In two offerings of Georgia Tech's ECE 4320, 36.66% of students found all three reasoning errors in a ChatGPT o1 power factor solution, versus 75% finding all or nearly all of GPT-4's cruder errors, and the newest model o3 solved the problems almost correctly.
Exploring the Capabilities and Limitations of Large Language Models in the Electric Energy Sector,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
support 1representative citing papers
citing papers explorer
-
VArsity: Can Large Language Models Keep Power Engineering Students in Phase?
In two offerings of Georgia Tech's ECE 4320, 36.66% of students found all three reasoning errors in a ChatGPT o1 power factor solution, versus 75% finding all or nearly all of GPT-4's cruder errors, and the newest model o3 solved the problems almost correctly.