I'm still thinking the greatest danger of GPT is its abundantly demonstrated ability to turn off and/or get past people's critical thinking capabilities moreso than its ability to replace people's jobs. I'm yet to see a code snippet past 4 lines that particularly impresses me. Is that legitimate progress in the field? Yes. But not quite ready to throw in my towel.
I do somewhat fear my career turning into cleaning up ChatGPT-created messes. Of course I've already cleaned up my fair share of previous coder's messes. But ChatGPT messes have the potential to be a real nightmare even beyond that.
Everything beyond 4 or 5 lines has contained bugs, be they subtle or blatent (as this one is). But what's really concerning is that either A: the author doesn't notice before writing about how amazing ChatGPT is at code or B: the author doesn't even think to check. Both are terrible, but each in its own way. And it is this reaction that concerns me more than the quality of ChatGPT itself.
Maybe you have stellar junior engineers, but I find reviewing GPT code as very similar to reviewing purely human code. We just need to get much better at verification…
My comment is specific to GPT, which is why I said that and not AI. GPT is not the whole of AI.
But the fact that people are already back to full-blown 1970s-style "the computer said it! it must be true!" with GPT-based technologies does not bode well for our ability to assess future technologies either. The possibility of future AI technology being just an even-more obfuscated and convincing error generator at this point can not be dismissed, if people are already failing this badly at evaluating what is still an embryonic technology.
I'm sure people will accuse me of being a Luddite about AI in the future, and I'm sure they won't appreciate "Look, it's not that I don't appreciate the technology, what I'm not trusting is you and your assessment, since you have a proved past track record of being unable to assess AI technology reliably." I've got all sorts of friends to make in the future with that.
I've seen this and similar predictions repeated so many times. What are they based on? Who says those systems "will improve"? How will they "improve"? Why is everyone so certain?
To do a really good job I think you need an LLM. So the relevant Python code would be an API call to chatGPT. I just tested it.
Me: Tell me if the following sentence contains any typos or grammar errors:
"This is my CV.I am a experianced developer. I have 5 years of experiance."
ChatGPT:
Yes, there are typos and grammar errors in the sentence. Here is the corrected sentence:
"This is my CV. I am an experienced developer. I have 5 years of experience."
The corrections made are as follows:
1. "experianced" should be "experienced".
2. "experiance" should be "experience".
3. The first sentence is incomplete and should be separated from the second sentence with a period
Point #3 correctly calls out the error (missing space) but describes it incorrectly. Also it corrected "a" to "an" (good for a grammar checker) but didn't list it as a mistake.
And even if it generated \s{2,}, well, a multiple whitespace would be a typo? You need a dictionary to identify typos.