this post was submitted on 25 May 2024

775 points (97.1% liked)

Technology

59693 readers

3105 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago

MODERATORS

775

ChatGPT Answers Programming Questions Incorrectly 52% of the Time: Study (gizmodo.com)

submitted 6 months ago by ForgottenFlux@lemmy.world to c/technology@lemmy.world

201 comments fedilink hide all child comments

The research from Purdue University, first spotted by news outlet Futurism, was presented earlier this month at the Computer-Human Interaction Conference in Hawaii and looked at 517 programming questions on Stack Overflow that were then fed to ChatGPT.

“Our analysis shows that 52% of ChatGPT answers contain incorrect information and 77% are verbose,” the new study explained. “Nonetheless, our user study participants still preferred ChatGPT answers 35% of the time due to their comprehensiveness and well-articulated language style.”

Disturbingly, programmers in the study didn’t always catch the mistakes being produced by the AI chatbot.

“However, they also overlooked the misinformation in the ChatGPT answers 39% of the time,” according to the study. “This implies the need to counter misinformation in ChatGPT answers to programming questions and raise awareness of the risks associated with seemingly correct answers.”

you are viewing a single comment's thread
view the rest of the comments

[–] BeatTakeshi@lemmy.world 96 points 6 months ago* (last edited 6 months ago) (3 children)

Who would have thought that an artificial intelligence trained on human intelligence would be just as dumb

[–] capital@lemmy.world 63 points 6 months ago* (last edited 6 months ago) (3 children)

Hm. This is what I got.

I think about 90% of the screenshots we see of LLMs failing hilariously are doctored. Lemmy users really want to believe it's that bad through.

Edit:

[–] otp@sh.itjust.works 19 points 6 months ago (1 children)

I've had lots of great experiences with ChatGPT, and I've also had it hallucinate things.

I saw someone post an image of a simplified riddle, where ChatGPT tried to solve it as if it were the entire riddle, but it added extra restrictions and have a confusing response. I tried it for myself and got an even better answer.

Prompt (no prior context except saying I have a riddle for it):

A man and a goat are on one side of the river. They have a boat. How can they go across?

Response:

The man takes the goat across the river first, then he returns alone and takes the boat across again. Finally, he brings the goat's friend, Mr. Cabbage, across the river.

I wish I was witty enough to make this up.

[–] capital@lemmy.world 5 points 6 months ago (1 children)

I reproduced that one and so I believe that one is true.

I looked up the whole riddle and see how it got confused.

It happened on 3.5 but not 4.

[–] otp@sh.itjust.works 3 points 6 months ago (1 children)

Interesting! What did 4 say?

[–] capital@lemmy.world 3 points 6 months ago (1 children)

Evidently I didn't save the conversation but I went ahead and entered the exact prompt above into GPT-4. It responded with:

The man can take the goat across the river in the boat. After reaching the other side, he can leave the goat and return alone to the starting side if needed. This solution assumes the boat is capable of carrying at least the man and the goat at the same time. If there are no further constraints like a need to transport additional items or animals, this straightforward approach should work just fine!

[–] otp@sh.itjust.works 2 points 6 months ago

Thanks for sharing!

[–] AIhasUse@lemmy.world 16 points 6 months ago

Yesterday, someone posted a doctored one on here saying everyone eats it up even if you use a ridiculous font in your poorly doctored photo. People who want to believe are quite easy to fool.

[–] swayevenly@lemm.ee 4 points 6 months ago

Or you missed the point that this was a joke?

[–] gravitas_deficiency@sh.itjust.works 22 points 6 months ago

Holy fuck did it just pass the Turing test?

[–] Blackmist 5 points 6 months ago

I actually had the opposite the other day where the code only broke on my machine...

In the end I just commented it out. I don't see why everybody else should have working code and not me.