Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

news.ycombinator.com

Post reply on HN
Print view View original

121–129 of 129 posts

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

#121

Post by ComplexSystems »

beering wrote: post #61
ComplexSystems wrote: post #50

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.

o3 is the best OpenAI model but it still makes tons of mistakes. It's got a very strong background in most of undergrad level math, and a decent amount of grad level machine learning stuff, but its tendency to hallucinate means it will greedily fixate on some initial conjecture early on, not realize it's a conjecture, and continue to assert that it's true for the rest of the conversation. Similarly, if it thinks something is impossible, it will just assert that and continue to assert again and again that it's impossible, even if it's actually true. It's like the mathematical version of a hallucination. There is no real reason it should do this for grad level topics - they just haven't trained it enough. It has a survey level knowledge of a TON of ideas, which can be great if you are looking for topics related to something, but as far as the details of exactly how things are related, what subtleties and caveats there are and so on, it will just hallucinate its first guess and get stuck there for the rest of the conversation.

o3-pro is maybe marginally better, but it takes a very long time to respond and so I rarely use it.

4o is much worse and so I usually use o3.

Gemini 2.5 Pro is much better - and free. Grok 4 is also probably up there with Gemini 2.5. They just have less tendency to hallucinate in this way in general: they will spend more time reasoning, checking claims, searching for prior literature, etc. They still mess up, but not quite as much as o3. I don't use Sonnet or Opus for math all that much - my impression was that o3 was better than Sonnet 3.7 but not sure about 4.

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

#122

Post by 8bitsrule »

zyruh wrote: post #110
8bitsrule wrote: post #88

I've most disliked made-up, completely incorrect answers easily proven to be so, followed by GPT-grovelling when contradicted with the facts, promises to 'learn' and 'I'll strive to do better'. Time after time over months, the same dodging and weaseling. A simple 'I don't know, I haven't got access to the answer' would be a great start. People who don't know better are going to swallow those crap answers. For this we…

LLMs need regular transparency - fact checking so the user can verify an validate accuracy.

DuckDuck's service started adding one or two backup source citations to their 'Search help' service lately. One can check them to see how trustworthy they are.

Of course backup citations can be hard for 'services' breaking copyright laws to train their machines to be thieves. And legally getting into the realm of academic papers could be expensive.

So for them, providing a trustworthy source is hard to do. Actually knowledgeable people are needed to distinguish trustworthy sources. So there are several discernable motivations to just fake it ... if you don't care what you're doing to the innocent.

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

#123

Post by divan »

I just want it to be able to read/edit text files. Coding agents can edit code, but for writing we're limited to copy-pasting dance.

I use projects for research purposes for articles/scripts/etc, and I would love to use chatgpt in voice mode to talk about the article I'm writing. Like "hey, read last paragraph from the article... let's elaborate on topic X... here what I would love to write - x,y,z - please improve the style and read it back to me... nice, add it as a next paragraph."

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

#124

Post by zyruh »

divan wrote: post #123

I just want it to be able to read/edit text files. Coding agents can edit code, but for writing we're limited to copy-pasting dance. I use projects for research purposes for articles/scripts/etc, and I would love to use chatgpt in voice mode to talk about the article I'm writing. Like "hey, read last paragraph from the article... let's elaborate on topic X... here what I would love to write - x,y,z - please improve t…

Makes sense. Is there another LLM you're using for this that works better than GPT?

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

#125

Post by divan »

zyruh wrote: post #124
divan wrote: post #123

I just want it to be able to read/edit text files. Coding agents can edit code, but for writing we're limited to copy-pasting dance. I use projects for research purposes for articles/scripts/etc, and I would love to use chatgpt in voice mode to talk about the article I'm writing. Like "hey, read last paragraph from the article... let's elaborate on topic X... here what I would love to write - x,y,z - please improve t…

Makes sense. Is there another LLM you're using for this that works better than GPT?

I think all mainstream models are good at this. What is lacking is just a tooling to use projects/voice/llm to work on the simple text documents.

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

#128

Post by jdironman »

multjoy wrote: post #97
kristianp wrote: post #96

Earlier quoted context omitted.

I've found the same thing with Claude Sonnet 4. I suggest something, it says great suggestion and agrees with me. I then ask it about the opposite approach and it says great job raising that and agrees with that too. I have no idea which is more correct in the end.

The LLM has literally no idea which one is better. It cannot think. It does not understand what it is putting on the screen.

This is why multi-pass sessions is something I try sometimes. "What's wrong with the solution your provided, how should it be done instead, and if you use any specific APIs or third party libraries research them to ensure complete accuracy of syntax, usage, and logic simplicity. Refactor your original solution to the correct minimum based on the ask."

Usually after running whatever it first spits out through this I get a bit better of a response or base I can build off of. Really, the best you can do is already know what you want and need and do very targeted sessions. Like the old saying goes, commit small and often.

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

#129

Post by footy »

zyruh wrote: post #117
footy wrote: post #67

I just don't like the user experience of talking to a computer. I would probably have more use for these things if they weren't chatbots.

So, are you preferring a UX that feels more human?

no, I prefer a computer that knows it's a computer and acts like it.
Post reply on HN