A flurry of AI releases now: GPT-4 and new educational projects

The generative AI world continues to develop at a very fast pace. I’m buried in project work right now, but wanted to quickly note some developments.

The big announcement today was OpenAI’s launch of GPT-4, the next version of its large learning model. 4 draws on a larger training set and can also write responses to user-uploaded images.

Note how OpenAI uses higher education tests to demonstrate the software’s improvement, version by version:

Currently it’s only available to ChatGPT+ customers. I became one for this purpose, and asked the bot a question: “How are you different from ChatGPT’s previous version?”

The reply:

As an AI language model, I am a constantly evolving and improving entity based on the advancements in natural language processing and machine learning. Although I’m presented as ChatGPT, I am based on the GPT-4 architecture, which is an advanced version of the previous GPT-3 model. While specific differences may not be mentioned explicitly, the improvements between the versions typically include:

Larger training dataset: As newer versions are developed, they usually benefit from an increased amount of data used in the training process. This enables me to have a broader understanding of various…