Interesting how these findings refute the assertion that LLMs are just predicting the next word. Sometimes they plan ahead.

This seems like it was made specifically for me and my interests.

At least it’s not 50 cents per second of processing time.

I was NaN years old when I learned this.

I’ve delved into writing assembly only on the level of a student project. I really enjoyed it though. Obviously implementing a python math library would be far more complex but wouldn’t it be worth it for the possible performance gains?

What is the reason to avoid assembly? Is it prohibitively difficult?