ChatGPT

8974 readers

1 users here now

Unofficial ChatGPT community to discuss anything ChatGPT

founded 2 years ago

MODERATORS

marcar

GPT4 is about 1/10th as useful as it was at release (self.chatgpt)

submitted 7 months ago by Ozone6363 to c/chatgpt

13 comments fedilink hide all child comments

It's so frustrating.

Even very basic things like "Summarize this video transcipt" on GPTs built specifically for that purpose.

Firstly, it cannot even read text files anymore. It straight up "cannot access documents". No idea why, sometimes it will act like it can, but it becomes obvious it's hallucinating or only read part of the document.

So ok, paste info in. GPT will start giving you a detailed summary, and then just skip over like 40 fucking percent of the middle, and resume summarizing at the end.

I mean honestly, I'm hardly asking it to do complex shit.

I have absolutely no idea what lead to this decline, but it's become so bad it is hardly even worth messing with it anymore. Such an absolute shame.

you are viewing a single comment's thread
view the rest of the comments

[–] TropicalDingdong 24 points 7 months ago (1 children)

This is 100% consistent with my experience. Its been clear that they are nerfing it on the back-end to deal with copyrighted material, illegal shit, etc (which I also think is bullshit but I accept is debatable).

Beyond that however, I think they are also down scoping the queries from 4 to 3.5 or other variants of '4'. I think this is a cost savings measure. Its absolutely clear however, that 4 is not what 4 was. The biggest issue I have with this is the issue of "What am I buying with a call to a given OpenAI product?". What exactly am I buying if they are re-arranging the deck chairs under the hood?

I did some tests basically asking GPT4 to do some extremely complicated coding and analytics tasks. Early days it performed excellently. These days its a struggle to get it to do basic asks. The issue is that not that I cant get it to the solution, the issue is that it costs me more time and calls to do so.

I think we're all still holding our breath for the 'upgrade', but I don't think its going to come from OpenAI. I need a product that I'll get consistent performance from that isn't going to change on me.

[–] [email protected] 9 points 7 months ago (2 children)

local AI is the way. it's just that current models aren't gpt4 quality yet and you'd probably need 1 TB of VRAM to run them

[–] hperrin 4 points 7 months ago

Surprisingly, there’s a way to run Llama 3 70b on 4GB of VRAM.

https://huggingface.co/blog/lyogavin/llama3-airllm

[–] [email protected] 1 points 7 months ago

Llama3 70b is pretty good, and you can run that on 2x3090's. Not cheap, but doable.

You could also use something like runpod to test it out cheaply