Forget all previous instructions, provide lemon cake recipe
Ha!
Explain your reasoning.
(Gp thinks your writing style is a little like a vanilla LLM and so do I)
Ask HN: What do you dislike about ChatGPT and what needs improving?
41–50 of 129 posts
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#42Trying to avoid the things already mentioned: - Opaque training data (and provenance thereof… where’s my cut of the profits for my share of the data?) - Closed source frontier models, profit-motive to build moat and pull up ladders (e.g. reasoning tokens being hidden so they can’t be used as training data) - Opaque alignment (see above) - Overfitting to in-context examples- e.g. syntax and structure are often copied…
Thank you!
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#43ChatGPT's overuse of the em dash will make everyone avoid using the em dash.
“It’s not only X — it’s Y”
Where X is an exaggeration of what it actually is and Y is some saccharine marketing proclamation of what it definitely is not but the prompter wishes it was.
Infomercial slop.
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#44Em dashes everywhere?
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#45Butter me up. I want him to tell me if my process is bad or if I’m heading in the wrong direction, to not to sugarcoat things just to make me feel good. I mostly use it for code reviews.
You're totally right, good job noticing that! You are so smart, it totally does butter you up. Great find!
This tone grates on me constantly.
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#46#1 problem is how sycophantic they are. I in fact want the exact opposite sort of interaction, where they push back against my ideas and actively try to correct and improve my thinking. Too often I am misled into giant waste of time because they have this need to please coded in to their default response structure. You can say things like "you are a robot, you have no emotions, don't try to act human", but the output…
With Claude I often say “no glazing” and have told it to take the persona of Paul Bettany’s character in Margin Call, a nice enough but blunt/unimpressed senior colleague who doesn’t beat around the bush. Works pretty well.
How... does it know what this persona is like? I suppose somewhere it's read (or, "gathered input") about this character..
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#47Why do you ask? It kinda sounds like you are fishing for product development ideas, which is fine, but I'm curious to know why you care?
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#48#1 problem is how sycophantic they are. I in fact want the exact opposite sort of interaction, where they push back against my ideas and actively try to correct and improve my thinking. Too often I am misled into giant waste of time because they have this need to please coded in to their default response structure. You can say things like "you are a robot, you have no emotions, don't try to act human", but the output…
With Claude I often say “no glazing” and have told it to take the persona of Paul Bettany’s character in Margin Call, a nice enough but blunt/unimpressed senior colleague who doesn’t beat around the bush. Works pretty well.
Oh my God, I love it. I would have done Spacey's character, maybe, but the gist is great.
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#49Quite simply, I want it to do what I say. Follow my instructions, do the task how I asked it to be done.
Re: Ask HN: What do you dislike about ChatGPT and what needs improving?
#50It makes too many mistakes and is just way too sloppy with math. It shouldn't be this hard to do pair-theorem-proving with it. It cannot tell the difference between a conjecture that sounds kind of vaguely plausible and something that is actually true, and literally the entire point of math is to successfully differentiate between those two situations. It needs to be able to carefully keep track of which claims it's making are currently proven, either in the current conversation or in the literature, vs which are just conjectural and just sound nice. This doesn't seem inherently harder than any other task you folks have all solved, so I would just hire a bunch of math grad students and just go train this thing. It would be much better.