I started to use ChatGPT4 since it started to charge 20$ per month, by using it on daily basis, I found it getting much worse in recent, especially from July. It seems not able to read the my draft content in detail and often create content not including the key word, key points, that I like it to be included and even drafted in my reference content. There are few words, ChatGPT really like to use, but I do not like, such as " In light of" , " rest Assured " , even I ask it do not use these words, will not stop it keep using it regardless. Not mention the letter it wrote often seems too long and too much extra words which is not needed. Anyone else has the same problem?
2 Likes
Yes, we all are in the same boat.
Many months ago when ChatGPT was originally like that many discovered that adding be concise to the prompt often helped/worked.
Yep, i call this the alzheimer lazy edition.
Its like
Prompt:
-Write me a joke
Answer:
I’m sorry, the last prompt got cutoff but i can still assist you with a joke:
There was a man (…write the rest of the joke here)
I’m glad i was abl
But hey, now we have 50 prompts, even tho we have to prompt 5 more times than before, yay!
Some people will dismiss our claims as subjective or anecdotal, but there is absolutley no doubt that ChatGPT-4’s outputs have been changing, in my mind for the worse, lately. There’s enough evidence that can’t be dismissed in good faith. Is it some cost cutting measure or something else? No idea, but it’s an undeniable fact something has changed.
It is definitely worse. I was gpt4 pretty consistently for work. However, in recent months it has become so bad to the point where it is unusable for what I needed it to do. I also noticed that the custom prompts that I have been using for a while are significantly less effective. Overall I am super disappointed and have canceled my subscription because it is no longer useful to me.
I can for sure say it has been nerfed. A couple reason why this might happen. The addition of “Custom Instructions” are included in the request (seems after about 40 responses, it forgets this information.) At 60 responses it is just like fighting a toddler for a sucker. Another problem might be that they are adding a bunch of stuff to the request (well server side) for linking data. Here are some notes I have been using to ensure a somewhat decent responses. (These things were no issues on release, so more then likely they are being pressured to reduce the performance of things like coding due to market influence. )
Notes: Day Dreaming Started At : 41 Responses.
At Response 46, I resent the base Custom Instructions (went back to single steps.)
Became completely dumb about response 60.
Yup mine too. It literally doesn’t answer even to the smallest of requests anymore like it used to. I used it a lot for practicing language and at work and it can’t even respond to “Correct the grammar in my last sentence” anymore. It almost always hallucinates and corrects the things it has written instead of the things I have written, and you can’t get it to change or understand what you mean. On the work side I feel like simple requests have suddenly become more difficult, and regardless of how complex and clear I make the prompt, I just get below par material back now. Very sad as I loved to use this in my day to day.
Thought it was only me until i googled and discovered that no…chat gpt it is getting worse every time, now i cannot write jokes with it because “it is a sensitive material”, or cannot answer simple questions and have to write and re-write the prompts until i can find the result desired.
Chat Gpt getting worse and degrading in relatively short time is giving us hope that AI is not going to replace us, it is like benjamin button but becaming from smart to dumb overtime…
yes, it is still getting worse and worse. they used us to train this AI on our money, and now they’ve limited our use with it
Yeah and the worsts part is somehow it is instructed to response in long paragraphs no matter what , that’s way most of the time its just printing garbage
I agree, I use chat gpt to aid me in schoolwork and it used to be amazing for that, almost always got me an 85% or above. Over the past 2 months, however, I’m lucky to get more than a 66%. I’ll give it a question and 4 answer choices and it will go on a borderline unrelated tangent and give me an answer that wasn’t listed, or the wrong answer. It also seems to ignore a lot of the criteria I give it for writing essays. For instance, one of the things that must be talked about ina lot of my essays is the big picture and importance of the subject matter, and I always specifically ask for this, and every time it is ignored
Yeah I don’t know what’s going on but recently it even stopped giving me any answers and basically crashes a few times and says “Hmm…something seems to have gone wrong.” before giving me any answer… I’m starting to think about resigning from GPT 4 since it basically does almost the same as GPT3.5