Testing AI Web Browsers: Current Limitations in Practical Shopping Tasks
By
Victoria Song
Master baker tier. Every paragraph earns its place on the tray.
Summary
The article tests several AI-powered web browsers and assistants (Comet, ChatGPT Atlas, Dia, Copilot in Edge, and Gemini in Chrome) to evaluate whether they can deliver a better internet experience than traditional browsing. Using a real-world shopping scenario for New Balance shoes, the author finds that current AI browsers struggle with practical tasks like finding specific products, comparing prices, and filtering out ads and fake deals. While promising in theory, these tools often provide generic or irrelevant results, fail to understand nuanced requests, and can't effectively navigate the complexities of modern e-commerce.
Key quotes
· 4 pulledAll I wanted was a pair of New Balances. I was done trusting stylish influencers who swore Vans, Converse, and Allbirds were up to the challenge of walking 20,000 steps day in and day out.
Wouldn't it be grand if I could skip all the fake deals and barely disguised ads, and have the internet find the best stuff for me? What if I could tell the internet my wish and have it granted?
Tech CEOs have been evangelizing that this is the future.
We test Comet, ChatGPT Atlas, Dia, Copilot in Edge, and Gemini in Chrome to find out.
You might also wanna read
Security Vulnerabilities in Agentic AI Browsers: Testing Reveals Scam Susceptibility
The article examines the emerging security vulnerabilities in agentic AI browsers that autonomously browse, search, and interact online. It
guard.io·9mo agoCritique of AI Browser Proliferation: Chromium-Based Browsers with AI Features
The article critiques the recent trend of AI browsers being announced by companies like OpenAI (Atlas), Perplexity (Comet), and others, argu
Why Browser Development Has Become a Benchmark Test for AI Systems
The article discusses why people are suddenly building browsers with AI, explaining that browser development serves as an ideal test case fo
news.ycombinator.com·4mo ago
Web Bench: A Comprehensive Benchmark for AI Browser Agent Performance
Web Bench is a new benchmark platform designed to evaluate and compare AI browser agents' performance in web navigation tasks. It provides c
Product Hunt·1y ago
How AI Shopping Tools Simplify Holiday Gift Finding and Purchasing
The article discusses how AI-powered shopping tools, particularly Google's new AI shopping features, can simplify holiday shopping by automa
blog.google·6mo ago
Analysis: Cursor's AI-Generated Browser Claim Raises Questions About Practical Software Development
The article critiques Cursor's claim of building a functional web browser using AI agents, specifically GPT-5.2. While the company's CEO twe
theregister.com·4mo ago