It seems like the memory from previous parts of the conversation don’t have the same memory limitations anymore. It seems to forget what it was doing after about 4 replies.
I’ve also noticed that relatively easy tasks (when getting gpt-4 in ChatGPT to write code) are presented with a reply telling me that the task I presented it with is “Too complex”.
Last month, I made an extremely complex application with GPT-4 in ChatGPT, but now it can’t even create a login screen for a react site?
What’s happening? It’s clear that you’ve somehow altered it, but I’m afraid you’ve done it for the worst. Even Bard is giving better results and not failing to complete the tasks I give it… and Bard is nothing on what I achieved last month with GPT-4
3 Likes
It seems to have been getting worse over the past week.
I noticed a similar change on 3.5 when 4 was being released.
I got access to the plugins alpha yesterday, today it shows as plugins Beta and a minor UI change.
BUT, the performance of GPT 4 has decreased dramatically. It is a bit dissapointing.
4 Likes
The speed of the response has increased.
It makes alot more errors in the code it produces, and has a hard time fixing it.
3 Likes
This is a huge problem that nobody seems to want to talk about. I frequently get straight-up gobbledygook answers from GPT4 these days after weeks of incredible results. Output that begins mid-sentence or produces fake references/fake data… It’s enough to make me want to quit my subscription until this bull**** gets ironed out. It’s like i’m talking to GPT3.5 or a concussed pre-May12-update GPT4…
1 Like
The May 12 version was a major downgrade from May 3. I thought it couldn’t get any worse, but now I am even more dismayed by the latest “May 24 Version” which appears to actually be a further step in the wrong direction.
@#$!
We should really be coming together to push for the ability to select previous versions (i.e., a toggle switch for using the May 3 version vs current release). I started a thread on this a couple days ago, but no replies.
2 Likes
Yes it has dreamy got worse.and bing. Just bloes
Sorry typos. It has gotten worse. So sad. And bing do t even bother
Please follow through here in this thread as we give example, because this thing really got severely degraded since they released the Beta plugin
major bummer. wish there was some kind of announcement regarding these concerns of many paying customers…
I’m a paying customer for the “plus” and where the hell has that plus gone?
I was used to code daily with GPT4, because gpt3 is just pretty useless for coding interesting things and now after 2-3 prompts it doesn’t even remember the context of the ongoing conversation?!
Like for real, *@ck privacy, and duck the Sam Altman travel to Europe which is probably related to the privacy memory limitation. We are paying for the powerful unrestricted model.
“oh no the alignment scary thing…”
cmon OpenAI, what the heck