The main ‘fighting’ that I’ve experienced is it being “confidently” incorrect about something I’m very knowledgeable about, so I have to constantly check what it’s doing anyway. I’ve also had to keep it from creating unnecessary functions and variables, from leaving empty comments (as in, empty of substance or actual context, leaving comments just to leave comments). It also constantly makes up problems to “solve”. It seems to have only gotten worse and worse with each subsequent model release. It wastes so many tokens doing things that don’t matter or are otherwise incorrect.
I honestly feel less productive in my job with it for 80-90% of the time, but the company makes me use the slop bot. It works for the basics, but any time I add complexity, I begin having to fight against the machine. I could see how I could feel more productive, it can iterate through code very fast. But most of it has something wrong, is bloated, or is just completely irrelevant. I ultimately just end up feeling like I wasted an entire day to get a subpar and soulless result.
That makes sense. I use it to solve bugs which it’s good at, but don’t use it for writing code. And yeah I do have to fight it a little to stay on track and stop looking for other bugs.
Only yesterday, on my personal free chatgpt account it had to commit to memory “stop stating things as fact that you don’t know for sure” lol. Like you’d think that would be trained in
It’s explicitly not trained in because people don’t go to the free chatGPT to get actual truthful answers (or “I don’t know”), they go there to have their biases confidently confirmed.
The main ‘fighting’ that I’ve experienced is it being “confidently” incorrect about something I’m very knowledgeable about, so I have to constantly check what it’s doing anyway. I’ve also had to keep it from creating unnecessary functions and variables, from leaving empty comments (as in, empty of substance or actual context, leaving comments just to leave comments). It also constantly makes up problems to “solve”. It seems to have only gotten worse and worse with each subsequent model release. It wastes so many tokens doing things that don’t matter or are otherwise incorrect.
I honestly feel less productive in my job with it for 80-90% of the time, but the company makes me use the slop bot. It works for the basics, but any time I add complexity, I begin having to fight against the machine. I could see how I could feel more productive, it can iterate through code very fast. But most of it has something wrong, is bloated, or is just completely irrelevant. I ultimately just end up feeling like I wasted an entire day to get a subpar and soulless result.
That makes sense. I use it to solve bugs which it’s good at, but don’t use it for writing code. And yeah I do have to fight it a little to stay on track and stop looking for other bugs.
Only yesterday, on my personal free chatgpt account it had to commit to memory “stop stating things as fact that you don’t know for sure” lol. Like you’d think that would be trained in
It’s explicitly not trained in because people don’t go to the free chatGPT to get actual truthful answers (or “I don’t know”), they go there to have their biases confidently confirmed.
I thought that’s what social media is for (idk I don’t use it, unless this counts)