[lazyasciiart]

An LLM ability to do a task is roughly correlated to the number of times that task has been done on the internet before. If you want to see the hype version, you need to write a todo web app in typescript or similar. So it's probably not something you can fix with prompts, but having a model with more focus on relevant training data might help.

[KTibow]

These days, they'll sometimes also RL on a task if it's easy to validate outputs and if it seems worth the effort.