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

251–260 of 270 posts

Re: Memory and new controls for ChatGPT

#251

Post by simonw »

oscarb92 wrote: post #246
simonw wrote: post #228

Here's how it works: You are ChatGPT, a large language model trained by OpenAI, based on the GPT-4 architecture. Knowledge cutoff: 2023-04 Current date: 2024-02-13 Image input capabilities: Enabled Personality: v2 # Tools ## bio The `bio` tool allows you to persist information across conversations. Address your message `to=bio` and write whatever information you want to remember. The information will appear in the mo…

Thanks. How do we know none of this is a hallucination?

Prompt leaks like this are never hallucinations in my experience.

LLMs are extremely good at repeating text back out again.

Every time this kind of thing comes up multiple people are able to reproduce the exact same results using many different variants of prompts, which reinforces that this is the real prompt.

Re: Memory and new controls for ChatGPT

#252

Post by simonw »

zaptrem wrote: post #245
simonw wrote: post #228

Here's how it works: You are ChatGPT, a large language model trained by OpenAI, based on the GPT-4 architecture. Knowledge cutoff: 2023-04 Current date: 2024-02-13 Image input capabilities: Enabled Personality: v2 # Tools ## bio The `bio` tool allows you to persist information across conversations. Address your message `to=bio` and write whatever information you want to remember. The information will appear in the mo…

What is personality V2?

I would love to know that!

Re: Memory and new controls for ChatGPT

#253

Post by 15457345234 »

asaddhamani wrote: post #95
Me1000 wrote: post #89

Earlier quoted context omitted.

It has a tendency to do: "// ... the rest of your code goes here" in it's responses, rather than writing it all out.

It's incredibly lazy. I've tried to coax it into returning the full code and it will claim to follow the instructions while regurgitating the same output you complained about. GPT-4 was great, GPT-4 Turbo first version was pretty terrible bordering on unusable, then they came out with the Turbo second version, which almost feels worse to me, though I haven't compared, but if someone comes claiming they fixed an issue…

People need to be using their local machines for this. Because otherwise the result is going to be a cloud service provider having literally everyone's business logic somewhere in their system and that goes wrong real quick.

Re: Memory and new controls for ChatGPT

#254

Post by ShamelessC »

hackerlight wrote: post #235
ShamelessC wrote: post #204

Earlier quoted context omitted.

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 m…

> I use gpt4-turbo through the api many times a day for coding. Why this instead of GPT-4 through the web app? And how do you actually use it for coding, do you copy and paste your question into a python script, which then calls the OpenAI API and spits out the response?

I use it fairly similarly via a discord bot I've written. This lets me share usage w/ some friends (although has some limitations compared to the openai chatGPT app).

Re: Memory and new controls for ChatGPT

#255

Post by gdestus »

I know it's the nature of the industry but it's insane how often I feel like I start a project personally or professionally only to find out it's already being worked on by better, more resource, people.

I started down the path of segmentation and memory management as (loosely) structured within the human brain with some very interesting results: https://github.com/gendestus/neuromorph

Re: Memory and new controls for ChatGPT

#256

Post by jsemrau »

oscarb92 wrote: post #246
simonw wrote: post #228

Here's how it works: You are ChatGPT, a large language model trained by OpenAI, based on the GPT-4 architecture. Knowledge cutoff: 2023-04 Current date: 2024-02-13 Image input capabilities: Enabled Personality: v2 # Tools ## bio The `bio` tool allows you to persist information across conversations. Address your message `to=bio` and write whatever information you want to remember. The information will appear in the mo…

Thanks. How do we know none of this is a hallucination?

Hallucinations are caused by missing context. In this case enough context should be available. But I haven't kicked all its tires yet.

Re: Memory and new controls for ChatGPT

#257

Post by jerpint »

hackerlight wrote: post #236
jerpint wrote: post #135

Earlier quoted context omitted.

Agreed, I do this all the time especially when the model hits a dead end

I often run multiple parallel chats and expose it to slightly different amounts of information. Then average the answers in my head to come up with something more reliable. For coding tasks, I found it helps to feed the GPT-4 answer into another GPT-4 instance and say "review this code step by step, identify any bugs" etc. It can sometimes find its own errors.

I feel like you could probably generalize this method and attempt to get better performance with LLMs

Re: Memory and new controls for ChatGPT

#258

Post by rpmisms »

emporas wrote: post #201
anotherpaulg wrote: post #196

Earlier quoted context omitted.

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 promp…

Just use Grimoire.

Re: Memory and new controls for ChatGPT

#259

Post by xdeshati »

ShamelessC wrote: post #204
anotherpaulg wrote: post #103

Earlier quoted context omitted.

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 m…

I whenever the chatGPT gets lazy with the coding for example //make sure to implement search function .... I feed its own comments and code as prompt :you make sure to implement the search function and so on has been working for me

Re: Memory and new controls for ChatGPT

#260

Post by djmips »

wolpoli wrote: post #218
thelittleone wrote: post #162

Earlier quoted context omitted.

Hamstringing high value tasks (complete code) to give forthcoming premium offerings greater differentiation could be a strategy. But in counter to this, doing so would open the door for competitors.

The question I have been wondering is if they are hamstringing high value tasks to creating room for premium offerings or are they trying to minimize cost per task.

I think it's the latter. Reading between the lines on costs gives me the impression they have strived to lower computational costs. They already added a cap of 30 queries per 3 hours...
Post reply on HN