GPT-3 vs other AI powered assistants

I been kicking the tires with Open AI’s #GPT-3. Based on the screenshot below, it might be easy to think “oh boy does the model think highly of itself”, but as with most things in life – devil is in the details.😃 The screenshot below was a forked version of davinci engine and follows the Q&A structure.

OpenAI's GPT3 answering questions when compared to other AI powered assistants.
GPT-3 vs other AI assistants

Using OpenAI’s API is quite simple; perhaps too simple! It is quite easy to unleash the beast as the code snippet shown below. If you are new to using GPT3, I would highly recommend you start with the use case model guidelines first.

In the context of a toy example, to get to a simple Q&A chatbot as the screenshot earlier shown is quite simple. The API is powerful, and simple to use, and getting started is easy as the code below shows.

import os
 import openai
 openai.api_key = os.getenv("OPENAI_API_KEY")
 response = openai.Completion.create(
   engine="davinci",
   prompt="I am a highly intelligent question answering bot. If you ask me a question that is rooted in truth, I will give you the answer. If you ask me a question that is nonsense, trickery, or has no clear answer, I will respond with \"Unknown\".\n\nQ: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: Unknown\n\",
   temperature=0,
   max_tokens=100,
   top_p=1,
   frequency_penalty=0.0,
   presence_penalty=0.0,
   stop=["\n"]
 )

There are three core concepts when using GPT-3: Prompt, Completion, and Tokens.

To start using the API, we need to start giving it some prompts – this provide some context to the engine on what is expecting. Without the surface area is too broad and we get into nonsensical situations. This is part of the task-specific fine-tuning required.

Think of when giving examples as part of the prompt, we are essentially “programming” the model and providing guidance and providing some hints to context and pattern matching. Note the training data cut off in late 2019, so the model in production today doesn’t have access to data and events post that (e.g., Covid).

Completion is the output that GPT3 generates based on the prompt. To be clear, this is not the full text but is the predicted completions; think of it as “autocomplete” in Word, or Outlook or a search engine. The API has flexibility to return more than one predicted completion along with the probabilities of alternative tokens at each position (to me it seems just like the wave function when thinking of Quantum mechanics 🐼).

Finally, think of Token are the smaller Lego blocks that combine to make words. The API, which is nothing but wrappers around GPT-3 breaks up the text into tokens before processing it. The GPT-3 model understands the statistical relationships between these tokens and uses this to produce the next token in a sequence of tokens.

For example, if we are curious about Tokens, we can see in the screenshot below how the API “tokenizes” this paragraph and get the details of the tokens. This paragraph contains 207 characters and 43 tokens.

Token text that GPT-3 API converts to before using.
GPT-3 Tokens – Text
Token ID's that GPT-3 API converts to before using
GPT-3 Token – IDs

At a high level, think of one token == ~4 characters of text, which is ¾ of a word; so, 100 tokens ~= 75 words.

This is just dipping our toes in the beast that is GPT-3; the API’s which wrap up and expose the engines (more on that in another post) make it simple to use and without getting too much in the weeds of 175 billion parameters. 🙂

Redis on Windows 8 and VS 2012 RC?

I am trying to see if I can get Redis working on Windows 8 using Visual Studio 2012 RC bits – I have not had much success, but then I have not had much time to invest to try this out.

I am wanting to give a demo tomorrow and would be good to see if I can get this working. Curious to know if anyone else has got this?

If not Redis, then have you got some other implementation working on Windows 8? I was thinking of RavenDB.

Hadoop in Azure

My dear friend Mario has finally got around to blogging and one of his latest posts shows, it is possible to run Hadoop (which if you are not familiar with, can be thought of as an open source version of Google’s MapReduce) in Azure. You need to setup a typical configuration of nodes (Name Nodes, Tracker and Slaves).

Sure, there are a number of dependencies some you would expect, others not (e.g. Cygwin – cringe!; but hopefully that will go away with Hadoop 0.22). I wonder what overheard the Cygwin runtime has?

It would be interesting to know if someone is (or planning) to use this at work.

BizTalk 2010

I was wondering what new features of BizTalk 2010 do you like the most? Also are they any must have tools now? I am interested in the following:

  • Automated deployment (of interfaces)
  • Automated testing (regression and functional where possible)
  • Automated configuration management (across various environments – development, various testing, pre-prod and of course prod).
  • Coordination with AppFabric?
%d bloggers like this: