3 articles tagged with #browser-automation. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce MiniAppBench, a new benchmark for evaluating Large Language Models' ability to generate interactive HTML applications rather than static text responses. The benchmark includes 500 real-world tasks and an agentic evaluation framework called MiniAppEval that uses browser automation for testing.
OpenAI has released a System Card for ChatGPT's new agentic model, which integrates research capabilities, browser automation, and code execution tools. The system operates under OpenAI's Preparedness Framework with built-in safeguards to manage potential risks from autonomous AI agents.
A new AI agent called Operator has been launched as a research preview, capable of autonomously using web browsers to perform tasks for users. The service is currently available exclusively to Pro users in the United States.
