Skip to main content
Share Your Experience: Take the 2024 Developer Survey
28 votes

Meaning of roles in the API of GPT-4/ChatGPT (system/user/assistant)

I think below examples will help to understand Chat GPT roles quickly: Role "user" : It means you or who is chatting or who is asking to chat gpt. Example: (API Request) ...
Touhid's user avatar
  • 381
13 votes

How is GPT 4 able to solve math?

Large Language Models actually can do math. It's an "emergent" property, i.e. it appears only at larger scales. Understanding complex English language does require some analytical ability, ...
Harsh's user avatar
  • 1,315
6 votes

How do open source LLMs compare to GPT-4?

The remarkable performance of GPT 4 is due to the massive size of its architecture and the amount of data it was trained on, which costs a lot of money. Few organizations have the hardware resources ...
Brian O'Donnell's user avatar
6 votes

Is GPT-4 based on GPT-3 or was it trained from the scratch?

GPT-4 is largely based on GPT-3. From the GPT-4 Technical Report: GPT-4 is a Transformer-style model [39] The transformer-style model originates from the paper Attention Is All You Need, which lays ...
Minh-Long Luu's user avatar
5 votes

How is GPT 4 able to solve math?

ChatGPT now uses Wolfram Alpha to deal with math as well as other factual information. https://writings.stephenwolfram.com/2023/03/chatgpt-gets-its-wolfram-superpowers/
Jaume Oliver Lafont's user avatar
4 votes

How do open source LLMs compare to GPT-4?

How do open source LLMs compare to GPT-4? https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard has a leaderboard containing both open source LLMs and GPT-4 (and GPT-3.5-turbo): Model ⭐ ...
Franck Dernoncourt's user avatar
4 votes
Accepted

Is GPT-4 based on GPT-3 or was it trained from the scratch?

GPT-4 is a transformer like GPT-3 and any other GPT. The training is certainly new, because it has a different size, you just can not transfer GPT-3 weights into an GPT-4 to continue training. The ...
Volker Siegel's user avatar
3 votes

How is GPT 4 able to solve math?

As far as we know, GPT-4's core capabilities are still based mainly on a Large Language Model (LLM). If so, then the apparent capabilities to reason are a somewhat surprising emergent phenomenom from ...
Neil Slater's user avatar
  • 32.5k
2 votes

What is the difference betwen fine runing and rlhf for llm?

RLHF is just one possibility of fine-tuning for generative LLMs, which is used to align an LLM to human tastes. However, you could just create a bunch of great data, and fine-tune (take a pretrained ...
Alberto's user avatar
  • 2,173
2 votes

How is GPT 4 able to solve math?

OpenAI's CEO explicitly mentioned last month in the GPT-4 announcement video that GPT-4 isn't hooked up to a calculator. One can however install plugins on top of ChatGPT, which may connect it to some ...
Franck Dernoncourt's user avatar
1 vote

How do open source LLMs compare to GPT-4?

In the "Fine-tuning" section of their end-user-documentation, OpenAU writes that The more training examples you have, the better. We recommend having at least a couple hundred examples. In ...
knb's user avatar
  • 165
1 vote

What researched-backed findings is there for prompting LLM’s / GPT-4 to give specific information or actionable plans?

It may not be a complete answer to your question as it is quite broad, but I would offer three approaches for you to have a look at: Fine-tuning via JSON: Ranedeer. Mr. Ranedeer AI Tutor is a ...
Hans-Peter Schrei's user avatar
1 vote

Is the GPT-4 for text the same model that can input and output images?

No chatGPT is a text-model only. If you know that HAL 9000 is mainly a red circle, and you know how to generate a red circle in python, you don't need to visually see the image to provide the code. ...
nammerkage's user avatar
1 vote

Is the GPT-4 for text the same model that can input and output images?

They are not the same model, and the text-only model is definitively able to output graphical content via various forms of code; see e.g. Sparks of Artificial General Intelligence: Early experiments ...
Polytropos's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible