AI Agents

Replit, an AI-driven integrated development environment, updated its mobile app to generate further mobile apps to order.

Browsing the web to achieve a specific goal can be challenging for agents based on large language models and even for vision-language models that can process onscreen images of a browser.

OpenAI introduced a state-of-the-art agent that produces research reports by scouring the web and reasoning over what it finds.

Even cutting-edge, end-to-end, speech-to-speech systems like ChatGPT’s Advanced Voice Mode tend to get interrupted by interjections like “I see” and “uh-huh” that keep human conversations going. Researchers built an open alternative that’s designed to go with the flow of overlapping speech.

As Anthropic, Google, OpenAI, and others roll out agents that are capable of computer use, new work shows how underlying models can be trained to do this.

OpenAI introduced an AI agent that performs simple web tasks on a user’s behalf.

In 2025, AI will have learned to see, it will be way smarter and more accurate, and it will start to do things on your behalf.

The AI community laid the foundation for systems that can act by prompting large language models iteratively, leading to much higher performance across a range of applications.

Amazon introduced a range of models that confront competitors head-on.

One of the world’s biggest payment processors is enabling large language models to spend real money.

An open source package inspired by the commercial agentic code generator Devin aims to automate computer programming and more.

Coding agents are improving, but can they tackle machine learning tasks? 

API commands for Claude Sonnet 3.5 enable Anthropic’s large language model to operate desktop apps much like humans do. Be cautious, though: It’s a work in progress.

An agentic coding assistant boosted the state of the art in an important benchmark by more than 30 percent.