HMC Tech VS Diffyn

HMC Tech's answer

The most complete, well organized, not ad bloated tech compare tool.

Diffyn's answer:

Addresses workflow and change management on LLM prompts, provide teams with traceability and visualization of tests across multiple models, provide deeper understading into efficiency of these prompts.

HMC Tech's answer

Not bloated with ads, more specs, and clean design.

Diffyn's answer:

Diffyn is the platform that specializes on both change management and multi-model analysis.

HMC Tech's answer

Anyone who cares deeply about tech!

Diffyn's answer:

Professionals incorporating LLMs or AI tools in their workflow and wants to keep track of changes and test their prompts.

HMC Tech's answer

Node.js, MySQL, Coolify, Cursor.

Diffyn's answer:

React, Next.js, POSTGRESQL

HMC Tech's answer

How it started.

I consumed so much tech videos and tech articles, naturally, I became the tech guy for my family and friends. So I was like... why don't I make a website on Webflow (or the like) where I can put all the stuff I know about these topics. So people can check my website to get the best recommendation. I right away saw the limitations of what you can do on these website builders. So I was like... maybe I should learn how to code? I saw a Web Dev course from Colt Steele on Udemy on sale ~$13. So I gave it a try. Best investment ever. I finished the course in 1 month, then bought 2 more: React, MySQL, took another month for these 2. React was too difficult for me. MySQL made more sense to me compared to MongoDB. So after 2 months I started building.

Building HMC as Recommendation System.

The first version was based on user input with a small database. Database only has products I would recommend. It made it easy to fill up the database. The algo was very simple: sliders each controlling a use case. For example: gaming level at 10 = 1080p 60FPS games, so find GPU capable of such, same for the other sliders. Once all inputs are in, get lowest price!

First Launch!

I finished the first working version of HMC on Sep 28, 2022.

The Problem.

HMC only works well if prices and availability are up to date. A laptop with a massive sale can become the best laptop to buy... as long as it is available. What's the point of the best laptop with amazing price that no one can buy? Unfortunately, I had to do all that manually. So right away it became unmaintainable. So this needs to be automated before HMC becomes useful as a recommendation system.

The Pivot.

So because of the need to keep pricing & availability up to date was a must to make it useful, I pivoted to making it a compare engine instead. Only issue with this is that the database I had was too small for it to be a proper compare site. So I started adding more products to the database. With so many "might as well add this and that" I ended up adding all CPUs, all GPUs, almost all Apple products, all Microsoft Surface, all Pixel Phones, all Razer Laptops, almost all game consoles.

Relaunch HMC as Compare Engine.

Now it has enough data to start working as a compare engine. Enjoy!

Diffyn's answer:

I started working on Diffyn when I notice that prompting has become an essential part of work across many industries. While there are version control platofrms like github, they are not designed for just prompt management are can be overkill such applications, it is also not integrated natively with various LLMs and relevant tools for users to validate ideas and visualise results properly.