liorgrossman

Thanks.

Interesting about the handwriting - I very rarely handwrite anything anymore, but maybe I should do it ocassionally.

Typically when I type something digitally, I forget about it pretty quickly.

I may try it for some product/architectural stuff where recall is more important.

Interesting.

Say you're looking for something from a few days ago, you grep all recent text files to find the relevant note?

How does it work with a physical notebook, though? I guess that's harder to grep

Uh nice, I never heard of logseq, it look really nice!

How do you use OneNote for work though, isn't it slow? (not a user, but I assumed it'll be something similar to Google Keep)

Thanks!

Hit me up if you have any questions

Well, it started off this way, but I went through several iterations with the audit prompt and the system prompt to improve the issue detection, the solutions suggested, tag them, reduce hallucinations, provide approximate image coordinates, provide examples to the model, etc. It's currently at over 20 lines of prompting and I guess this will grow over time.

Thanks for being one of our early adopters!

Glad to hear it did find something that you can correct.

Regarding the points about fine print (and the screenshot not loaded correctly) - would you kindly reply with the URL of the website you audited here, or email it to me to feedback at flawless.is ?

I'd love to take a look and see if these issues could be fixed or improved.

Of course, thank you for the kind words!

Yeah, happy to get it roasted by real (human) UX folks for some sanity check.

That's great to hear.

I think now I better understand your original question.

Yeah, to run an audit again on that same site, you'd need to pay again.

Otherwise, I'll have to put in place user management & user rate limits to avoid abuse, since someone could run this 50 times on their website within a given day, and currently OpenAI limits us to 100 queries per day.

All great points, thank you!

I think GPT-4V perception of size might be distorted, since it downsizes everything to be 512px wide before scanning it. I wonder how can this be overcome, I'll try to play with the prompts to instruct it specifically about sizes.

Regarding the "Meet Slack for Enterprise" - you're right, it is weird, looks like it's hallucinating. I'll try and dig deeper.

Thanks for giving it a try.

One time meaning you are charged $1.99 one time, and you can audit one URL, the one you've chosen on the main page.

After you pay, it takes you to a unique URL with a token. Might be a good idea to send users email with this URL...

There's no concept of logging in or logging out right now, that's why that URL is important. It looks something like this: https://flawless.is/audit?url=https%3A%2F%2Fslack.com%2F&t=1...

If you can't find this URL in your browser history, please ping me at lior at lifehacklabs.org, and I'll restore this URL and send it to you!

Eventually, Hacker News ended up bringing 20,000+ visitors. Had to upgrade our urlbox screenshot API account twice in 1 hour just to keep up with the demand.

This Hacker News post could have cost $1,000+ if the API rate limit hadn't kicked in. Oh well, silver linings...

Since almost no one could use the app (too many people, and not enough quota from OpenAI), I added a $1.99 one-time payment per audit. This would probably decrease the number of users and also help cover the insanely high costs.

Hey Rory, are we talking about the same app? https://uxaudit.vercel.app

It's really weird that you've seen an Apache2 landing page, as this page is hosted on Vercel.

Do you still get an error message while visiting the same page?

Yep, this is my life now: https://twitter.com/LiorGrossman/status/1722681560128762208

Thanks. Yeah, it seems that even on Tier 5 the limit is 100/day, that's not enough for any production app. I hope they go out of preview mode soon and therefore increase the limits

Oh, this is pretty cool! I was hoping to try and create a custom GPT too, but couldn't resist trying the API before.

Yeah, I think there are limitless possibilities. Yesterday I saw on twitter someone using GPT-4V to narrate a video game in realtime, just mind-blowing. The future is here.

Yeah, I feel like the Vision API will unlock many new opportunities. Honestly, it's been super easy to work with it. Just sad that they have such a low rate limit in the preview phase.

Thanks, it's OpenAI's rate limiting indeed.

Just deployed a version that shows some UI indications of OpenAI limit errors.

Please try again later today.

Boy, that escalated quickly...

Just deployed a version that shows some UI indications of OpenAI limit errors.

Yep, it looks like it :( Any idea how to overcome this limitation?

Yes, just getting a lot of traffic from HN. Try again tomorrow, please? Error: 429 Rate limit reached for gpt-4-vision-preview in organization org-..

Yes, just getting a lot of traffic from HN. Please keep window open and try again in 15min, sorry...

Error: 429 Rate limit reached for gpt-4-vision-preview in organization org-... on requests per day (RPD): Limit 100, Used 100, Requested 1. Please try again in 14m24s. Visit https://platform.openai.com/account/rate-limits to learn more.

Thank you!

Currently it's about:

* Rendering the screenshot (urlbox): $0.02

* GPT-4V 1K input tokens = $0.01

* GPT-4V 1K output tokens = $0.03

* GPT-4V Vision pricing (per image size): $0.008

Total: 6.8 cents per a single audit

May not seem like much, but I see a lot of traffic coming from HN, so say 10K people use it, it'll cost $680...

Yeah that's a good point. I wanted to keep the UI clean (Google search alike), but people don't even know what the results look like.

Yo dawg, I heard you have a UX audit app, so I ran the UX audit app on the UX audit app, so it does a UX audit to the app!

Hi HN,

Lior, the maker of DreamGift here.

I've always struggled with finding nice gift ideas for friends/family/wife, and often would go down a rabbit hole, trying to find something original and personalized.

Recently, I discovered how good ChatGPT is in generating gift ideas when given the right context and information.

I set out to build DreamGift, a friendly ChatGPT-alike gift advisor, powered by GPT-3.5 and Amazon's API: https://dreamgift.ai

The product is free, of course. The business model is affiliation, since I don't intend to sell any gifts directly (this would be a huge operational headache).

In the short term, my focus is further improve the gift suggestions, there's a lot of research and prompt engineering involved.

In the future, I'd like to take personalization to the next level: imagine it suggesting tailored gift ideas for your friend by browsing and learning from their Instagram profile. Still not 100% sure it's feasible, but I'd definitely like to try that.

Would love to hear your feedback, roasts, and answer any questions you may have!

Thanks for the heads up! We'll take a look.

Love the xkcd style chart!

<shameless-plug> We also show the GitHub star history, alongside npm download history, issue and PR stats on Openbase: https://openbase.com/js/react/insights </shameless-plug>

That makes sense, no GraphQL API back then.