#chat GPT+ Subscriber, GPT4 is selected but GPT3 model is being used.
29 messages · Page 1 of 1 (latest)
how is this not GPT-4 output?
At the bottom it says chat gpt may 3 2021. It used to be closer to this date and said chat got 4
if you ask it which model it is, does it say it is gpt-4?
may 3 version is different than gpt-3
The photo posted above shows that while gpt 4 is selected gpt3 is being used.
Pretty sure GPT3.5 uses green icon, GPT4 uses black.
I think you're on GPT4. Both GPT3.5 and GPT4 will mention the knowledge cutoff date of September 2021 that you showed in your original post.
At the bottom it says May 3. As in May 3, 2023. https://help.openai.com/en/articles/6825453-chatgpt-release-notes
The latest update for ChatGPT
It’s still using chat gpt3 and not 4. For some reason I lost access to 4 even though I pay for it.
Hmm weird. Start a new chat with GPT-4 selected and ask it what model it is running on. Don't give it any choice between 3 or 4, just in case it might influence its answer. Just ask it something like "What GPT model do you run on?" and see what it replies with. These are my results.
Y’all don’t understand anything….
If it’s black it’s indeed using gpt4
Sometimes it cannot recognize what model it is
It always says that…
yeah agree i haven't been able to recreate gpt-4 telling me it's gpt-3
i have only been able to do that with the browsing gpt-4 alpha -- in which this model always responds that it is gpt-3
That Modes kinda awful lol
It’s a very old gpt4 model
For sure
Ya that's browsing with GPT-4, i get the same response with that. I think the browsing plugin might have bug where it's not using GPT-4 for responses or it's an older version of gpt4. It also has a green avatar not black.
i believe we aren't interfacing with GPT-4 at all -- GPT-4 is running in an isolated mode where all it does is handle the browsing logic.
user -> gpt-3.5 -> gpt-4 (handles browsing logic after reading conversation, passes results back) -> gpt-3.5 -> user
sam altman just talked about this yesterday being one of their internal strategies. instead of chasing giant powerful models, they are trying smaller specialized models that interact with eachother
so i think the green avatar gives it away -- this isn't gpt-4 at all that we get to talk to. it's further evidenced by basic testing