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.

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

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)

It might be an old-school habit (40 y/o here), but I keep a .txt file on my Mac with tons of snippets and references, e.g. useful git or shell commands, TypeScript/CSS reference, helpful ASCII characters, my daily TODOs, and more.

For technical stuff, I find it much faster than using janky apps like Evernote or Google Keep, so it never slows me down.

However, it's still not ideal - since my .txt file has become pretty large, I'm finding it hard to keep it up-to-date or organized, and it's getting harder to find things.

I've been thinking of building a better alternative that would also allow easy sharing/discovery/forking of technical notes from others (https://earlytap.com/get/gitnotes), but I'm still pondering whether this is an actual need shared by enough people.

Curious to hear: are any of you keeping .txt files with notes on your computer too? What do you use the .txt file for? Did you find any better alternatives?

Comments URL: https://news.ycombinator.com/item?id=44226946

Points: 2

# Comments: 7

Hit me up if you have any questions

As an avid reader, I read many nonfiction books every year. While enjoyable, I find that nonfiction books usually contain a lot of information that is not relevant or helpful for me.

That's why I decided to build TailoredRead (https://tailoredread.com/). It’s a tool that uses AI to write full-length books that are tailored specifically to the reader.

Here’s how it works:

1. You answer a few questions: book subject, key topics, your background, your goals

2. The AI generates the book outline - title, description, chapters and subchapters, key insights, etc. I found that Claude 3.5 Sonnet produces great results here, but I want to give GPT o1 a try as well.

3. Our backend starts a worker that orchestrates the creation of the book. This typically takes 5-10 minutes, and you can start reading the book as it’s being written. Here I found that Claude 3.5 Sonnet produces significantly better output than GPT 4o and other models, but it still requires a lot of prompting and breaking down the book into smaller chunks.

4. We run a dedicated worker to create the book branding and cover with Claude, DALL-E, and some CSS.

5. The book is created and formatted in a semantic HTML format, which is then displayed in a book-alike paginated interface, similar to Kindle (React/Next). You can also download the book as a PDF or send it to your Kindle device.

So far, I've seen early users create fascinating books about a diverse set of subjects, e.g. programming, business, science, history, travel, hobbies, etc. There are 100+ free book samples from our early users here: https://tailoredread.com/books

I'd love to hear your feedback about TailoredRead and answer any questions you may have!

Comments URL: https://news.ycombinator.com/item?id=42064003

Points: 3

# Comments: 2

So I decided to build https://statussight.com/ - essentially it's an aggregator that crawls 3,000 status pages every minute, so I can see the status of all services and infrastructure in one central place.

I also added the capability to create a custom dashboard so that you can monitor specifically the services that you use. I built StatusSight using Next.js, with the frontend being deployed to Vercel, and the status page monitor deployed to Hetzner with Coolify.

Let me know your thoughts!

Comments URL: https://news.ycombinator.com/item?id=41193847

Points: 10

# Comments: 0

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.

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.

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.

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!

It's pretty simple to use - just go to https://flawless.is and enter your homepage or landing page URL.

I'm using the urlbox API to get a screenshot of your page, then I utilize GPT-4V to analyze the screenshot, find potential usability and conversion issues, suggest fixes, and highlight the relevant areas in the screenshot (although the position is sometimes inaccurate).

Last week, I launched it on Hacker News (https://news.ycombinator.com/item?id=38207892), but I wasn't ready for the 20,000 visitors that came next... Unfortunately, GPT-4V has a rate limit of 100 events daily, so almost no one could use the service - EPIC FAIL.

To manage demand, I now priced the service at $1.99 (still less than a cup of coffee), which should keep the demand at bay, and also cover the costs of GPT-4V, the screenshot API, and hosting.

As a proof of concept, there are some demo audits on the homepage you can click and check out.

Please let me know your thoughts and suggestions on how to improve it!

Comments URL: https://news.ycombinator.com/item?id=38266912

Points: 15

# Comments: 15

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.

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?