← Back to context

Comment by SeanAnderson

2 years ago

Not impressed with the Bard update so far.

I just gave it a screenshot of yesterday's meals pulled from MyFitnessPal, told it to respond ONLY in JSON, and to calculate the macro nutrient profile of the screenshot.

It flat out refused. It said, "I can't. I'm only an LLM" but the upload worked fine.

I was expecting it to fail maybe on the JSON formatting, or maybe be slightly off on some of the macros, but outright refusal isn't a good look.

FWIW, I used GPT-4 to stitch together tiles into a spritesheet, modify the colors, and give me a download link yesterday. The macros calculation was trivial for GPT-4.

The gap in abilities makes this feel non-viable for a lot of the uses that currently impress me, but I'm going to keep poking.

8 comments

SeanAnderson

Reply
sockaddr  2 years ago

> I just gave it a screenshot of yesterday's meals pulled from MyFitnessPal, told it to respond ONLY in JSON, and to calculate the macro nutrient profile of the screenshot

> Not impressed

This made me chuckle

Just a bit ago this would have been science fiction

  • SeanAnderson  2 years ago

    Hah, I agree. Looking at it from that perspective, my expectations are sky high :)

    Thanks for the reminder. It is definitely cool to be living in the future.

    • FergusArgyll  2 years ago

      I got to use gpt-3 and DALL-E before chatgpt was released and I remember just staring at the computer not believing my eyes.

      me less than 2 years later: "no that's not the bug!, I ALREADY TOLD YOU I TESTED FOR THAT"

  • ChatGTP  2 years ago

    I think this goes for nearly all material things, as fantastic as they are, they're not magic. We get used to them very fast.