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

31–40 of 207 posts

Re: GPT Unicorn has drawn a unicorn

#31

Post by pietroppeter »

sigmoid10 wrote: post #15

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 stud…

Is there some reference or explanation on why the model it is non deterministic at temperature 0?

Re: GPT Unicorn has drawn a unicorn

#32

Post by xnorswap »

dannyw wrote: post #27
xnorswap wrote: post #14

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.

This part: https://github.com/adamkdean/gpt-unicorn/blob/master/src/lib...

That'll do it! I wonder how many retries it averages, the images list "tokens", but it's a bit cryptic to work out how to translate that to attempts?

Re: GPT Unicorn has drawn a unicorn

#33

Post by horse_dung »

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…

The API layer receives fairly regular updates, but the model is (as I understand it) mostly static.

Within GPT there is an intentional randomness element called temperature which is how you get different answers each time.

I could copy their prompt and ask GPT4 to draw other things, but I’ll probably just look at the next few unicorns from this site :)

Re: GPT Unicorn has drawn a unicorn

#34

Post by amelius »

nullpilot wrote: post #2

For a second I thought this was about a GPT based product hitting a certain valuation, but I'm much more entertained by the actual content. This is great.

For a second I thought this was about a GPT based agent building a company that turned into a Unicorn.

Re: GPT Unicorn has drawn a unicorn

#35

Post by jwestbury »

xnorswap wrote: post #14

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.

Looks like it just reprompts for a valid SVG if the result isn't valid: https://github.com/adamkdean/gpt-unicorn/blob/master/src/lib...

Re: GPT Unicorn has drawn a unicorn

#38

Post by calderknight »

bhouston wrote: post #21
sigmoid10 wrote: post #15

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 stud…

100%. This person is trying to find patterns in random noise and believes they are meaningful. The original post hurts my head with its bad logic.

I don't see the bad logic.

Re: GPT Unicorn has drawn a unicorn

#39

Post by motoboi »

sigmoid10 wrote: post #15

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 stud…

Agreed. But have you seen the original talk?

I believe he's trying to find an unicorn similar in style to the one generated by the original researcher.

It's so sad that openai has a far more capable model internally that it can't give open access to because of safety (or any other argument).

Re: GPT Unicorn has drawn a unicorn

#40

Post by Frummy »

pietroppeter wrote: post #31
sigmoid10 wrote: post #15

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 stud…

Is there some reference or explanation on why the model it is non deterministic at temperature 0?

https://news.ycombinator.com/item?id=37006224
Post reply on HN