Migrating from GPT-3.5-turbo to GPT-4o-mini
Guess when I switched models.
Recently OpenAI released GPT-4o-mini — a new flagship model for the cheap segment, as it were.
- They say it works "almost like" GPT-4o, sometimes even better than GPT-4.
- It is almost three times cheaper than GPT-3.5-turbo.
- Context size 128k tokens, against 16k for GPT-3.5-turbo.
Of course, I immediately started migrating my news reader to this model.
In short, it's a cool replacement for GPT-3.5-turbo. I immediately replaced two LLM agents with one without changing prompts, reducing costs by a factor of 5 without losing quality.
However, then I started tuning the prompt to make it even cooler and began to encounter nuances. Let me tell you about them.
Hello, World!
Nice to meet you, friends!
My name is Aliaksei, but feel free to call me Tiendil — it is my nickname for the last 20 years or so :-)
A few words about me:
- By occupation, I am a software developer, mostly backend, mainly in Python.
- For most of my career, I've been working in game development on big projects and own indie games.
- I like playing games, reading books, and writing long-reads about partially complex topics.
You can find more about me:
- In the about page
- In my GitHub profile: github.com/tiendil
- In the LinkedIn profile: linkedin.com/in/tiendil
This is my first blog post in English, but not the first one in general. I have blogged in Russian for a long time and have always wanted to share my thoughts with the English-speaking world. At last, I found some time to adapt my blog, and here we are!
Most of the future posts will be bilingual (English & Russian). Also, with time, I'll translate my most interesting old posts.
Once again, nice to meet you! Feel free to contact me by any means.