this post was submitted on 10 Oct 2023
83 points (92.8% liked)

ChatGPT

577 readers
1 users here now

Welcome to the ChatGPT community! This is a place for discussions, questions, and interactions with ChatGPT and its capabilities.

General discussions about ChatGPT, its usage, tips, and related topics are welcome. However, for technical support, bug reports, or feature requests, please direct them to the appropriate channels.

!chatgpt@lemdro.id

Rules

  1. Stay on topic: All posts should be related to ChatGPT, its usage, and relevant discussions.
  2. No support questions/bug reports: Please refrain from posting individual support questions or bug reports. This community is focused on general discussions rather than providing technical assistance.
  3. Describe examples: When discussing or sharing examples of ChatGPT interactions, please provide proper context and explanations to facilitate meaningful discussions.
  4. No self-promotion: Avoid excessive self-promotion, spamming, or advertising of external products or services.
  5. No inappropriate content: Do not post or request explicit, offensive, or inappropriate content. Keep the discussions respectful and inclusive.
  6. No personal information: Do not share personal information, including real names, contact details, or any sensitive data.
  7. No harmful instructions: Do not provide or request instructions for harmful activities, illegal actions, or unethical behaviour.
  8. No solicitation: Do not solicit or engage in any form of solicitation, including but not limited to commercial, political, or donation requests.
  9. No unauthorized use: Do not use ChatGPT to attempt unauthorized access, hacking, or any illegal activities.
  10. Follow OpenAI usage policy: Adhere to the OpenAI platform usage policy and terms of service.

Thank you for being a part of the ChatGPT community and adhering to these rules!

founded 1 year ago
MODERATORS
ijeff@lemdro.id
83
"The word 'hello' doesn't contain repeated letters" - ChatGPT 3.5 (lemdro.id)
submitted 1 year ago by ElPussyKangaroo@lemdro.id to c/chatgpt@lemdro.id
16 comments fedilink hide all child comments
 

Thank God humans aren't being replaced with these Generative AI models.

Oh wait... THEY ARE!

all 17 comments
sorted by: hot top controversial new old
[–] drekly@lemmy.world 17 points 1 year ago* (last edited 1 year ago) (5 children)

I'm super happy that people share stuff like this to discredit AI and say that it doesn't help with code.

And then I correct it and say "hey yeah there's two Ls in a row" and it apologises for its mistake and gives me perfect code.

Yeah it can't give you perfectly working code 100% of the time for every single thing, first time. What it can do is can get you 75% of the way, and then get to 99% with a short conversation.

[–] Shadow@lemmy.ca 7 points 1 year ago

I haven't met a programmer who can deliver working code 100% of the time either.

[–] tja@sh.itjust.works 5 points 1 year ago (3 children)

Yes, but you have to know if it is wrong.

[–] mayonaise_met@feddit.nl 2 points 1 year ago

It's faster than typing the whole thing.

[–] ijeff@lemdro.id 1 points 1 year ago

You can also try asking it to review the code for errors. I've had some success with this.

[–] hubobes@sh.itjust.works 2 points 1 year ago* (last edited 1 year ago)

The issue I mostly have that it then corrects the error I pointed out but introduces a new one. I then point out the new error and it reintroduces the old one.

But overall still very helpful, so helpful actually that I actually pay for Plus. Web Plugin is awesome for quickly searching trough documentation.

[–] AlboTheGuy@feddit.nl 1 points 1 year ago

Most times it works like that but sometimes it gets stubborn and can't give me a correct answer, try asking the AI for something like: which variables are unused in this code: ...

I knew at least some were unused but chatgpt refused to acknowledge so, until it did but also included a bunch of other variables that were used.

[–] ElPussyKangaroo@lemdro.id 1 points 1 year ago

I wouldn't say I'm discrediting it, given that I use it on a regular basis.

But I have seen companies choose the generative mess from ChatGPT over actually experienced devs or writers, that too the first response. They won't even correct it, because they won't even read it fully.

I know it sounds like a rare occurrence, but boy oh boy do I have news for you.

[–] Aussiemandeus@aussie.zone 9 points 1 year ago

Just let every company that does this, fail.

Like that time we all stood up together to stop self service checkouts at grocery stores.

[–] PsychedSy@sh.itjust.works 6 points 1 year ago (1 children)

I mean there isn't a repetition of a single letter. There's a single instance of a double letter.

[–] ElPussyKangaroo@lemdro.id 2 points 1 year ago

Ah! See, that's what the problem was. Dammit!

[–] ijeff@lemdro.id 5 points 1 year ago (2 children)

What's the prompt? GPT-4 tends to handle these things better. Not perfect, but better!

[–] gerrywastaken@lemmy.world 3 points 1 year ago

Shhhh busy attacking the old version via a single prompt, so we don't have to adapt.

[–] ElPussyKangaroo@lemdro.id 2 points 1 year ago

The original prompt was a description of a use case where my client needed to be able to identify if a cell contains a repeated letter. I can't give you the exact prompt since I don't have access to their instance. This is a screenshot from them.

But I'll ask them to give it a whirl in GPT-4 and report back 🫡.

[–] xilliah@beehaw.org 3 points 1 year ago

Try it with gpt4

[–] flossdaily@lemmy.world 0 points 1 year ago

You would be making a huge mistake to look at this and say "AI isn't there yet. We have nothing to worry about."

In this case here, is just a misunderstand about how GPT-3.5 sees words and to what degree it can examine is own output. The user here has found a double blindspot, where GPT-3.5 appears to be weakest, because we assume that it "sees" the interface as we do and thinks in the same way we do.

A couple things to keep in mind: you can easily plug gpt into additional functions, which will give it whatever language-parsing abilities you need. Secondly, you can simply ask GPT to review it's answers, and you'll get a 85% improvement on just the first pass.

Moreover, gpt4 is a completely different animal. Much smarter right out of the box.

Lastly, it's really important to remember to think about a large language models like gpt3 and gpt4 as if they were the language centers of the brain... Not the complete brain.

They are capable of extremely advanced reasoning and creativity. And with just a little bit of know how even an amateur programmer can plug these things into additional tools which turn them into essential, AGIs... Like Jarvis from iron Man, or HAL from 2001.