Saving you some time, if you have a Macbook pro M1/M2 with 32GB of RAM (I presume a lot of HN folks would), you can comfortably run the `34B` models on CPU or GPU.
And... If you'd like a more hands on approach, here is a manual approach to get llama running locally
- https://github.com/ggerganov/llama.cpp
- follow instructions to build it (note the `METAL` flag)
- https://huggingface.co/models?sort=trending&search=gguf
- pick any `gguf` model that tickles your fancy, download instructions will be there
and a little script like this will get it running swimmingly
I like the fact minimalist approaches, like svelte, htmx and alpine.js are getting more and more traction.
I felt like fighting this fight alone for years in the golden years of node, webpack and react where everybody was creating crazy stacks and adding GraphQL and so on, to basically get what Django + jquery did 10 years ago in a tenth of the time and code.
So far I also survived:
- xml is the future
- let's use nosql for all the things
- you must use the same language at the back and front
- yes, you site must have an AMP version (ah, you forgot this one, didn't you? It was sooo imporant, and then pouf, it was gone like tear in the rain)
- yes, your home page must be an SPA
- you can't code anything without async
- you can't live without a message queue
- everything must become a micro service
- of course you need a container for that
- of course you need a orchestrator to organize those containers
- of course you need the cloud, it would be crazy to deal with those containers and orchestrators yourself
- dude, why do you have a server? Use a serveless backend!
- dude, why do you have a backend? Just call saas from the edge!
Every year, some generation of engineers have to learn the concepts of "there is no silver bullet", "use the right tech for the right problem", "your are not google", "rewriting a codebase every 2 years is not a good business decision", "things cost money".
A generation was raised on usable designs which clearly communicated interactability with a consistent visual language. It is only natural that they would come to think of computers as inherently ordered, understandable devices. Machines had always been this way.
It was obvious to this new generation that the affordances of youth were purely redundant. Clutter. Overhead. Junk! Widget by widget, pixel by pixel, bevels were smoothed. Tasteful gradients and transparency replaced harsh outlines. Explanatory text was tucked away. Manuals became brochures, then a lonely slip of paper with a URL. Maybe a QR code.
Now my screen is the very picture of elegance and sophistication. There are no extraneous details. Indeed, there are no details. I caress my phone's surface gently, hoping to see a sliver of its rapturous visage peel back, hinting that I have found the first step in the puzzle box of its interaction model.
Alas, no dice. Maybe I can hunt down a how-to video... to show me how to hunt down a video...
2. Focus on smaller to mid-size companies (large corporations likely have the tech team and contractors to cover almost of their needs)
3. (Optional) Search for each company on Linkedin and add managers with relevant roles (VIP of sales, project manager, marketing manager, etc.). The goal is to familiarize them with your name so they're more likely to open your email (step 5).
5. Reach out to the most senior person with a relevant role at each company with a personalized 1-on-1 email.
The key here is to review their website and business and share 2-3 ideas of what you can them build or fix (if there are any glaring issues or vulnerabilities). They may not necessarily use your ideas but the goal is stand out and help them understand how they can put your programming skills to use. Here's a template you can reference: https://artofemails.com/new-clients#developer
There are a lot of businesses out there whose teams don't have the capacity to build everything so they would be keen to have a reliable freelance programmer help them bring some features or projects out of backlog.
