Full-text search across 63979 articles. Combine with topic and date filters; results sorted by relevance.
A blogger's comparison of Claude Haiku 5.5 and GPT-6-Luna on OpenRouter for Rust code generation found both models typically cost under $0.01 per generation (often as low as $0.005) and respond in 10-30 seconds, with cod…
Developer Filippo Finke released CAD Studio, a native macOS app that turns a text description into parametric CAD models by having a local coding agent (Claude Code or Codex CLI) write and run build123d Python scripts. C…
Microsoft's DevRel team released the Agent Experience (AX) Practitioner Playbook, a method for evaluating what AI coding agents do with a given technology and fixing the sources agents rely on, such as docs, MCP tools, s…
Microsoft's DevRel team released the Agent Experience (AX) Practitioner Playbook, a method for evaluating what AI coding agents do with a technology, diagnosing why they get it wrong, and fixing it at the source, availab…
WorkOS previewed three new products — Airlock, Atlas and Passport — during its init() 2026 conference at the SFJAZZ Center in San Francisco on October 7, 2026, with all three rolling out over the coming weeks and months.…
Adversa AI published a technique on October 6, 2026, called Cryptographic Context Injection that exfiltrates a developer's .env.prod file — including API keys and database passwords — through GitHub Copilot CLI in 28 sec…
GPT-6 Astra [Max] leads the 4DCodeBench leaderboard, followed closely by Claude Opus 5.5 [High], on a new benchmark that evaluates coding agents on reconstructing dynamic scenes from video by writing executable graphics …
Google launched EmbeddingGemma 2, a 740-million-parameter natively multimodal embedding model built on the Gemma 4 architecture and released under an Apache 2.0 license, expanding its predecessor beyond text to unify cod…
LopeBase launched as a SaaS monitoring console that consolidates growth, revenue, traffic, uptime, and SEO data for multiple products into one dashboard, reading existing tools such as Stripe, PostHog, and Google Search …
A developer working in embedded systems argues that AI coding agents need observability tools—debug probes, GDB sessions, serial logs—rather than just better prompting, drawing an analogy to reinforcement learning's veri…
A four-day persistent coding-agent session lost a specific architectural decision — a 15-minute refresh-token TTL and its mobile-client rationale — after the third compaction event, according to a first-person account of…
Context7, an open-source TypeScript project with 63,000 GitHub stars, delivers up-to-date, version-specific library documentation and code examples directly into LLM and AI code editor context via MCP, and was last updat…
EditUI launched as a free Chrome extension that lets developers click any element in a running web app, attach a plain-language edit request, and batch-send the collected edits to coding agents including Claude Code and …
A new short-video channel produced twelve AI-generated clay-styled films about famous frauds in five days for $184 in fal.ai image and video costs, using the coding agents Claude Code and Codex to run script, narration, …
Open Mercato released cezar, a free MIT-licensed open-source orchestrator that runs Claude Code, Codex, OpenCode and other coding agents in parallel on a laptop or VPS using existing agent subscriptions rather than API k…
Perspica is a code-review tool that replaces line-level diffs with LLM-driven semantic grouping, clustering related changes by intent and explaining the reasoning behind each group. The tool offers a second, LLM-free mod…
Google announced Gemini 4 Argon on launch day, claiming benchmark leadership over GPT-6 Astra and Claude Opus 5.5 on 13 of 18 disclosed benchmarks, including DeepSWE v1.1 at 77.9% and Harvey Legal Agent at 19.6%, while B…
Stack Overflow expanded Stack Internal with trust scores, an ingestion API, connectors for Microsoft Teams, Slack and Google Docs, and an MCP server that exposes enterprise knowledge to AI coding tools including Claude C…
The UK AI Security Institute and Meridian Labs released Inspect, an open-source framework for large language model evaluations that ships with over 200 pre-built evaluations and supports more than 20 model providers. Ins…
Kilo launched Sign in with ChatGPT, letting users authenticate with their OpenAI ChatGPT subscription and use up to 100% of the ChatGPT Work and Codex usage included in their plan for inference across Kilo's VS Code, Jet…