GPT-4 increased BCG consultants’ performance by over 40%

Re:GPT-4 increased BCG consultants’ performance by over 40% by simonw on Saturday September 30, 2023 @11:25AM (#37716335)

That's one of about a dozen at this point - but yeah, that's the one that I used LLMs to research the initial triggers and schema design for.

Here's the transcript (it pre-dates the ChatGPT share feature): https://gist.github.com/simonw/1aa4050f3f7d92b048ae414a40cdd...

I wrote more about it here: https://simonwillison.net/2023/Apr/15/sqlite-history/

Here's another one I built using AppleScript: https://github.com/dogsheep/apple-notes-to-sqlite - I wrote about that here: https://til.simonwillison.net/gpt3/chatgpt-applescript

[ Parent | on HN ]

Re:GPT-4 increased BCG consultants’ performance by over 40% by gumballindie on Saturday September 30, 2023 @09:21PM (#37721629)

While it is impressive that an ai can generate all this, the code is anything but significant. Using triggers for history is one sure way to bring a scalable system down fast and one of the first lessons a junior will learn.

[ Parent | on HN ]

Re:GPT-4 increased BCG consultants’ performance by over 40% by simonw on Sunday October 01, 2023 @09:36AM (#37725825)

Are you sure that holds with SQLite? My benchmarks so far have shown it to add a pretty inconsequential overhead.

Also: not every system has to be a scalable system. That's another lesson junior engineers (should) learn.

[ Parent | on HN ]