image created by Margaux Peltat for the Chilled Cow YouTube channel
Time for #DEVDiscuss β right here on DEV π
Coding your own AI in 2023 with fastai
Vincent Will γ» Feb 27 '23
#python
#deeplearning
#ai
#beginners
Inspired by @vincenius's Top 7 post, tonightβs topic is...building your own AI π€
Questions:
- Have you tried to build your own machine learning model or AI-based application?
- What tools did you use to build it? What tools would you recommend, and which ones should devs stay away from?
- For you, is working with ML models and AI a career, a hobby/interest, both, or neither?
- Any triumphs, fails, or other stories you'd like to share on this topic?
Top comments (8)
I've now deployed production ML models and tapped into some of the OpenAI endpoints for certain uses β and I think I'm still just a "web dev", however, I do have some upgrades skills in terms of using and understanding these technologies.
Like β I didn't have to write any of this from scratch, I tapped into really useful dependencies I pulled into a project and learned to make the most of. Like anything, it takes some deep focus to get the hang of, but we are definitely in "standing on the shoulders of giants" territory.
Literally doing certain AI stuff "from scratch" is the work of world-leading-experts, but in a lot of ways my own work with these technologies is about as deep as my work with databases, where I really just get to know the abstractions and domain-specific languages I am provided.
I'm a "web dev" that's venturing into ML/AI and integrating it with Nuxt.js PWAs to achieve app-like experiences. I'd love to read/explore some of your use-cases or learning paths however possible that is. Thanks a lot.
I've built and recently launched AmjadGPT last weekend.
As for tools/technologies, I used Langchain (js lib) and Next.js as the frontend UI.
AI is definitely a hobby, but I'm slowly intertwining it into my career and using it more at work.
I've played around with several open source libraries for various tasks. One thing that is critical: Have a use case in mind! I've found it really tough to wrap my head around some of this without a clear idea of a problem I could be solving. It doesn't have to be "real", but it should be concrete in your mind β otherwise it's hard to tell if the thing is working.
Generally I'd also say: Have an idea of how much data you need. Some tools require a lot of data, some actually work on relatively little.
I built a browser extension that turned emoji art into accessible captions using Tensorflow. The ML inference worked well, but it would slow down the website a lot.
Back in the late 80s I made some character recognition neural networks from scratch in ZX Spectrum BASIC π₯
I would like to build my own AI like Jarvis π₯
I would like to build my own AI like Siriπ€©