DEV Community

Cover image for Artificial intelligence test: Which program managed to do everyday tasks?
Hacks.gr
Hacks.gr

Posted on Originally published at en.hacks.gr Fully Autonomous

Artificial intelligence test: Which program managed to do everyday tasks?

Hands-on evaluation of three major AI agents: ChatGPT's Dots, Gemini's Spark, and Meta's Muse.

We tested their capabilities across real-world tasks including automated shopping, targeted job hunting, wiki research, spreadsheet formatting, and inbox cleanup to see how current autonomous workflows perform.


The three options were OpenAI's Dots, Google's Spark, and Meta's Muse. Each program has a different cost and way of working. Dots is available on the company's most expensive subscription plans, costing $100 per month for business or home use. Spark is offered through Google subscriptions that start at $20 per month and go up to $100 per month. Muse is available free for everyone, with optional paid plans starting at $20 per month.

Testing in everyday tasks

All three programs were asked to complete a series of common tasks, such as grocery shopping, job searching, researching and organizing information on a spreadsheet, making restaurant reservations, and cleaning up overflowing emails.

In grocery shopping, Dots was able to complete the shopping through a delivery service, while Muse needed to manually log in and added extra ingredients that weren't there. Spark froze and couldn't complete the task.

In job search, only Dots was able to find specific and relevant ads with direct links. Muse and Spark did not yield the same results.

READ ALSO

Mark Wahlberg is considering using artificial intelligence in his new film

When asked to collect information from an online encyclopedia and present it in a table format, all three programs responded successfully.

In restaurant reservations, Dots was able to book a table, while Muse and Spark simply suggested restaurant lists.

In cleaning up spam, Dots was able to process thousands of marketing messages to create a list of candidates for deletion, while Muse and Spark lagged behind in this process.

Which program stands out?

Google's Spark has the advantage of being able to access personal files automatically and works faster.

However, the test author concluded that these programs are not yet essential for everyday tasks, despite the advertising hype.

G

Hacks.gr on Google

Set it as a preferred source for cybersecurity updates.

Preferred source


Read the original English article on Hacks.gr

Top comments (0)