This systematic literature review examines the role of large language models (LLMs) in UI/UX design, synthesizing findings from 38 peer-reviewed studies published between 2022 and 2025. We identify key LLMs in use, including GPT-4, Gemini, and PaLM, and map their integration across the design lifecycle, from ideation to evaluation. Common practices include prompt engineering, human-in-the-loop workflows, and multimodal input. While LLMs are reshaping design processes, challenges such as hallucination, prompt instability, and limited explainability persist. Our findings highlight LLMs as emerging collaborators in design, and we propose directions for the ethical, inclusive, and effective integration of these technologies.

Large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing…

This article warns that the AI industry is repeating historical security failures by normalizing over-reliance on LLM outputs...

An open-source specification and ecosystem for building multi-provider, interoperable LLM interfaces. Enables builders to work with different AI providers using a unified schema, streaming events, and tool integration.

Discussion on Hacker News examining whether larger language models necessarily hallucinate more and if scaling laws have plateaued.

A real filesystem abstraction for AI memory with a single binary. No SDK or vector database required - simple persistent storage for LLM context and memory.

Research benchmark comparing open-weight and frontier AI models on vulnerability detection. GLM 5.2 outperformed Claude Code by 7 points on IDOR detection at 1/6 the cost, demonstrating that open-weight models are becoming viable alternatives for security applications.

A framework for multi-hop question answering over large knowledge graphs using semantic-aware path retrieval combined with...

ax is a specialized tool for AI coding agents that streamlines web data retrieval. Unlike traditional curl and throwaway Python...

Ponytail is a decision-making framework for AI coding agents that prevents over-engineering. It prioritizes a structured...

An AI code verification platform that automatically generates and verifies production-ready code using formal methods. Converts natural language prompts to formal specifications and bridges AI code generation with deployment confidence.

ICLR 2025 research paper introducing a novel LLM architecture that integrates human-like episodic memory for superior long-context processing, achieving state-of-the-art results on LongBench and ∞-Bench benchmarks.

AssBench is a benchmarking platform for comparing LLM outputs. It lets you run the same prompt against multiple language models...

Cloudflare introduces Clairic, a new class of System One extraction models capable of extracting, computing, estimating, and forecasting data from unstructured inputs.