tl;dr: Over the next few months, I will be writing a series of articles on building applications using large language models. If you would like to get these articles in your email as I write them, then scroll down to the bottom and subscribe (its free!)
Artificial intelligence - and large language models in particular - is of course the hot topic in the industry right now, and hype is at an all time high. Social media is full of "influencer" posts like "These 10 ChatGPT prompts are all you need" and "Say goodbye to Excel" or jumping on the latest model "that obsoletes everything". Many people read these articles and think that having a prompt or hopping on to the latest model/framework is enough to do anything.
On the other side are people deep into AI who expect everyone to know probability, statistics and linear algebra before being able to work in AI. Furthermore, this field is evolving so fast, with new techniques coming out every month, replacing old methods.
So what does the average developer - who wants to build applications, but not necessarily get into the math and research - do?
There is a gap here, and filling that gap is what I've been working on. I believe having a strong understanding of fundamentals is critical here. New models keep coming out, and techniques keep changing. Tons of frameworks are coming out, and the popular one changes on a week by week basis.
However, fundamentals do not change. The transformer model on which current day LLMs are built was developed in 2017 and it's still here today. Knowing fundamentals places one on a strong footing to adapt to whatever new features or framework is the popular of that moment.
On that note, I will be posting a series of articles on this topic right here on Playful Python. I'm looking to build an intuitive understanding of what is going on, rather than lean on rigorous maths. My target audience is the application developer and not the researcher.
Most of there articles will be for subscribers. Subscribing is free. Enter your email in the form below to subscribe, and you will get an email everytime I write a new article.
PS: If you don't see a sign up form below then you are already a subscriber 🎉If you are reading this article by email, then you are already a subscriber 🎉🎉
PPS: Know anyone else who might be interested in this series? Send them this link and ask them to subscribe - https://www.playfulpython.com/subscribe/ 😎
Did you like this article?
If you liked this article, consider subscribing to this site. Subscribing is free.
Why subscribe? Here are three reasons:
- You will get every new article as an email in your inbox, so you never miss an article
- You will be able to comment on all the posts, ask questions, etc
- Once in a while, I will be posting conference talk slides, longer form articles (such as this one), and other content as subscriber-only