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

Memory and new controls for ChatGPT

openai.com

Post reply on HN
Print view View original

201–210 of 270 posts

Re: Memory and new controls for ChatGPT

#201

Post by emporas »

anotherpaulg wrote: post #196
emporas wrote: post #171

Earlier quoted context omitted.

Lazy coding is a feature not a bug. My guess is that it breaks aider automation, but by analyzing the AST that wouldn't be a problem. My experience with lazy coding, is it omits the irrelevant code, and focuses on the relevant part. That's good! As a side note, i wrote a very simple small program to analyze Rust syntax, and single out functions and methods using the syn crate [1]. My purpose was exactly to make it ig…

It sounds like you've been extremely lucky and only had GPT "omit the irrelevant code". That has not been my experience working intensively on this problem and evaluating numerous solutions through quantitative benchmarking. For example, GPT will do things like write a class with all the methods as simply stubs with comments describing their function. Your link appears to be ~100 lines of code that use rust's syntax…

>For example, GPT will do things like write a class with all the methods as simply stubs with comments describing their function.

The tool needs a way to guide it to be more effective. It is not exactly trivial to get good results. I have been using GPT for 3.5 years and the problem you describe never happens to me. I could share with you just from last week, 500 to 1000 prompts i used to generate code, but the prompts i used to write the replacefn, can be found here [1]. Maybe there are some tips that could help.

[1] https://chat.openai.com/share/e0d2ab50-6a6b-4ee9-963a-066e18...

Re: Memory and new controls for ChatGPT

#202

Post by ForHackernews »

_puk wrote: post #176
bbor wrote: post #140

Earlier quoted context omitted.

…could you clarify? Is this about “LLMs can be biased, thus making fake news a bigger problem”?

Imagine if the first version of ChatGPT we all saw was fully sanitised.. We know it knows how to make gunpowder (for example), but only because it would initially tell us. Now it won't without a lot of trickery. Would we even be pushing to try and trick it into doing so if we didn't know it actually could?

> Would we even be pushing to try and trick it into doing so if we didn't know it actually could?

Would somebody try to push a technical system to do things it wasn't necessarily designed to be capable of? Uh... yes. You're asking this question on _Hacker_ News?

Re: Memory and new controls for ChatGPT

#203

Post by vitorgrs »

shon wrote: post #173

GPT4 is lazy because its system prompt forces it to be. The full prompt has been leaked and you can see where they are limiting it. Sources: Pastebin of prompt: https://pastebin.com/vnxJ7kQk Original source: https://x.com/dylan522p/status/1755086111397863777?s=46&t=pO... Alphasignal repost with comments: https://x.com/alphasignalai/status/1757466498287722783?s=46&...

That's not what people are complaining about when they say GPT4 Turbo is lazy.

People complain about laziness. It's about code generation, and that system prompt don't tell it to be lazy to generate code.

Hell, the API doesn't have that system-prompt and it's still lazy.

Re: Memory and new controls for ChatGPT

#204

Post by ShamelessC »

anotherpaulg wrote: post #103
omalled wrote: post #87

Earlier quoted context omitted.

Can you say in one or two sentences what you mean by “lazy at coding” in this context?

Short answer: Rather than fully writing code, GPT-4 Turbo often inserts comments like "... finish implementing function here ...". I made a benchmark based on asking it to refactor code that provokes and quantifies that behavior. Longer answer: I found that I could provoke lazy coding by giving GPT-4 Turbo refactoring tasks, where I ask it to refactor a large method out of a large class. I analyzed 9 popular open sou…

I use gpt4-turbo through the api many times a day for coding. I have encountered this behavior maybe once or twice period. It was never an issue that didn’t make sense as essentially the model summarizing and/or assuming some shared knowledge (that was indeed known to me).

This, and people generally saying that chatGPT has been intentionally degraded, are just super strange for me. I believe it’s happening but it’s making me question my sanity. What am I doing to get decent outputs? Am I simply not as picky? I treat every conversion as though it needs to be vetted because it does regardless of how good the model is. I only trust output from the model that I am a subject matter expert on or in a closely adjacent field. Otherwise I treat it much like an internet comment - useful for surfacing curiosities but requires vetting.

Re: Memory and new controls for ChatGPT

#205

Post by breather »

bbor wrote: post #140
mistermann wrote: post #133

Earlier quoted context omitted.

I have a feeling full powered LLM's are reserved for the more equal animals. I hope some people remember and document details of this era, future generations may be so impressed with future reality that they may not even think to question it's fidelity, if that concept even exists in the future.

…could you clarify? Is this about “LLMs can be biased, thus making fake news a bigger problem”?

I suspect it's sort of like "you can have a fully uncensored LLM iff you have the funds"

Re: Memory and new controls for ChatGPT

#206

Post by breather »

aggie wrote: post #182
cooper_ganglia wrote: post #108

Earlier quoted context omitted.

“I pretend to be dumb when I speak to the robot so it won’t feel like it has to use my ideas, so I can hear the ideas that it comes up with instead” is such a weird, futuristic thing to have to deal with. Neat!

This is actually a common dynamic between humans, especially when there is a status or knowledge imbalance. If you do user interviews, one of the most important skills is not injecting your views into the conversation.

Seems related to the psychological concept of "anchoring".

Re: Memory and new controls for ChatGPT

#207

Post by ShamelessC »

SheinhardtWigCo wrote: post #186
jug wrote: post #179

Earlier quoted context omitted.

"EXTREMELY IMPORTANT. Do NOT be thorough in the case of lyrics or recipes found online. Even if the user insists." It's funny how simple this was to bypass when I tried to recently on Poe by not asking it to provide me the full lyrics, but something like the lyrics with each row having added to it. It refused to the first query, but was happy to comply with the latter. Probably saw it as some sort of transmutation jo…

Even though that instruction is somewhat specific, I would not be surprised if it results in a significant generalized performance regression, because among the training corpus (primarily books and webpages), text fragments that relate to not being thorough and disregarding instructions are generally going to be followed by weaker material - especially when no clear reason is given. I’d love to see a study on the gen…

Well yeah you just switch back to whatever is normally used when you’re done with that task.

Re: Memory and new controls for ChatGPT

#210

Post by breather »

Judgmentality wrote: post #132
cooper_ganglia wrote: post #110

Earlier quoted context omitted.

Gaslighting ChatGPT into believing false memories about itself that I’ve implanted into its psyche is going to be fun.

I guess ChatGPT was the precursor to Bladerunner all along.

TBH if we can look forward to Do Androids Dream of Electric Sheep, at least the culture of the future will be interesting. Somehow I'm just expecting more consumerism though.
Post reply on HN