First Impressions with Google Gemini

Re:First Impressions with Google Gemini by yeldarb on Wednesday December 13, 2023 @12:38PM (#38630985)

Weird that the object detection prompt refused to answer. What other variations of that have we tried? Do you think that's an intentional task that was RLHF'd out or a quirk of some kind?

Thinking out loud some things I'd try:

Find the x/y position of the dog.

What is the center point of the dog?

Give the pixel coordinates (xywh) of the dog in this photo.

Simulate an object detection model trained to find dogs run on this photo; give your output in JSON format.

[ Parent | on HN ]

Re:First Impressions with Google Gemini by zerojames on Wednesday December 13, 2023 @12:40PM (#38631033)

I have experienced intermittent performance with the web interface.

I am really curious about the object detection performance so I’ll be rerunning that test regularly.

[ Parent | on HN ]

Re:First Impressions with Google Gemini by zerojames on Wednesday December 13, 2023 @01:20PM (#38631737)

After some prompting, I got a response. It identified the dog in the image, but the dog was in the center point. I gave Gemini the Home Alone image and it couldn't identify the Christmas tree, returning invalid coordinates.

The post has been updated accordingly.

[ Parent | on HN ]

Re:First Impressions with Google Gemini by s0laster on Wednesday December 13, 2023 @02:49PM (#38633252)

Just guessing but it might be some kind of safety such that Gemini can't be used to solve captchas.

[ Parent | on HN ]