Did ChatGPT 4o get progressively "dumber" for anyone else lately?

I have been using ChatGPT for help with various Python coding help for some projects. Beyond the fact that OpenAI clearly limits the heavy use of it after using it continuously for a few hours, the actual quality of interactions has declined to the point to where the tool is virtually unusable.

I guess my questions are:

  1. Is anyone else experiencing a steep decline in the quality of responses?
  2. ChatGPT 4o for me now behaves like 3.5 insofar as being completely unable to maintain a context, or “remember” what was discussed just 2 minutes ago.
  3. Can anyone from OpenAI perhaps tell me if perhaps there is some “reset” function for an account to wipe out all the contexts and maybe start fresh? I know there is a claim there is no such thing, but I am not imagining this. Either my account is “blacklisted” somehow (if that’s a thing) or something is broken.

Either way, when 4o came out, it was rocking as far as quality of interactions, memory and being able to obey instructions and track changes across multiple project.

All that is gone now. Any advice? I am at the point to where I want to close my account and open another one just to see if it functions the same, except my work account is starting to suck as well.

5 Likes
  1. I have the same problem as you and it seems that GPT 4o is much faster now but more stupid!
  2. true
5 Likes

YESSS PLEASE CHATGPT IS BEHAVING LIKE CHATGPT 3.5 now. It’s as if it’s been dumbed down for some reason. PLEASE FIX IT. I gave it a question a few days ago and it was able to solve it correctly, but now it tells me that it can’t be solved, or it give me no details at all which is used to do originally

3 Likes

Yep! No more subscription!!!

2 Likes

Yeah felt the same. Can’t use 4o for any coding tasks anymore. Does anyone know if there’s a different behaviour when you use it via API than browser?

2 Likes

Yeah I cancelled my work account and switched to Anthropic. I still have a personal account with them but for coding help I would basically labeled 4o as a “scam” almost because it’s literally useless. I would love to know how it’s possible for an extremely high quality product and service like this to decline so rapidly to virtually being unusable in just a couple of months.

2 Likes

Exactly! I’m having the same problem. ChatGPT 4o is so limited and gives no clear answers, even after multiple prompts with different explanations. It’s like it’s not even ChatGPT 3—more like ChatGPT 0! Does anyone have an alternative they’re using? I’d rather pay for something that’s worth the money!

2 Likes

I had to pay for claude to get my coding tasks done, and it is very message rate limited. WTF.

3 Likes

it’s getting dumber everyday!
literally every response contains more than 65% fake, made up part that i didn’t even ask for

3 Likes

Yeah no kidding. I just used it again today for the first time in almost a week and I gave it some python code to analyze and it instantly gave me a long list of useless suggestions which had nothing to do with the code and on top of that were wrong. Whatever happened to it, whether it is being done purposefully to push their users to use the API to increase their revenues, or accidentally (which is probably worse), shows that OpenAI is probably held together by spitballs and toothpicks. It’s a shame because just a month and a half or so ago I was telling friends over lunch about how great of a tool it is.

4 Likes

It was passable (although producing worse output than Claude for example) until a few days ago. Now GPT-4o is completely unusable, ignoring most instructions and being lazy every time. Looks like a pretty sharp decline in quality.

2 Likes

Yesterday and today I noticed some very glaring difference in the ways in which it behaves compared to before and I can successfully replicate those things:

  1. If you give it code to analyze, it will answer immediately providing very long and verbose answers which have virtually nothing to do with the code. It’s obvious that it does not parse the code you provide before answering any questions.

  2. It also now uses strange words like “IF the function normalizes the audio stream” or “the class MIGHT be producing inconsistent results” or “IF the sql table has this row” - which is very weird because i literally just provided the code in question for analysis or the database schema. When asked about why it uses uncertainty in its answers and I ask it to analyze the code given, then it finally analyzes the data I gave. It’s clear that the interactions are seriously diminished and it does not follow instructions.

  3. The worst one is having to ask it the same thing many times until it finally provides the answer you are looking for. Usually it takes 3-5 exchanges and going back and forth after it prints endless pages of useless data on the screen to finally give a somewhat accurate and concise answer. Instructions to not be verbose are totally ignored.

I would be happy to hear from other users experiences and see how you guys suffer too. lol. I am not yet ready to fully give up on it.

2 Likes

Yeah… it just suggests some kind of nonsense. If I already send him my configuration file, it goes over it and tells me ‘ENSURE’ you have set up this and this. OK but I already had this set up. And how am I supposed to work with that? I just have to constantly create new chats, set up custom instructions or use chat gpt 3.5, this version at least doesn’t dump me with hyperinformation.

update: I really think to switch completely to Anthropic, it seems to be better for now at solving some coding tasks.

2 Likes

Oh yes. “Ensure” is another one. lol. Ensure that you are treating this as a tuple instead of a list!

No. I gave you 500 lines of code to look at. You analyze it and ensure that it is.

Every interaction is like that. So much waste of time.

3 Likes

I have an importat update on the topic of ChatGPT getting “dumber” which may be relevant to others.

I have been using 4o more in the past two days or so and the problems are virtually gone. I have not changed the way in which I interact with chatgpt, so it is unclear to me why it is suddenly offering excellent coding advice, maintaining context and following instructions way better than before.

Whatever changes were made, and if OpenAi staff is behind this, thank you for resolving whatever the problem was. I wish there was more transparency regarding the root cause, but I am thankful the service is back to the quality it was before, at least for me.

I hope the rest of you are experiencing improvements as well.

It’s still dumb for me unfortunately. I’m just trying to change the name of a project I’m forking and I’ve pasted in the code for each file and it gives stuff like:

  • Navigate to C:\repo\BoseCineMatePulse.
  • Ensure the solution file is named BoseCineMatePulse.sln.


Ensure the task configuration references the correct solution and project files.

I’ve cancelled my paid plan for now, but it’s still active until the end of the term. Hopefully it gets back to the original model so I can continue to use it.

I wish OpenAI would comment

1 Like

This is infuriating. it was doing its job perfectly of putting spaces between the thai words and then translating them. Now its lost all sense and putting spaces between every letter im also having to tell it it is making mistakes before it corrects its’self. It has the english next to it from the text book for context

100% GPT4o has gotten worse, specifically the past month or so, its now rtarded, like no context, spits out the same crap and over regardless of requests. It’s 100% been downgraded and to claim otherwise is gaslighting. I’ve cancelled my subscription to these snake oils salesmen, and will give me money to anthropic, talking to claude is not like talking to a child with brain damage.

Too late, besides, this happens far too often for this product to be a reliable tool. openai are done now, they’ve burned us too many times and theyre lack of communication is a form of gaslighting…”oh no its not worse, you must be crazy, you’re just used to the magic”

1 Like

I’ve noticed that if I don’t use it for a few days it works better. lol. It’s the dumbest stuff you can imagine but it’s true. The more I use it, the dumber it gets and vice versa.

Only “they” know what’s going on behind the curtain…