Faizann20

Developer here, I love using ChatGPT and Perplexity finance but both of them have serious issues with out-dated data. Trying to address that by leveraging real time data and building an agent on top of it. Happy to answer any questions.

Developer here: Lots of apps around mock interviews with AI, and some around filtering as well, so this is not a new idea.

But a lot of the existing apps are not super easy to use, and come with a lot of restrictions and paywalls. With LLMs getting so cheap in 2024, I don't think it costs a lot on my end to offer this for free for quite some time, atleast to all consumers.

As for the business side, every friend of mine that owns a company has this pain point that they spend way too much time going through job applications, so that's a genuine problem I'm trying to solve here.

Any feedback around the idea would be awesome.

Quick tip: You can grab any image, and use the GPT vision API to convert it into code, it does a pretty decent job.

You can try this at Brewed.dev

Disclaimer: I'm the developer of the tool.

A live version for this has been online for a few days here! https://brewed.dev/

Just fixed the bug.

Thanks for letting me know. Mind sharing exact links? Would appreciate it

Thank you!

Perfect, thank you.

Love hearing that. Let me know how it goes.

Tailwind actually. Not really since the backend covers for that. As long as you can provide it instructions in plain english, it does a decent job of building that design. And if you don't like it, you can always edit it in various ways - by asking the AI, by using a UI editor, or by changing the HTML code itself.

Developer here. I have to spend a lot of time developing frontends which is not what I like since I am a backend engineer. To that end, developed this tool that uses GPT4 and GPT4 vision to convert user queries & images into HTML code.

Happy to answer any questions. Would appreciate feedback since we just launched yesterday.

Developer here.

Happy to take in requests for more podcasts to add - should be available on Youtube since that's what this is covering right now.

Happy to answer any other questions as well.

We initially labeled a small sample of gradient colors which we bootstrapped to create our initial classifier. We did a few tuning iterations until the product was ready.

Founder here. Happy to answer any questions you people might have. We built this tool for developers and designers who want to find great gradient colors from a single color. A random forest algorithm is used to find the best possible colors for you based on thousands of candidates. We'd love for everyone to give it a try.

This is some good feedback, thanks a lot. I'll make sure to include some of these points in our next iteration of the product.

Thanks again.

I don't disagree with you at all. As mentioned in some other comments, our initial goal wasn't to generate perfect logos like professional designers. It was to let new startup founders who can't pay much buy a decent logo.

And we're not stopping here, no way! We are working on some features that will create a lot of stuff from scratch based on several deep learning architectures. We are excited to work on those features and we hope you'll like them once they are done.

Again, the goal is not to replace designers. The goal is to complement them or give founders a tool to get a decent logo in a few bucks. Happy to talk more.

That seems like a great idea. I'll definitely see what I can do. Thanks!

What we are doing different?

We are training a deep learning architecture that creates logos from scratch. But we wanted to ship a simple yet decent product before we started working on more sophisticated stuff. In a couple of months, users will have option to select icons that are entirely generated by an AI engine.

Honestly speaking, having worked on over 8-10 ML and DL projects in last 4 years, I am quite aware of the fact that the term "AI" is used at places where it shouldn't be used.

The term "AI" in our product comes from the fact that in long term, we actually want AI to create entire logos/icons/fonts and we're actively working on this right now. Most of our current models use Conv Nets, Word Embeddings, and Random Forests which still atleast come under the category of AI.

The reason I have been trying to explain everyone about the inner workings of our product is to demonstrate that we're indeed using different ML systems and they actually make sense where they're used.

Founder here. If the website was down, please retry. We just fixed some issues and everything should work well now.

We're not claiming we're magical. Our machine learning systems are fairly straight forward right now but we're going to keep improving and understanding brand information is on the top of our todo list. The task of understanding emotion is non trivial but not impossible. We are working on a few areas to sort this out. Please keep in touch, we'll try our best to improve this product as well as we can.

The apology is because the fact that our system was not able to create logos that match the context you provided. That is what we intend to do and we want to do it well. The problem right now arises from the facts that we're somewhat in the range of 50-100k icons but we really need a couple million perhaps to always be able to offer you something that semantically matches your description. We'll keep working on our product and hopefully very soon, people won't have such issues.

Thanks for the feedback though. Really appreciate it.

Apologies for inconvenience. It's working again. You can try now.

You can follow us on twitter https://twitter.com/DesignwithAiHQ

For updates on our product.

Any suggestion? Would love your feedback on this problem.

Yes, we are planning to launch on product hunt. Thanks for your suggestion and appreciation :)

Yes. We are planning to target that audience.

Comparison with Looka (and Brandmark), both of them are excellent competitors and it just raises the bar for us. But we want to be different in several ways.

More automation by AI - That's our main goal. If you create logos on Looka and Brandmark repetitively, you'll observe patterns. That happens because although Looka and Brandmark are applying AI, they are still getting a lot of information from the user before making logos i.e "select the logos you liked", "select the color schemes you like". We want to do away with all these things and only require the brand description. This cuts the time in less than half according to what we've measured. Below are some of the AI use cases we are working on. No other website is doing that right now.

AI Based Coloring - Our colors are not hand-picked by us. They are entirely generated by machine learning algorithms. We are also working on icon coloring using AI where the icon will have multiple colors entirely added by AI.

AI Based Icons - Almost every website including ours is using repositories of icons from websites like Flaticons, Nounproject etc. We are working on adding another layer where the icons are generated by the AI system itself.

AI Based Suggestions - We believe our in-browser customizer is relatively easier to use than others. We give the user an option to just select items that are suggested to him/her by our machine learning algorithms. We've got extremely positive feedback about this and are happy that people are liking it.

These are some of the areas where we're trying to be different than our competitors. We also offer more affordable prices than both Looka and Brandmark.

I apologize if you didn't like the logos. We have a feedback loop in place that takes care of this. Since we just launched a week ago, there are some logos that users don't usually like.This is by no means perfect right now but it'll get better with time. We already have 118 logos that users have ranked using the "like" and "dislike" buttons. We'll soon be using all this data to create better logos.

That's a very real concern for us. We are taking a few measures for this and are continuing to look into this. - As soon as a logo is purchased with a unique icon, we delete that icon from our data. - We manually go through our icon repositories and try to find icons that have already been used in logos and delete them.

We'll continue doing this until we are left with stuff that has not been used anywhere else in a logo.