-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
> However at some point you have to admit the LLM does generate things that are good answers. They might be good answers that happen to pass the smell test, but they are nonetheless good answers. For instance when you ask it for a snippet of code and it gets it right.
+1, though it took some time to figure out what questions work well. Yesterday, I asked chatGPT to help me document some R functions, and in my opinion, it did a great job [0]. I asked it to summarize what my functions were doing, and it gave me nice, plain-language summaries, and then reformatted my notes into the the form that Roxygen2 1] expects, and added some useful explanatory comments. Moreover, it was fast. It read and understood my code in a few seconds. No human can compete with that.
Is this bullshit? I would say it's more that chatGPT shows expertise with some formal conventions that can be kind of a pain to memorize and work with. You might think those conventions were BS in the first place, but regardless, they're what we settled on, and it's really nice to have a coding assistant do the tedious work.
I don't think chatGPT could have written the functions in the first place. But who knows what GPT [5,6...N] will be capable of
[0] https://github.com/setgree/sv-meta/commit/5f71e7c251b38e1981...
[1] https://cran.r-project.org/web/packages/roxygen2/vignettes/r...