Live data from Hacker News

Ask HN: What do you dislike about ChatGPT and what needs improving?

news.ycombinator.com

61–70 of 129 posts

Re: Ask HN: What do you dislike about ChatGPT and what needs improving?

#61

It 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…

Curious to know how the different models compare for you for doing math. Heard o4-mini is really good at math but haven’t tried o3-pro much.

Re: Ask HN: What do you dislike about ChatGPT and what needs improving?

#65

Earlier quoted context omitted.

How... does it know what this persona is like? I suppose somewhere it's read (or, "gathered input") about this character..

Interesting question. I described what I liked about his character, so maybe it's just using that and is nodding along to the character's name. Maybe it has access to the script or some analysis of the character.

most likely it was trained on tons of fan ficfion where his character is thoroughly described.

Re: Ask HN: What do you dislike about ChatGPT and what needs improving?

#66
There is this bias problem not just with ChatGPT, but with LLMs in general. It is not able to be objective. For example, if you paste arguments from 2 lawyers, for which lawyer A uses very strong words and writes a lot more VS that of lawyer B, which has a strong case but says less. LLMs in general will always be biased and err towards the side which uses stronger language and write a lot more.

This to me, is a sign that intelligence/rationalization is not present yet. That said, it does seem like something that can be "trained" away.

Re: Ask HN: What do you dislike about ChatGPT and what needs improving?

#68

Earlier quoted context omitted.

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..

The screenplay script is on line:

https://www.scriptslug.com/script/margin-call-2011

Re: Ask HN: What do you dislike about ChatGPT and what needs improving?

#69
Context windows please. ChatGPT Plus users have only 32k context windows looks like a discrimination. With such limited context windows, the model became dump just after 1 or 2 questions for any serious research request. I truly hope the GPT-5 plus would increase it at least to 200k. Compare to Gemini 2.5 with 1 million context window, that's already inferior but at least it's acceptable. It's $20, sama, not cheap chunks money

Re: Ask HN: What do you dislike about ChatGPT and what needs improving?

#70

#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.

This is perfect, especially because I spend a good amount of time talking about financial topics with the bots. Will try this one out!
Post reply on HN