agent was not truly least privilege, granting broader access than the code required. The policy's Bedrock statement used wildcards that matched all Cl…
Bullet, a coding agent launched from YC's Summer 2026 batch, claims 95.8% on SWE-bench Verified at 119 seconds per task, but its founders concede the benchmark is saturated and the speed pitch is the real product. The st…
Andrej Karpathy introduced "agentic engineering" at Sequoia Capital's AI Ascent event in February 2026, defining it as "the professional discipline of coordinating fallible agents while preserving correctness, security, …
A developer's study of agent-authored pull requests in major .NET organizations found that the primary failure mode of AI code review is not hallucination but ignoring existing repository knowledge. Using the open-source…
A developer argues that AI-assisted coding is stunting junior engineers' debugging skills, citing an Anthropic study showing AI users scored 50% on comprehension quizzes versus 67% for hand-coders, and GitClear data reve…
Amazon Web Services (AWS) introduced a suite of six Agent Skills for Amazon Bedrock Automated Reasoning checks, enabling coding agents to build, test, deploy, and validate policies end to end. The skills, based on Anthro…
Clixad, a terminal coding agent with no subscription, funds model API calls through an offerwall where 100,000 credits equal one US dollar of advertiser payout, with a fixed exchange rate in code. The platform keeps one …
Unsloth, an open-source AI startup, released Unsloth Studio (Beta), a platform that lets users run and train text, audio, embedding, and vision models locally on Windows, Linux, and macOS, with support for 500+ models, u…
A developer nearly merged a Claude Code suggestion to delete all products in a Rails repo after an indirect prompt injection hid a destructive instruction in a code comment, highlighting a vulnerability in AI pair progra…
Microsoft Corp. on July 1 added Moonshot AI's Kimi K2.7 Code to its Microsoft Foundry model catalog in public preview, and GitHub Inc. made it the first open-weight model in the Copilot model picker, rolling out to Copil…
Developer nagisanzenin released Engram v1.0.8, a learning system for humans that turns AI coding assistants into tutors, examiners, and spaced-repetition schedulers across six agentic platforms including Claude Code, Ope…
In 2026, AI has become the central nervous system of software development, with IDEs like Copilot X, Cursor, and JetBrains AI evolving into 'development agents' that understand entire codebases and proactively suggest fu…
Google released Gemini 3.6 Flash on July 21, 2026, improving on its predecessor with faster speeds, lower costs, and better benchmark performance across coding, long-context retrieval, and computer use. The model runs at…
A senior developer argues that AI should augment, not replace, human capabilities. The developer advocates for using AI tools like GitHub Copilot for drafting code while retaining human oversight for defining goals and v…
A joke made to Claude Code led to the discovery that 72 percent of a feature in the German-conjugation app Konjugieren was unimplemented, along with fixes for nine documentation defects and a new tool in the repository. …
A developer migrated the Anyhide project to post-quantum hybrid encryption using ML-KEM-768, adopting two opposite strategies for different subsystems: backward-compatible 'bend' for persistent codes and a clean 'break' …