Anyone else getting issues with chatgpt 4 repeating itself over and over?

This has started recently, when i ask a question, chatgpt will repeat its last answer before answering me. Has anyone else encountered this issue, am i using it wrong? See below:

User

how can i get into fpga programming?

ChatGPT

Getting started with FPGA (Field-Programmable Gate Array) programming can be an exciting venture into the world of hardware design and digital logic. FPGAs are versatile and powerful devices that can be used in various applications, from simple logic controllers to complex system-on-chip designs. Here are some steps to help you get started:

Understand the Basics

Learn Digital Logic Design: Before diving into FPGA programming, it’s important to understand the basics of digital logic and circuit design. Study topics like logic gates, flip-flops, multiplexers, and finite state machines.

User

are there any cheap fpga boards

ChatGPT

Getting into FPGA (Field-Programmable Gate Array) programming can be an exciting journey, offering the chance to work on cutting-edge hardware projects. Here’s a structured approach to start with FPGA programming and some suggestions for affordable FPGA boards to consider:

Understand the Basics

Learn Digital Logic Design: Before diving into FPGA programming, it’s essential to have a good grasp of digital logic and circuit design. Consider starting with basic logic gates, combinational and sequential logic, and how digital circuits work.

Study Verilog or VHDL: These are the two primary hardware description languages (HDLs) used in FPGA programming. Choose one to start with (Verilog is often considered more straightforward for beginners) and get comfortable writing and understanding HDL code.

  1. Select an FPGA Board

When choosing an FPGA board, consider your budget, the complexity of the projects you aim to work on, and the learning resources available for the specific board or its development environment. Here are a few affordable options:

This happens every time, and my chats have also not been getting saved when this happens and i referesh the page.

2 Likes

Yes, a similar issue was previously reported, with the assistant messages not being saved and the user input being seen as multiple questions to be answered, or similar.

You can abandon that broken chat and try again.

But several recent problems with network etc have been found and are related to browser (default) privacy settings, adblock and tracker blocking extensions, certificate trust, etc.

You can click on the shield icon in Firefox, for example, and see where sites are trying to elevate their privileges beyond what is required, for example. Or what should not be required, but web developers and captcha makers and session recorders and trials want to impose on you.

image

2 Likes

Yes, the same thing has been happening to me since at least 2 or 3 days ago. Very annoying. I have to tell it not to repeat itself.

This has also been happening to me. I think what is happening is the response isn’t saved. But when you type in your next prompt, since it hasn’t saved your last response, it just assumes to add the 2 prompts together. Resulting in it answering the first prompt again into the second one. It is really annoying and I have not found a fix.

1 Like

I tried mentioning this in the custom instructions settings, but no success.

Anyone found some working prompt there?

We also had some cases where new conversations had the same conversation id as the previous one.
Then the two prompts from the two conversations would get ‘fused’ and the model reply resulted in a error message.

While I didn’t have this issue before it may be worthwhile to check the conversation id in the browser and try to force a new id before continuing.

Logging in and out, clearing the cookies and the cache before each conversation etc…

Hope this helps somebody…

Maybe some relation to chat history?
I’m thiinking about delete it all but i still access some info from some of them.

Very annoying, answers get longer each iteration in a chat.
And it seems to ignore now my custom instructions from settings too.

We can just assume OpenAI is aware of every bug, since we don’t have a way to report?

It is also esting through my usage like multiple calls are being made.

I’m using the OpenAI Python API and I also have these problems, so it has nothing to do with network connection or messages not being sent.
Also tried changing the prompt and increasing presence_penalty/frequency_penalty with no luck.
Has anyone found a solution for this that does not involve fine-tuning?

I think I might be running into the same issue.
Whenever I start a new conversation, it works fine the first two or three prompts and answers, but after that nothing works - as soon as I refresh the page, the last answer(s) will be gone and all of the prompts I’ve sent up to that point will be crammed together into my first message.

Also, the GPTs will start repeating their answer from the previous prompt - and then everything vanishes as soon as I refresh the page. This happens on the standard GPT4 model as well as all of the custom ones I’ve tried.

I’ve archived all my other chats, no change. Deleted them, no change. I have tried Firefox, Opera and Safari so far, all without any extensions and in incognito mode. I have tried on my computer and on my phone. Nothing seems to work, it’s completely unusable like this. This happens on BOTH accounts in my workspace.

I seriously don’t know what to do anymore, I’ll probably cancel the subscription at this point.

1 Like