OpenAI’s GPT-4: What You Need to Know
OpenAI’s latest language model, GPT-4, has been making waves since its release. This large language model (LLM) is said to be ten times more advanced than its predecessor, GPT-3.5. While GPT-3.5 was the first mass public version, GPT-4 is only accessible through OpenAI’s subscription service, ChatGPT Plus, for $20 a month.
If you’re looking for accurate answers to your questions, ChatGPT Plus is a much better option than the free version. However, it’s important to note that GPT-4 can still make blunders, which are known as “hallucinations”. Despite this, GPT-4 is an excellent tool for getting smart answers to challenging questions. Here’s what you need to know about the technical differences between GPT-3.5 and GPT-4.
OpenAI describes GPT-4 as “10 times more advanced than its predecessor, GPT-3.5”. This is due to several key differences between the two models. Firstly, GPT-4 has been trained with around 100 trillion parameters, which is an order of magnitude greater than GPT-3. Secondly, GPT-4 is a multimodal model that can process both text and image data. This means it can accept an image as part of a prompt and provide an appropriate textual response.
Thirdly, GPT-4 has a much longer memory than previous versions. While GPT-3.5’s short-term memory is around 8,000 words, GPT-4’s short-term memory extends to around 64,000 words. Additionally, GPT-4 can pull text from web pages when you share a URL in the prompt. Fourthly, GPT-4 has improved multilingual capabilities and can work with 25 languages other than English, including French, German, and Spanish.
Fifthly, GPT-4 has more “steerability”, meaning that it provides more control over its responses using a “personality” you pick. For example, you can instruct it to give you answers as if it were a pirate. Finally, while ChatGPT-4’s LLM is still limited to training data up to September 2021, you can instruct it to also search the internet with Bing. This capability helps you get more timely answers.
With plugins, OpenAI and third-party developers can work with external application programming interfaces to make ChatGPT-4 “smarter”. For example, with the Expedia and Kayak travel plugins, you can ask for the best flights to Vancouver. Or with the Ask Your PDF ChatGPT Plugin, OpenAI will seek your answers from any PDF document you point it to.
The net result of these improvements is that GPT-4 is “smarter” than its predecessor. For example, GPT-4 has achieved higher scores on exams, including the LSAT, SAT, Uniform Bar Exam, and GRE. OpenAI claims that GPT-4’s answers are “40% more likely to produce factual responses than GPT-3.5”. However, it’s important to note that GPT-4 is still far from being truly smart.
For example, on the AP English Language and Composition test, GPT-4 still only scores a 2. While GPT-4 can talk a good game, it and other AI engines are just very advanced, auto-complete, fill-in-the-blank machines. Their answers come from the words that are most likely, statistically speaking, to pop out of their LLMs.
Despite its limitations, OpenAI claims that GPT-4 is 82% less likely to respond to prompts that are technically not allowed and 60% less likely to fabricate facts. So is GPT-4 better? Is ChatGPT Plus worth the money? The answer to both of these questions is yes. However, it’s important to keep in mind that it’s a useful aid for work, not a worker replacement.
In conclusion, GPT-4 is a significant improvement over its predecessor, GPT-3.5. With its increased parameters, multimodal capabilities, longer memory, improved multilingual abilities, and plugins, GPT-4 is a valuable tool for getting smart answers to challenging questions. While it’s not truly smart, it’s still an excellent aid for work.