https://www.codeslog.com/en/tags/ai/ Recent content in AI on Codeslog https://www.codeslog.com/images/default-cover.png?v=20260114T1436 https://www.codeslog.com/images/default-cover.png?v=20260114T1436 Hugo -- 0.168.0 en-US Sat, 10 Oct 2026 23:55:00 +0900 https://www.codeslog.com/en/posts/lighthouse-agentic-browsing-accessibility/ Sat, 10 Oct 2026 23:55:00 +0900 https://www.codeslog.com/en/posts/lighthouse-agentic-browsing-accessibility/ On test pages, a div button no keyboard can press scored Accessibility 100 and Agentic Browsing 2/2. What the check sees, what it misses, and where agent tools split. https://www.codeslog.com/en/posts/frontend-testing-ai-pitfalls/ Fri, 07 Aug 2026 14:59:00 +0900 https://www.codeslog.com/en/posts/frontend-testing-ai-pitfalls/ AI-written code is wrong in plausible ways. The accessibility and edge cases AI repeatedly drops, and how the test suite from this series reports each hole automatically — with a real before and after. https://www.codeslog.com/en/posts/frontend-testing-ai-playwright/ Thu, 06 Aug 2026 01:11:00 +0900 https://www.codeslog.com/en/posts/frontend-testing-ai-playwright/ AI now drives the browser itself. A practical map of Playwright codegen and MCP agents: why Playwright MCP reads the accessibility tree rather than screenshots, and why self-healing selectors aren't a Playwright feature. https://www.codeslog.com/en/posts/frontend-testing-ai-generate/ Thu, 06 Aug 2026 00:46:00 +0900 https://www.codeslog.com/en/posts/frontend-testing-ai-generate/ How good is AI at writing tests? Practical ways to generate and extend tests with LLMs, what AI reliably misses, and the checklist for trusting AI-written tests. https://www.codeslog.com/en/posts/frontend-testing-why-now/ Fri, 03 Jul 2026 16:33:17 +0900 https://www.codeslog.com/en/posts/frontend-testing-why-now/ The faster AI writes code, the more testing matters. In this opener of the Frontend Testing, Done Right series, we cover what tests really give you, pyramid vs. trophy strategy, and the full curriculum ahead. https://www.codeslog.com/en/posts/moduweb-accessibility-seminar/ Thu, 23 Apr 2026 22:30:00 +0900 https://www.codeslog.com/en/posts/moduweb-accessibility-seminar/ A recap of presenting ModuWeb, an open-source overlay accessibility tool, at an AI Accessibility seminar in Seoul — plus an honest take on overlay-tool criticism and other speakers' talks. https://www.codeslog.com/en/posts/ai-basic-act-accessibility/ Wed, 07 Jan 2026 18:59:00 +0900 https://www.codeslog.com/en/posts/ai-basic-act-accessibility/ Reading Korea's AI Basic Act (effective Jan 22, 2026) through a web accessibility lens: mapping WCAG's four principles onto its transparency, high-impact AI, and generative AI labeling duties. https://www.codeslog.com/en/posts/ai-evaluation-review/ Wed, 31 Dec 2025 01:51:00 +0900 https://www.codeslog.com/en/posts/ai-evaluation-review/ My experience as a citizen evaluator for an AI agent competition. Recording the questions I asked about accessibility, failure response, and communication design. https://www.codeslog.com/en/posts/evaluation-panel-seoul/ Tue, 30 Dec 2025 01:07:37 +0900 https://www.codeslog.com/en/posts/evaluation-panel-seoul/ A full day of my time, travel paid out of pocket, and just 50,000 won in return — yet I'm heading to Seoul as a citizen evaluator for an AI agent competition. A reflection on why a seemingly losing choice can plant seeds for the future. https://www.codeslog.com/en/posts/web-accessibility-ai-era/ Tue, 23 Dec 2025 00:29:12 +0900 https://www.codeslog.com/en/posts/web-accessibility-ai-era/ Can everyone use the web that AI builds? The accessibility gaps generative AI tends to miss, the four WCAG 2.2 principles in code, AI-generated alt text, and building an accessible AI chatbot.