Ask HN: How did LLMs change your products?

I'm currently unemployed and looking for work, but I can say I have seen more than one job listing that mentions LLMs, and even one that specifically mentioned GPT-4 as part of the company's tech stack. So, people definitely are integrating LLMs into their products.

Made it easier to document code. You can send the function as context, and it will generate a well-formatted docstring that accomplishes 90% of the task!

well... My company was aiming to do codegen to fix errors. We took quite some time to figure out what to do with AI in our product. When we finally implemented something, we found apis like gpt4 to be quite expensive, though GPT4 did work well for the task. We later turned towards llama2 and codellama, which worked decently but had a higher "wrong output" rate.

And then they laid off 60% of the workforce (We were only 30 people)... I am not sure LLMs are going to affect their outlook very positively in the long term.

Made it way easier to generate the hundreds of lines of boilerplate crap you have to write with typescript backends