yoouareperfect

I’ve been working on a project built with Next.js. Like most projects that want to be discoverable by humans, it needed a blog.

I didn’t want to:

run a headless CMS (Strapi, Contentful, etc.)

build and maintain a full blog UI in Next.js

deal with SEO tradeoffs from putting content on a separate subdomain

So I went with a slightly unfashionable but practical solution: WordPress.

The goal was simple:

Main app at yoursite.ai (Next.js)

Blog at yoursite.ai/blog/...

WordPress doing what it’s good at: writing, previews, publishing

No SEO penalty from split domains

There are a lot of questions online about this setup, and surprisingly little concrete guidance. This is the approach that worked for me.

Hi, this is a short Saturday morning project.

I usually want to learn how big repos work, but looking at the latest commit is not worth it. They more often than not contain a lot of yadda yadda and edge cases that aren't helpful when learning.

So I like to go to the very first commit and step forward.

This tool helps me do that, hope you find it useful as well!

What's the difference with lowering the temperature?

Openai owns the intelligence until it doesnt, and the open source model is good enough

To all the commenters asking how is this product different from another product:stop asking that question! Its a month old! instead why don't you chime in with your idea to help this founder out on how he can differentiate?

An example of the output would be nice

Very very nice :)

Super interesting, please do show what the other trees (collatz) that you mention look like

Coming for v2

OP here, Is there a way to figure that out?

Check the filters, not all batches are selected as default. Only the latest ones. If you select all of them, then there are many public companies

For scraping and all the processing, typescript. Embeddings: openai

For visualizing react (nextjs) + plotly (though the lack of mobile zoom makes me question if I should chsnge it)

should be fixed now, thanks!

haha awesome, shipped!

100%

As an argentinean a way to stand out and have US companies look at me is through my dev blog

https://mikealche.com

SEEKING WORK | Remote | Buenos Aires, Argentina

Willing to relocate: No

Technologies: React, React Native & Node.JS development with JavaScript and TypeScript. Python, Pytorch for Machine Learning. My dream stack which I LOVE working with is Next.js + tRPC + Prisma and PostgreSQL

Résumé/CV: I have a masters in computer science, with a thesis in deep learning.

I also have a blog at https://www.mikealche.com where I've written several blog posts that made it to the front page in Hacker News: General problem solving: https://www.mikealche.com/software-development/how-to-implem...

Databases schema design: https://www.mikealche.com/software-development/a-humble-guid...

React animations tutorial: https://www.mikealche.com/software-development/learn-react-a...

Email: mikealche at gmail

Location: Buenos Aires, Argentina

Remote: Yes

Willing to relocate: No

Technologies: React, React Native & Node.JS development with JavaScript and TypeScript. Python, Pytorch for Machine Learning. My dream stack which I LOVE working with is Next.js + tRPC + Prisma and PostgreSQL

Résumé/CV: I have a masters in computer science, with a thesis in deep learning.

I also have a blog at https://www.mikealche.com where I've written several blog posts that made it to the front page in Hacker News: General problem solving: https://www.mikealche.com/software-development/how-to-implem...

Databases schema design: https://www.mikealche.com/software-development/a-humble-guid...

React animations tutorial: https://www.mikealche.com/software-development/learn-react-a...

Email: mikealche at gmail

If AMD and Intel team up on soft to replace CUDA, then I'm selling all my NVDA stock and even shorting it short term

SEEKING WORK | Remote | Buenos Aires, Argentina

Willing to relocate: No

Technologies: React, React Native & Node.JS development with JavaScript and TypeScript. Python, Pytorch for Machine Learning. My dream stack which I LOVE working with is Next.js + tRPC + Prisma and PostgreSQL

Résumé/CV: I have a masters in computer science, with a thesis in deep learning.

I also have a blog at https://www.mikealche.com where I've written several blog posts that made it to the front page in Hacker News: General problem solving: https://www.mikealche.com/software-development/how-to-implem...

Databases schema design: https://www.mikealche.com/software-development/a-humble-guid...

React animations tutorial: https://www.mikealche.com/software-development/learn-react-a...

Email: mikealche at gmail

Location: Buenos Aires, Argentina

Remote: Yes

Willing to relocate: No

Technologies: React, React Native & Node.JS development with JavaScript and TypeScript. Python, Pytorch for Machine Learning. My dream stack which I LOVE working with is Next.js + tRPC + Prisma and PostgreSQL

Résumé/CV: I have a masters in computer science, with a thesis in deep learning.

I also have a blog at https://www.mikealche.com where I've written several blog posts that made it to the front page in Hacker News: General problem solving: https://www.mikealche.com/software-development/how-to-implem...

Databases schema design: https://www.mikealche.com/software-development/a-humble-guid...

React animations tutorial: https://www.mikealche.com/software-development/learn-react-a...

Email: mikealche at gmail

Amazing! Congrats on launching!

What? this is the first time that I hear about this. This is a typical Next.js app like any other else. Is there any default config that next.js users should disable?

EDIT: Well, I just fixed it. Seemed like an issue with sentry not actually hiding the source maps.

Next time, please a private email instead of a hn comment would be way less destructive.

Is anyone training LLMs outside of Meta, OpenAI, etc... ?

I don't much get the point. For huge models, it's impossible to outcompete them. For smaller models, isn't mistral or LLaMa good enough?

What are other startups finetuning LLMs for?

I first read it as "War-GPT" and was very relieved to find it was otherwise.

Thank you very much for the suggestions. Just shipped the fixes for autocapitalization and the space you mention (which was actually a margin).

Deploying as I type

update: Just found out that the Impact font wasn't rendering correctly outside of my Macbook. So fixing that as well

Very interesting. Are you generating a jpg and then converting it somehow to svg? Or is the AI model creating SVG directly?

Very nice! I asked it for "React Suspense" and the results were pretty ok!

Very nice! Thanks for sharing, will definitely give it a try. I think we settled for chat interface to play with LLMs, but there's nothing really holding us back to try new ways.

What's a good use case for this library? Something that needs to send messages from an embedded system?

How's the wake-sleep pattern different from the exploration/exploitation in Deep Reinforcement Learning?