GPT Unicorn has drawn a unicorn

Post by imdsm » Thu, Aug 10, 2023, 2:14 PM UTC

throwuwu wrote: post #65

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…

If the model understood the spacial relationships as well as the one that produced the original drawings of a unicorn then variance in the choice of the next token should produce many similar but somewhat different images of unicorns. None of the images until today bear any resemblance to the original images.

Post by imdsm » Thu, Aug 10, 2023, 2:16 PM UTC

kachnuv_ocasek wrote: post #88

hk__2 wrote: post #69

Earlier quoted context omitted.

It’s using GPT-4 by default, but we can’t know what it uses for real since that’s in the environment config.

It says "gpt-4-0613" on the web page as well. Why would they pretend it's GPT-4 but use GPT-3.5 in the background?

    "Env": [
        "VIRTUAL_HOST=gpt-unicorn.adamkdean.co.uk",
        "LETSENCRYPT_HOST=gpt-unicorn.adamkdean.co.uk",
        "HTTP_PORT=8000",
        "STORAGE_PATH=/data",
        "OPENAI_API_KEY=sk-**SNIP**",
        "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
        "NODE_VERSION=16.17.1",
        "YARN_VERSION=1.22.19"
    ],

Post by imdsm » Thu, Aug 10, 2023, 2:18 PM UTC

elaus wrote: post #11

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...

Post by imdsm » Thu, Aug 10, 2023, 2:20 PM UTC

horse_dung wrote: post #53

devjab wrote: post #16

Is it just me or doesn't image-2023-04-25 look like a unicorn as well?

4-22 is my favourite… hahaha

Post by Karawebnetwork » Thu, Aug 10, 2023, 2:27 PM UTC

itsoktocry wrote: post #110

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…

> 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 You need only to look at the discourse around the Tesla FSD superusers to see this: they report a glitch at an intersection one day, then believe the ne…