Hacker News Reader

You lads... I remember when we had to paste the code from the chat window into VSCode.

Remember when 200k was a HUGE context window, but you still had to be precious about how many files you'd paste into it?

I remember when most of my work came down to how to deal with the 512 token window of BERT.

Remember using the models pre-thinking? I had to build thinking into ChatGPT requests manually.

(I wonder if they stole that idea from my logs…)