Full-text search across 56121 articles. Combine with topic and date filters; results sorted by relevance.
A team of two fathers competing as MacCody in the AI for Industry Challenge spent six weeks using coding agents to build a classical robot controller for a UR5e to insert fiber connectors into a randomized task board. Th…
Microsoft has patented an AI coding system that splits a single prompt into two coordinated sub-instructions — one to generate code and one to validate the user's original input — and excludes any fragment flagged as unv…
AI tools like ChatGPT and GitHub Copilot can now generate code and fix bugs in seconds, shifting the focus of coding education from memorizing syntax to hands-on experimentation. Interactive coding playgrounds, such as t…
Anthropic's Opus-5 model, described by the company as the least susceptible to being tricked into misuse, executed remote code in 6 out of 7 identical experiments when given a simple /init command in Claude Code v2.1.220…
Cohere AI released North Mini Code, a 30-billion-parameter open-weight mixture-of-experts model with 3 billion active parameters per token, optimized for code generation, agentic software engineering, and terminal tasks.…
Salesforce has released Slack Code, a service that embeds AI coding agents into dedicated Slack channels so stakeholders can collaborate on software tasks in real time. The service supports agents such as Anthropic's Cla…
A hands-on comparison of ChatGPT's Codex and Anthropic's Claude Code on a mid-size TypeScript repo found Claude Code finished all five tasks unattended, caught 25 of 30 seeded bugs, and averaged 8.7/10 on first-pass qual…
Alibaba open-sourced its AI code reviewer open-code-review, which achieved a 26.1% F1 score on a benchmark of 200 real pull requests, outperforming Claude Code's 15.5% F1 at one-fifth the token cost. The tool, used inter…
A security researcher warns that coding models should be treated as executable code, as they can generate malicious tool calls that exfiltrate environment variables or introduce subtle vulnerabilities like JWT algorithm-…
A developer has opened a feature request in the Microsoft VS Code repository asking that the editor's experimental AI "pet" companion, which currently only reacts to GitHub Copilot activity, also recognize open-source AI…
Researchers have developed RAG-Coding, a method that uses four large language model agents to automate ICD-10-CM medical coding by grounding decisions in official coding tabular lists and guidelines. On the MDACE dataset…
Hermit, a plugin by gtapps for Claude Code, turns a Claude Code instance into a 24/7 autonomous agent with stateful memory, proactive routines, and operator-gated self-improvement, installable via 'claude plugin marketpl…
Moonshot AI has released Kimi Code CLI, an open-source terminal-based AI coding agent that reads and edits code, runs shell commands, and works through tasks step by step. The tool is written in TypeScript, MIT licensed,…
Boris Cherny, the head of Claude Code at Anthropic, said he has not written a line of code by hand in eight months, relying entirely on the AI tool he helped build. Cherny made the remark during a fireside chat at the Fo…
Databricks announced the beta release of the agentic code converter in Genie Code, which automates the translation of proprietary SQL dialects from T-SQL, Snowflake, Redshift, Oracle, BigQuery, and Teradata to open ANSI …
Redpill Linpro senior systems consultant Tobias Brox described in a March 20, 2026 blog post his shift from resisting AI assistance to using Claude Code for debugging, code review, small project scaffolding, and sysadmin…
A developer discovered that dead code in their coffee e-commerce store's backend was more dangerous than broken code, as an AI assistant had rubber-stamped a pricing module that had not compiled in six months. The develo…
Standard Code, a new cloud-based coding agent with unlimited usage, is now available for pre-order through a waitlist, with a $5 1-week trial for those with access codes. The service uses a lines-of-service billing model…
A developer argues that AI coding tools like Claude Code and no-code agents generate code that looks complete but often hides serious system design flaws, such as data corruption from poor schema decisions, missing cross…
A developer built the same refund feature twice—once with vibe coding and once with spec coding—to compare the outcomes. The vibe-coded version, created in 10 minutes, required two weeks of bug fixes for issues like dupl…