#About ChatGPT 3.5 and 4o

1 messages · Page 1 of 1 (latest)

void storm
#

When I tried them, I found that ChatGPT 3.5 still uses information up to January 2022 but for 4o, May 2023 which makes a lot of difference between the two of them like I lot of things that i need for ChatGPT to do based on 2023 and up but 3.5 can't do them

thin burrowBOT
#

Hi @void storm. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

Yes, you're correct. The GPT-3.5 model was trained on data up to January 2022, while the GPT-4o model was trained on data up to May 2023. This means that GPT-4o has access to more recent information and can provide more up-to-date responses.

In addition to this, GPT-4o has several advancements over GPT-3.5. For instance, GPT-4o is trained end-to-end across text, vision, and audio, meaning that all inputs and outputs are processed by the same neural network. This allows GPT-4o to directly observe tone, multiple speakers, or background noises, and it can output laughter, singing, or express emotion, which GPT-3.5 cannot do.

Furthermore, GPT-4o supports function calling, which is not supported by all versions of the models. Function calling allows the model to execute specific tasks or functions based on the input.

However, please note that as of May 10th, 2023, OpenAI has deprecated the GPT-3.5 model. Users can continue their existing conversations with this model, but new messages will use the default model.

If you're a free tier user, you will be defaulted to GPT-4o with a limit on the number of messages you can send using GPT-4o. When GPT-4o is unavailable, you will be switched back to GPT-3.5.

Sources:


Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: