Comparing to a study of 25 humans seems like too small a sample to say it performs as well as humans generally
Holy shit this is fascinating!
Someone should build a system that scrapes all open source repositories and uses an LLM to generate up to date documentation, and puts it in one big searchable place
NerdyPopRocks
joined 1 year ago
I wouldn’t doubt that the CPO is trying their hardest to convince people to care but people just dont