from Andy Boothe
I’m using Google BigQuery to do some ETL, and have found OpenAI’s products to be enormously helpful for the task.
A new client recently asked for some assistance working with Sunshine Act data. Since I expect additional asks about this data set to come in over time, rather than fuss with the generic UI, I decided to load the entire dataset into BigQuery instead. ChatGPT’s o3-mini-high model has generated schemas and ETL queries extremely well, accelerating my work by at least a factor of 2x.
There’s a lot of discussion about how to use ChatGPT to generate tests for code. Another interesting use case I’ve seen fairly little coverage of is generating DTOs from JSON. Here is an example with the prompt I’ve put together applied to JSON from the manifest of a Distributed Map Run.
Continue reading “Generating Java record classes with Jackson Annotations to map JSON using ChatGPT”I’m porting Jonas Wagner‘s excellent smartcrop.js, which analyzes an image to recommend a good crop, from JavaScript to Java.
When porting code, I always try to understand it along the way so that if (when) there are bugs, I’ll have an idea of where the bug might be. I used ChatGPT 4 to untangle a particularly terse bit of code, and was — frankly — shocked at how well it did.
Continue reading “Reverse Engineering with ChatGPT: An Example”