Haha, interesting! What made you stop?

I might get back to you regarding the domain

Fair point, I gathered the crowdsourcing element to be implicit but I included it for completeness. The novelty here is the direct interface to LLMs.

I thought OpenAI had been sleeping a bit and given up on the image generation race. However, with the recent release of the oddly named 4o Image Generation model (Why not continue with the DALL-E naming scheme? I personally love the pun) it looks like they cooked up one hell of a model.

If you are into visual GenAI you have probably already seen many examples of quite incredible outputs from the new model. However, we decided that we wanted to make a large scale evaluation, based on 200k human responses across 13k image pairings.

Unfortunately that also meant that we had to generate a large amount of new images, and since OpenAI have not yet opened up API access, we had to do it manually through the UI :(.

The benchmark tests the model in coherence, prompt-alignment, and overall aesthetic preference. Especially for the first two, OpenAI's new model is very far ahead of the competition.

Check out the detailed results and the collected data which is openly available on huggingface!

Let me know if you have questions or feedback!

Can definitely relate to the feeling of getting buried on producthunt! Nice work on this, might just have to try it out.

Cool! Did not know about this. I was not able to see anything other than the pipe - which I assume is the SDR versions, maybe some clearer instructions/limitations (and description of what you should expect to see) would be beneficial.

good point. I added more information to the README

Can you provide some context or additional info?

Looks nice. What do you do to fetch the job postings?

Looks like currently you only support jobs in the US, is that correct?

Thanks! US (majority), Canada, and remote. Jobs are sourced from https://github.com/SimplifyJobs/Summer2025-Internships and https://github.com/SimplifyJobs/New-Grad-Positions. I'm looking into additional sources.

Why does it show Chinese characters in the tab title once the countdown starts? Is this intended? 番茄工作法

Because OP used Deepseek not only to code the entire app. But also to generate his future roadmap.

Pretty cool! And also really difficult as it turns out. Love that you can try it without signing up! Runs quite smooth and I like the simplicity of the UI. Maybe a button to return to the starting position is missing?

Thanks! Good idea to add the return button.

Call me old fashioned, but I think a speech should be something personal that reflects you and the person/people on the receiving end of the speech. If you do not know what to say, then maybe there is no need for a speech. That being said, it could be helpful to some people that have something particular things on their mind, but unsure how to structure it into a speech.

Nice job on finishing this project though!

Yeah, I agree. I would consider it rude to present the output straight from the tool. But if you use it as an advanced template that gives you structure it can be useful to overcome the blank page syndrome.