Connect with us

OpenAI

OpenAI launches ChatGPT Agent, which runs computer on your behalf

Published

1 year ago

on

OpenAI ChatGPT Agent

AI is evolving every day, and today, OpenAI has evolved its generative AI offerings to a new level by launching ChatGPT agent, a new way to let AI control some important tasks on your behalf inside its own computer.

You can ask ChatGPT to complete tasks such as the following:

  • Look at my calendar and brief me on upcoming client meetings based on recent news.
  • Plan and buy ingredients to make the Japanese breakfast for four.
  • Analyze three competitors and create a slide deck.

Once submitted, the prompt will trigger ChatGPT to get to the work. It will surf the internet and open websites, find results, notify you to input credentials, run code, look for related data and deliver final results once the tasks are completed.

OpenAI reveals that this capability relies on a unified agentic system, a compound of Operator and Deep Research. First it finds the information on the internet through operators and then analyzes the key details through deep research.

The AI firm clarifies that these tasks are completed within ChatGPT’s virtual computer, which supports the workflow in switching between different tasks while following your prompts. Despite using its own virtual computer, ChatGPT agents will still remain in your control, and you have the ability to interrupt, take over the task, or stop the whole process at any time.

OpenAI is rolling out the ChatGPT agent feature for Pro, Plus, and Team users. Pro will get it first with 400 messages per month, while other paid users will get 40 messages per month.

Plus and Team users will get access gradually over the course of the next few days. Enterprise and Education users will get ChatGPT agent in the coming weeks.

How to use

You can use the new agentic feature from the tools dropdown from the composer after selecting ‘agent mode’. Describe the task and ChatGPT will start showing the activity on the screen for a live-preview.

(source)

Related Topics:

Mannoo specializes in Generative AI, Large Language Model (LLM), and Aerospace Science. Prior to delving into these fields, he was a Python programmer, a game designer, and an Android and iOS app developer with over 5 years of experience. He has prior writing experience in creative writing about smartphones and technology before working at Eonmsk.com. You can explore his X/TWitter and LinkedIn pages or contact him through his email.

Continue Reading