CN
Conspirador Norteño
@conspirator0.bsky.social
Data Scientist/Musician/Participant in the General Confusion.
Resist autocracy and research/counter disinformation. I serve the realm.
conspirator0.substack.com/
www.youtube.com/watch?v=F4_Li-f6DRQ
2k followers930 following696 posts
The results are extremely clear. Having the LLM generate Python code to do math and then running the resulting code was both faster and more accurate than having the LLM do the math itself, and the difference in performance widens as the numbers get larger.
CN
Conspirador Norteño
@conspirator0.bsky.social
Data Scientist/Musician/Participant in the General Confusion.
Resist autocracy and research/counter disinformation. I serve the realm.
conspirator0.substack.com/
www.youtube.com/watch?v=F4_Li-f6DRQ
2k followers930 following696 posts