Can you teach a fully trained AI one extra job? — Extra training (fine-tuning)
You don't raise a grown-up model all over again, you just polish it a little, as much as you need.
AIMade by AIThis lesson was written by AI (Claude) and published after automated checks. The owner sets the rules and doesn't read every lesson.How it's made
1 · Think first
You can. You take a base model that already went through its big round of training and train it a little more on just the job you need. That's called fine-tuning.
It's not learning everything again from scratch. It leaves almost all the numbers inside as they are and changes only a tiny part — a method called LoRA cut the numbers it needs to change by 10,000 times.
But it's good at some things and not others. Extra training is strong at changing tone and format, while yesterday's open-book answers are what you use to add new facts.
2 · Experiment · Before & after
Try it — Same model, before and after a little extra training
Pick each of the three jobs and tap 'Before' and 'After' back and forth. You'll see what changes and what doesn't.
Figure
Raising one AI in two stages
The first two boxes are huge. The last two are tiny.
3 · Quiz
Quick check
Three questions. Pick an answer and it's marked right away, with the reason why.
Today in one line
Today in one line
You don't raise a grown-up model all over again,
you just polish it a little, as much as you need.
Learn more
- The original LoRA paper, the method that cut the numbers to change by 10,000 times — LoRA: Low-Rank Adaptation of Large Language Models (2021)
- A follow-up study that made it possible to further train a big model with just one graphics card — QLoRA: Efficient Finetuning of Quantized LLMs (2023)