Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT Unicorn has drawn a unicorn

gpt-unicorn.adamkdean.co.uk

Post reply on HN
Print view View original

11–20 of 207 posts

Re: GPT Unicorn has drawn a unicorn

#11

Post by elaus »

suby wrote: post #8

I'm confused as to why this would see any improvement over time. Looking at the code, it's by default hitting the gpt 3.5-turbo API. Maybe I'm misremembering, but I thought I've seen statements from people working at OpenAI where it's been claimed that the API is static, we'd be informed of any changes to the underlying model. Is the model actually receiving updates? edit: Looking at previous days, too, it doesn't ex…

According to the author's blog post [1] the idea was that it "will use the latest gpt-4 model made available". Not sure if the code isn't up to date or this was changed in the meantime...

[1] https://adamkdean.co.uk/posts/gpt-unicorn-a-daily-exploratio...

Re: GPT Unicorn has drawn a unicorn

#13

Post by dspillett »

soxocx wrote: post #7

I would argue that `image-2023-04-25` looks comparable close to a unicorn. The art style does vary a lot though.

One or two others, 06-20 for instance, could be a very stylised unicorn too. Though that might be confirmation bias in my human brain making it see patterns it wouldn't have had it not been primed by the word unicorn before looking.

Re: GPT Unicorn has drawn a unicorn

#14

Post by xnorswap »

How do they get GPT-4 to produce valid SVGs so well?

I experimented with SVG generation and it would often produce junk that wasn't even valid as an SVG, and even when it did produce a valid SVG, was often a couple of blobs which it would describe as if it were the mona lisa while just being a couple of elements.

Re: GPT Unicorn has drawn a unicorn

#15

Post by sigmoid10 »

It has become common knowledge that GPT4 (and also 3.5) have problems with deterministic outputs (even at T=0). So what we're seeing here is just the effect of random sampling, not any actual change to the model itself. If you scroll down, you'll see other close attempts by the exact same model that could already be counted as a win depending on who you ask.

Edit: This comment section is a super fascinating case study on the inherent flaws in human cognition. Especially when it comes to seeing patterns in random noise. The fact that some people believe that the model really has to have changed in the past few days is amazing, because if you've kept up with the GPT architecture and the way OpenAI does things (especially on the API), it is incredibly obvious that nothing has happened. But people who want to believe that something has happened will definitely also start to see something.

Re: GPT Unicorn has drawn a unicorn

#17

Post by knolan »

I’ve asked ChatGPT to create models using Blender’s Python API. It typically generates working code. The API has been updated since 2021 so it’s expected that things might break.

It mostly just arranges simple spheres and cylinders. You can have it label parts which are usually correct.

It struggles with the orientation of things so if you ask it to model a plane the engine nacelles are oriented the wrong way but correctly positioned.

Post reply on HN