all AI news
Running Python micro-benchmarks using the ChatGPT Code Interpreter alpha
Simon Willison's Weblog simonwillison.net
Today I wanted to understand the performance difference between two Python implementations of a mechanism to detect changes to a SQLite database schema. I rendered the difference between the two as this chart:
From start to finish, this entire benchmarking exercise took me less than five minutes - because ChatGPT did almost all of the work for me.
ChatGPT Code Interpreter alpha
I ran the benchmark using the new ChatGPT "Code Interpreter" alpha, which I recently gained access to, presumably …
ai alpha benchmark benchmarking benchmarks chatgpt chatgpt code chatgpt plugins code database difference exercise five generativeai llms new chatgpt performance promptengineering python running schema sqlite work