News for hackers. Stuff that matters.
Re:Vibechart by qustrolabe on Thursday August 07, 2025 @06:58PM (#44831430)
GPT-5 would've caught this mismatch for sure
Re:Vibechart by datadrivenangel on Thursday August 07, 2025 @07:06PM (#44831501)
Claude and ChatGPT actually took me several prompts to get them to identify this. They recognized from a screenshot that labeled axes that start at zero can be misleading, but missed the actual issue.
Re:Vibechart by nonhaver on Thursday August 07, 2025 @08:35PM (#44832110)
thats hilarious actually. gives credence to the gpt theory haha
Re:Vibechart by KronisLV on Friday August 08, 2025 @01:01PM (#44839271)
How hard would it be for the model to be like: "Okay, there's a bar chart in the picture, the left bar is 350 px in size and the right bar is 120 px. Meanwhile, the labeled values are X and Y, which doesn't seem to match those relative sizes due to this math I ran thanks to all the cool deterministic tools I have."

Apparently quite a bit.

Re:Vibechart by macNchz on Thursday August 07, 2025 @07:06PM (#44831492)
That seemingly depends a bit on how hard you ask it to think, or how hard it decides to think based on your question.
Re:Vibechart by danpalmer on Thursday August 07, 2025 @08:10PM (#44831956)
"ChatGPT, this slide deck feels a bit luke warm, help me make a better impression"

I could completely believe someone who is all-in on the tech, working in marketing, and not really that familiar with the failure modes, using a prompt like this and just missing the bad edit.