I can't give you much advice about Claude or Copilot since I refuse to use either, but I do use open weight models which I can run on my own hardware.

If you're interested in exploring LLMs from that angle, download llama.cpp and some models that'll fit on whatever hardware you've got and start poking at it. I got started a few months back, and it's been an interesting experience. llama-server (which is one of the tools that comes with llama.cpp) includes a web UI. You can also use llama-cli on the command-line (but that gets old pretty quick).

Gemma and Qwen are the two most popular open weight model families right now since they're small enough to run on local hardware and give good enough results that they can be useful.

I've found them to be useful for:

• debugging assistance (e.g. Qwen often points out typos I've made in Python scripts that would've taken me a while to find otherwise)
• brainstorming (think: interactive rubber ducky you can bounce ideas off of -- set a system prompt telling it NOT to give you code though unless you explicitly ask for it for this use case; they're too eager to write code otherwise)
• OCR
• natural language to JSON data extraction (e.g. here's an email, here's a reference table, here's an example of what I want, extract the data from the email into similar JSON...)
• prototyping web UIs (e.g. here's the HTML skeleton for [insert project here], write CSS to style it; here's a screenshot of how it looks now, fix the bug that causes [issue] in the CSS; iterate)
• light scripting (e.g. straightforward but tedious tasks that can be handled by a ~100 line or less Python script)
• quick search/snippet generation for things that I would've done by Googling for a link to documentation/stackoverflow a few years ago -- this works well enough for webdev questions; YMMV with other subjects
• answering questions based on reference data buried somewhere in a PDF

If you try to do batch processing with them, it's helpful to think about them like a flaky distributed system -- i.e. use timeouts, retries, error handling mechanisms that account for invalid output, etc.

from my experience they are usually integrated into the ide the business uses.

EDIT: I’d also like to hear from those downvoting this post.

Just make up whatever and pretend to know how to use AI. It's not like the people recruiting will know any better, they're operating on hype and copium. Worst case scenario, you can just burn tokens to show pretend work.

There was a question in this community that might get you to think otherwise "Has your company lost its mind with AI, too?" (non-Cloudflare link at https://suppo.fi/post/11441199).

Seriously if you want to learn GenAI (or AI) workflows, start using them yourself in your personal life. That way you can honestly try it out and maybe even create something. If you do follow a tutorial, don't create and publish exactly what they do (as everyone else has done that).

What's the best way to get an intro to these tools?

Find a website with a free chat bot and ask it for guidance on learning these tools. If that doesn't work, try another site. Keep asking for guidance to run up their chat bot bill until it blocks your IP range. Rinse and repeat with a new bot, or a VPN.

That's the most fun way to learn about this stuff.

Oh, the best way? I have no idea.