Ask HN: What's your favorite AI tool for front end design?
A Hacker News user asks which AI tool is currently the least worst for front-end design, listing Google Stitch, Claude Code, and Lovable. The user notes that many options exist but all have been awful in their experience.
Background
This is an "Ask HN" post — a question thread on Hacker News (HN), a tech-news aggregator and discussion forum run by Y Combinator where developers and founders debate tools and trends.
- **Google stitch** (likely a typo for *Google Studio*/Gemini or *Screenshot-to-Code*) — a tool that turns design images into front-end code.
- **Claude Code** — Anthropic's AI coding assistant built into the terminal, popular for generating full UI components.
- **Lovable** (formerly GPT Engineer / Lovable.dev) — a startup that generates complete web apps from natural-language prompts.
The post reflects a common frustration in 2025: dozens of AI "design-to-code" tools exist (v0.dev, Bolt.new, Replit Agent, Cursor, Copilot, etc.), but developers find them unreliable for real-world, pixel-perfect, production-quality front-end work. The question is asking the community which tool is currently the "least bad" — a pragmatic, cynical framing that signals deep skepticism about AI replacing front-end engineering.
Max Weinbach says he had early access to OpenAI's new model GPT-5.6 Sol, calling it his favorite model by far. He highlights that it never gives up and will keep reasoning until it's done. OpenAI announced that GPT-5.6 Sol, along with Terra and Luna, will launch publicly on Thursday, with preview access expanding globally now.
The US government ordered Anthropic to suspend access to its Fable 5 and Mythos 5 models for all customers, citing a potential jailbreak technique that involved asking the model to review a codebase for vulnerabilities—a capability Anthropic says is available in other public models. Access was abruptly cut off on June 12.
Andrej Karpathy announces the release of Claude Fable 5, the same underlying model as Mythos but with added safeguards. He calls it a major step forward, particularly for long problem-solving sessions on difficult tasks, and describes it as state-of-the-art on nearly all benchmarks with exceptional performance in software engineering, research, and vision.
Roman Storm warns that the legal theory in his case could set a precedent making open-source developers liable for how others use their code, potentially criminalizing the mere publication of privacy, messaging, or crypto tools. He notes that developer Michael Lewellen cannot publish lawful code due to prosecution fears, and argues this chilling effect extends beyond any single case.
Meta's engineering culture is deteriorating under Mark Zuckerberg and Scale AI CEO Alexandr Wang, who have introduced keyboard tracking, reassignments to data labeling, and AI-centric performance metrics. Critics argue this incentivizes performative AI use, drives away experienced engineers, and contributed to a major Instagram hijacking incident caused by AI-written and AI-reviewed code.