AI coding assistants

Goldman Sachs is removing Anthropic's Claude Code coding tool from its bankers and traders, restricting staff access to the AI assistant. The move has drawn widespread attention in tech and finance circles, with debate over why the bank is limiting an AI tool that had been embraced as a productivity booster for employees.

A software developer has published a write-up explaining a switch from Anthropic's Claude coding assistant to Pi, sparking discussion among developers about which AI assistant best fits day-to-day programming work. The piece, shared widely on Hacker News, is drawing hundreds of upvotes as readers weigh in on their own experiences moving between AI coding tools.

Google Chrome team member Paul Irish released a resource called modern-web-guidance, aimed at getting AI coding assistants to stop generating JavaScript and web patterns from around 2019 and instead use current browser primitives and APIs. The project, hosted on GitHub, provides guidance that developers can feed to their agents so generated code reflects modern web capabilities rather than outdated defaults.

Google has updated the Play Store to make it easier for developers to publish apps created with AI coding tools, often called vibe-coded apps. The move lowers barriers for hobbyist developers and reflects the wave of AI-assisted software development. It comes as Android-adjacent platforms, including Amazon's new Alexa tablets, continue blurring lines around app distribution.

IEEE Spectrum reports that AI tools are exposing long-standing flaws in legacy software, illustrated by the php2shell vulnerability class, where decades-old insecure coding patterns in PHP applications let attackers turn input into shell commands. The argument is that AI-assisted discovery and exploitation of such weaknesses is compounding an accumulated security debt from 40 years of software practices, forcing organizations to finally remediate old code.

A new open-source tool called Klad has been released, presenting itself as a paint application that can be driven by coding agents such as AI assistants. The app is available as source-available code on GitHub, letting developers inspect and adapt it. Early discussion online is focused on how AI agents could automate creative and design workflows, not just software tasks.

Developer Julius Brussee released 'Caveman', a Go-based skill and proxy for coding agents that rewrites the model's output in stripped-down, simplified language to cut token usage by roughly 65%. The tool's promotional pitch leans on the joke 'why use many token when few token do trick'. It is circulating as a quirky but practical way to reduce costs when running AI coding assistants.

A GitHub project called free-claude-code by Alishahryar1 is trending. It claims to let developers use AI coding assistants including Claude Code, Codex, VSCode, Pi and OpenCode for free, advertising over 1.3 billion free tokens accessible from a terminal, IDE, app, phone or browser. The tool supports multiple harnesses and models and describes itself as terms-of-service friendly.

Cloudflare has published an open-source coding-agent skill for carrying out multi-phase security audits. The tool produces independently verified, machine-readable findings, letting AI coding agents run structured security reviews of codebases. Its release is drawing attention from developers interested in integrating automated security auditing into AI-assisted development workflows.

Developer Nolan Lawson has published an essay arguing that AI coding assistants favor popular JavaScript frameworks and generate code whose complexity and bundle size carry real costs. He contends that prompting tools toward heavyweight solutions can bloat performance and maintainability, and urges developers to weigh whether a framework is needed at all when AI writes the code.

Anthropic has introduced measures preventing its Claude AI model from being used to reverse-engineer or clone video games. The move comes as AI tools increasingly demonstrate the ability to reproduce playable game mechanics from footage or code, raising copyright concerns across the games industry. Developers have welcomed the restrictions, while others argue it highlights unresolved questions about how far AI companies should police how their models are used.

A detailed write-up describes how a real company runs 17 Claude Code bots in production for roughly $100 per month, breaking down actual costs and operational experience. The account of how cheaply AI coding agents can be deployed at scale is drawing attention among developers weighing the economics of AI-assisted engineering.