Full-text search across 65860 articles. Combine with topic and date filters; results sorted by relevance.
GitHub has made Google's Gemini 3.8 Flash model available in GitHub Copilot, with early testing showing strong performance on complex terminal-based coding tasks. The model is billed at introductory provider pricing unde…
A developer on Hacker News asks peers how they track the most cost-effective AI models for coding, citing their own $20/month Claude Code subscription and seeking resources to compare alternatives and tools for quickly s…
A developer released Human Tool for Claude Code, a satirical MCP server that treats humans as high-latency, stochastic tools for AI coding agents, inverting the typical agentic loop. The project, available on GitHub, use…
Arjun Krishna Lal, writing at TechSpot, used AI coding agents and a $100 ChatGPT Pro account to port Morrowind, Duke Nukem 3D, and Serious Sam: The First Encounter to an iPhone, despite having no coding experience. He co…
Anthropic released Claude Fable 5.1 and Mythos 5.1, claiming Fable 5.1 outperforms Fable 5 in coding, knowledge work, and problem-solving, with expected cost reductions of about 25% overall and up to 45% for highly agent…
AI coding agents achieve their most impressive results where correctness is cheap to verify, such as in the rewrite of the Bun JavaScript runtime from Zig to Rust, according to a blog post by Paul Dix. The post argues th…
Anthropic released Claude Fable 5.1 and Claude Mythos 5.1, its most capable models for coding and knowledge work, with Fable 5.1 broadly available and Mythos 5.1 restricted to vetted partners in cybersecurity and life sc…
Dan Eble released Keel, an open-source harness for coding agents that provides auditable stopping conditions and durable memory, installable via `cargo install keel-harness`. Keel introduces falsifiable oracles for accep…
Anysphere, the company behind the AI code editor Cursor, is hiring a Software Engineer for its ML Platform team in San Francisco, with the role focused on building infrastructure for telemetry, data pipelines, observabil…
A developer tested Claude Code on eight real DevOps tasks, including CI log triage and on-call fixes, and found it genuinely useful for reading logs and proposing fixes, but unreliable as a deterministic gate: the same A…
A developer has adapted Effect TypeScript's mental model into a call graph planning technique for AI-assisted coding, making AI-generated plans easier to review and understand. The approach, inspired by Dillon Mulroy and…
A developer with a non-technical background but years of experience in software development companies is seeking advice on advancing their AI-driven app development. They have spent six months building a cataloguing app …
SVG Lab, a developer tool, compares three routes for generating SVG files with AI: direct code generation from models like ChatGPT, Claude, and Gemini; auto-tracing raster images from Midjourney or DALL-E; and its own AI…
A developer shared a benchmark plan for validating an AI code reviewer before migrating to MonkeyCode's free model access and free server option. The plan includes collecting code samples with known issues, running them …
A new study finds that AI coding assistants Claude Code and Codex have no sense of time, systematically overestimating task durations by up to ten times and rating their own work about 20 percentage points too high, crea…
Archify, a developer tool that enables AI coding assistants like Cursor and Claude Code to automatically generate verifiable architecture, workflow, sequence, and data-flow diagrams as self-contained HTML files, has gain…
Carla Urrea Stabile of Auth0 for Developers discusses how AI tools are changing the way developers interact with code, suggesting that reading code may become less necessary. The post highlights the shift toward AI-assis…
Lanes Link, a new open-source tool from Lanes, provides a unified memory and skills layer for AI coding agents, allowing users to store context once and access it across different clients like Claude Code and Codex. The …
Agenteam, a new macOS app in early access, lets users run coding agent CLIs like Claude Code, Codex, opencode, and pi as floating desktop characters that persist across restarts, with a free tier and a $9.9 one-time earl…
Enterprises rapidly deploying AI tools are often unprepared for internal and external security threats, according to analysts at Gartner, Forrester, and J. Gold Associates. Pete Shoard, chief of research for cybersecurit…