It's my understanding that ChatGPT isn't very good with facts and figures.
100% disagree with that. In particular re: donkey-work code-related tasks – Jenkins and so on – it has been a genius in terms of writing any script you can think of. We lately incorporated a mono-repo ‘micro-frontend’ soluton called NX, and it has answered every single question you could think of in the most perfect way possible. All of its ‘suggestions’ have been incorporated into the project, and each has added a new layer of automation that was otherwise difficult to extract from the obsure NX documentation.
Similarly, for essential boilerplate that my brain seems to de-prioritise over more innovative tasks, ChatGPT hits the nail on the head every single time. It has increased my productivity tenfold in this regard.
I’ve also quite a big interest in medicine, and, for example, I was quizzing ChatGPT on the iqoro recently, an interesting innovation for neuromuscular training, and all of its knowledge has been spot on, absolutely perfect. Again, it was difficult to get the facts from the site – I now am seeing unprecedented gains from this device, which is quite difficult to ‘master’ without a guide like ChatGPT to set you on the right path. It is an extremely effective piece of ‘kit’ – but only if you ask the right questions and get the right answers.
It makes mistakes from time to time, but so do humans. I would say 95% of its answers have either a) advanced my career to some measurable degree or b) advanced my health and fitness in the same manner.
So yeah it gets my goat because the intellectual laziness of the argument is emblemic of a significant societal problem in the United States of America, and that is something i care about.
Cool story bro.
