Can Microsoft Copilot code? We put it to the test

ZDNET Innovation Weekly

May 3, 2024

Yikes! Microsoft Copilot failed every single one of my coding tests

I ran Microsoft Copilot against Meta AI, Code Llama, Gemini Advanced, and ChatGPT. It managed to get every test wrong. That's some kind of record or something.

plus

Why the future must be BYO AI: Model lock-in deters users and stifles innovation

OpenAI makes 'Memory' available to all ChatGPT Plus subscribers - how to use it

GitHub releases an AI-powered tool aiming for a 'radically new way of building software'

5 ways AI can help you study for finals - for free

featured

DJI made a rugged power station that I can't recommend enough to drone users

5 Gemini features I hope Google announces at I/O 2024

This $299 Galaxy Ring challenger is launching May 15 - and its specs look promising

Rabbit's first R1 software update fixed my biggest problem with the AI gadget

The best Roomba vacuums for your home: Expert reviewed

most popular

01	This thumb-sized accessory gave my old PC an instant speed boost
02	Arc browser is now available for Windows and it's so much better than Chrome
03	One of the best QLED TVs I've tested is not made by Samsung or Sony
04	The work laptop I recommend to most people is not made by Apple or Lenovo
05	Sorry, you really can't disable Facebook's Meta AI tool - but here's what you can do

You are receiving this email because you've signed up to receive newsletters and promotional content from ZDNET.

Unsubscribe | Terms of Use | Privacy policy

Trouble viewing this? Read Online