And they are tasks with standardized best practices. I knew that I wanted to write an internal web app that allowed users to upload a file to S3 using Lambda and storing the CSV rows into Postgres.
I just told it to do it.
It got the “create S3 pre-signed url to upload it to” right. But then it did the naive implementation of download the file and do a bulk upsetting wrong instead of “use the AWS extension to Postgres and upload it to S3”. Once I told it to do that, it knew what to do.
But still I cared about systems and architecture and not whether it decided to use a for loop or while loop.
Knowing that or knowing how best to upload files to Redshift or other data engineering practices aren’t knew or novel
They aren’t. But there are a lot of mistakes that can happen, and until an AI workflow is proven that it can’t happen, it’s best to monitor it, and then the speed increase is moot. Hunans can make the same kind of mistakes, but they are incentivized not to (loosing reputation and their jobs). AI tools don’t have that lever against them.
And so are mid level developers. A mid level developer who didn’t have 8 years of experience with AWS would have made the same mistake without my advice.
I would have been just as responsible for their inefficient implementation in front of the customer (consulting) as I would be with Claude and it would have been on me to guide the mid level developer just like it was on me to guide Claude.
The mid level developer would never have been called out for it in front of my customer (consulting) or in front of my CTO when I was working for a product company. Either way I was the responsible individual
I just told it to do it.
It got the “create S3 pre-signed url to upload it to” right. But then it did the naive implementation of download the file and do a bulk upsetting wrong instead of “use the AWS extension to Postgres and upload it to S3”. Once I told it to do that, it knew what to do.
But still I cared about systems and architecture and not whether it decided to use a for loop or while loop.
Knowing that or knowing how best to upload files to Redshift or other data engineering practices aren’t knew or novel