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

GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

adamkdean.co.uk

Post reply on HN
Print view View original

1–10 of 109 posts

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#3

Post by ShamelessC »

As is noted in the paper from which this is inspired from: GPT-4's image generation capabilities were severely diminished by the instruction/safety-tuning process. Unfortunately this means the currently available model from the API won't be very capable - certainly not as capable as the early version of GPT-4 that Microsoft had access to.

edit: I'm specifically referring to the "image generation by trickery (e.g. SVG)" technique being diminished. Other tasks were diminished as well though - is my understanding.

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#4

Post by abrichr »

MH15 wrote: post #2

Would be useful if the prompts used to generate the drawing code were included in the site.

They appear to be here:

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

      { role: 'system', content: `You are a helpful assistant that generates SVG drawings. You respond only with SVG. You do not respond with text.` },
      { role: 'user', content: `Draw a unicorn in SVG format. Dimensions: 500x500. Respond ONLY with a single SVG string. Do not respond with conversation or codeblocks.` }

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#5

Post by famouswaffles »

ShamelessC wrote: post #3

As is noted in the paper from which this is inspired from: GPT-4's image generation capabilities were severely diminished by the instruction/safety-tuning process. Unfortunately this means the currently available model from the API won't be very capable - certainly not as capable as the early version of GPT-4 that Microsoft had access to. edit: I'm specifically referring to the "image generation by trickery (e.g. SVG…

It's not just image generation the rlhf worsens too. Calibration (confidence on solving a question in relation to ability to solve that problem) went from excellent to non existent. and you can see from the report that the base model performed better on a number of tests. Basically a dumber model.

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#6

Post by dangond »

> The idea behind GPT Unicorn is quite simple: every day, GPT-4 will be asked to draw a unicorn in SVG format. This daily interaction with the model will allow us to observe changes in the model over time, as reflected in the output. Is it useful to do this every day? Correct me if I'm wrong, but my understanding is that OpenAI does not update the models available in production incrementally on a day-to-day basis.

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#7

Post by sp0rk »

Did you generate a bunch all at once before starting to get some idea of what the natural variance looks like? I would think it's important to verify some level of progression over time, because with the current four it seems entirely possible that the examples could have all been generated at the same time with no changes to the model.

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#9

Post by arthurcolle »

famouswaffles wrote: post #5
ShamelessC wrote: post #3

As is noted in the paper from which this is inspired from: GPT-4's image generation capabilities were severely diminished by the instruction/safety-tuning process. Unfortunately this means the currently available model from the API won't be very capable - certainly not as capable as the early version of GPT-4 that Microsoft had access to. edit: I'm specifically referring to the "image generation by trickery (e.g. SVG…

It's not just image generation the rlhf worsens too. Calibration (confidence on solving a question in relation to ability to solve that problem) went from excellent to non existent. and you can see from the report that the base model performed better on a number of tests. Basically a dumber model.

Are you saying this specifically for the GPT-4 API endpoint compared to idealized described GPT-4 from the paper?
Post reply on HN