I tested it with college class level documents. Then did extensive tests (questions, choices) on the material. I took all notes, lectures, images from a law class and crammed them in a large pdf. I mainly used GPT-4 architecture vs GPT4o (plus membership). GPT-4 architecture is similar to GPT-4 Turbo. GPT-4o is for high interaction rates that compromise a bit of precision. GPT-4 architecture rarely hallucinates, while GPT4o seems to have more of these moments.
You also have to understand you’re now talking to a different “brain”, different neural networks. It deducts differently. So getting used to communicating to it (tuning) is also part of the challenge. Both engines seem to interpret my “customized” settings differently as did GPT4 Turbo vs CustomGPTs (plus membership) when fed the same instructions. I do a lot of things with GPT4 architecture, like programming, and law documents. At times more than 40hours a week. It’s very efficient, regardless, everything must be double checked.
In this simple test GPT4o fails, vs GPT4 architecture.
Does GPT Turbo and GPT4o use different neural networks?
GPT4o:
Yes, GPT-4 and GPT-4 Turbo use different neural networks. GPT-4 Turbo is designed to be cheaper and faster than GPT-4, although the exact differences in architecture and operation are proprietary and not disclosed by OpenAI. Both models aim to provide high-quality language generation but with different optimization focuses.
Does GPT Turbo and GPT4o use different neural networks?
GPT4 architecture:
“Yes, GPT Turbo and GPT-4o use different neural networks. GPT Turbo is optimized for speed and lower resource usage, making it more suitable for applications requiring fast responses, while maintaining a high level of language understanding and generation capabilities. GPT-4o (often referred to as GPT-4 Optimal) provides more detailed and nuanced responses, suitable for more complex tasks requiring deeper understanding. Each model is tailored for different use cases based on performance and complexity needs.”