How do you know you yourself aren't an AI, being trained on synthetic data?
Because I have no reason to. How do you know the earth isn't orbited by a flying teapot?
how can you tell if I'm being facetious or not?
How to get coworkers to stop giving me ChatGPT-generated suggestions?
131–138 of 138 posts
Re: How to get coworkers to stop giving me ChatGPT-generated suggestions?
#132Earlier quoted context omitted.
If I understand correctly, you're not happy with the way ChatGPT can realise it's own mistake? or that it makes the mistake? I am not really sure, what is the problem exactly?
it doesn't "realize its own mistake", it requires negative feedback from the user to spur it into "apologizing" and trying to fix the "mistake(s)". It doesn't matter if the mistake is real or imagined. even the uncensored (less RLHF'd) models do this - apologize after negative feedback and attempt to fix. And "it's" only means "it is", the possessive is "its". You probably knew that, but didn't realize your own mista…
>It doesn't matter if the mistake is real or imagined.
Is this based on your experience?
My experience with ChatGPT is that rarely it apologises or attempts to fix something that is correct, though sometimes it does apologise and give you an alternative or the exact same working solution.
Re: How to get coworkers to stop giving me ChatGPT-generated suggestions?
#133Earlier quoted context omitted.
That you think this is weird advice or advice that makes LLMs look good shows that your position is one of reflective opposition rather than understanding and experience with the things. If you interact with them much it's an obvious course of action. It will come up with nonsense, and if you tell it it's nonsense it will immediately apologise and explain why the nonsense was nonsense. It will come up with good infor…
> It will come up with nonsense, and if you tell it it's nonsense it will immediately apologise and explain why the nonsense was nonsense. This only makes sense if you believe LLMs are something more than they are. As someone who knows how LLMs work pretty well I don't. The presumption here is that the following advice is 100% better or correct and I also don't believe that.
The assumption that anything is "100%" is absurdist. It is not a meaningful or useful discourse.
Re: How to get coworkers to stop giving me ChatGPT-generated suggestions?
#134Re: How to get coworkers to stop giving me ChatGPT-generated suggestions?
#135Earlier quoted context omitted.
It's not "tattle to the boss", it's using a manager as a resource to help a team work together more effectively. That's part of what they're paid for. If it was one person, a 1::1 could make sense, but they're getting swamped by teammates interrupting their work, it's not their job to deal with that and delegating it to the person whose job it is makes a lot of sense.
I guess different strokes. As an employee, before I escalate any issue I always try to do my best to fix it myself first (barring some efficiency gain like it's far easier for someone else to resolve). And as a manager I appreciate reports who do the same.
As a past manager (and getting ready to manage another team now), the last thing I'd want would be for anyone on my team to have to deal with being swamped by inane requests from another team and that's something I'd step in to help with even unasked. As an IC whose time has always been highly valuable my current manager and none of my past managers would ever have put up with a group of people from another team interrupting me and squandering my time like that and would have stepped in as well.
Re: How to get coworkers to stop giving me ChatGPT-generated suggestions?
#136Earlier quoted context omitted.
I'd say tell them to ask GPT why it won't work. It'll say something like "You're right, I've made a mistake...". This should illustrate that it can be helpful, but it's just aiming to please whether or not the solution is workable or sane.
Is this really your suggestion to someone dealing with a coworker making your work harder to do by gumming up the works with a bad tool? This is cult like behavior.
I don't see the problem. What's the issue? What is cult like about this?
Re: How to get coworkers to stop giving me ChatGPT-generated suggestions?
#137Re: How to get coworkers to stop giving me ChatGPT-generated suggestions?
#138I'm not looking forward to having to argue with a coworker that thinks MongoDB is web scale because ChatGPT told them so. It will be a hell of a lot more annoying than[1] [1] https://www.youtube.com/watch?v=b2F-DItXtZs&t=3s
It would be more helpful for yourself and your colleagues if you didn’t base technology opinions on 13 year old memes.