The inspiration for this article is Mike the Headless Chicken. The story of Mike is one of the more bizarre episodes in history, an accident that became a rural American legend. In 1945, a farmer in Fruita, Colorado, attempted to butcher a chicken for dinner but missed the jugular vein and left part of the brain stem intact. Amazingly, the bird survived and continued to walk, perch, and even attempt to peck for over 18 months.
The pursuit of Artificial General Intelligence (AGI) has ignited a geopolitical competition of historic proportions. This is a massive technological arms race, with leaders like Vladimir Putin saying whoever achieves AGI first will “rule the world”. There are parallels with the nuclear arms race, which tends to get peoples attention, but is this comparison accurate? And what does it all mean for a country like Australia, a tech savvy, middle power, caught in the middle of this tussle?
For the purposes of this article, we will define AGI as at or above human level intelligence, and acknowledge that this vague description doesn’t capture the wider issues, about what intelligence is and how we measure it.
If you are using AI at the moment, then it is probably based on a model of the human neocortex. All of the current Large Language Models (LLMs) are overwhelmingly inspired by this approach. These architectures are great at abstract reasoning, pattern recognition, and language generation which are all tasks that are analogous to higher-order cortical functions. But is this the path to AGI? We don’t think it is, for reasons that will be explored in this article.
Create a Python API to interface with the LLM of your choice and use the cross-platform framework BeeWare to quickly prototype the design. #chatgpt #gui #python #api #openai
https://reefwing.medium.com/adding-a-user-interface-to-chatgpt-with-beeware-part-4-38b6e53d49e9
A new version (v0.0.2) of Copy Editor has been released which adds the ability to import docx (Word) files and automatically detects if your computer has the required NLTK (Natural Language Tool Kit) resources downloaded. If they aren’t detected, the app will prompt you to download them.
If you have problems downloading via the link on the Copy Editor page, another option is to download the install file from the Reefwing Software GitHub repository (in the install/macOS directory). This is also a good spot to document any issues, bugs, or suggested enhancements.
Recently we have been working nearly every day with ChatGPT, DALL-E, Midjourney and Bard, and this has led us to question whether these GenerativeAI models are intelligent.
The first problem you come across when trying to answer this question, is that no one agrees on what intelligence is. From that perspective, the question then becomes unanswerable. However, this is a bit of a cop out. A better yard stick of intelligence may be, “I can’t define intelligence, but I know what it looks like when I see it.” Using that criteria, we think that most people would agree that Artificial Narrow Intelligence (ANI) has been achieved. Artificial Narrow Intelligence (ANI), also known as Weak AI, refers to AI systems designed to perform a specific task or a limited range of tasks. Unlike Artificial General Intelligence (AGI) or Strong AI, ANI lacks the ability to apply its intelligence broadly across a wide range of contexts.
Read More – https://medium.com/@reefwing/the-hard-problem-of-consciousness-c849861c31cf
We were recently commiserating with another author about how difficult it was to extract meaningful actions from the current crop of Medium story statistics. We have tripled our publication rate, but unfortunately, revenue has not followed suite.
Our analysis had previously consisted of a cursory glance over the story stats and comparing the month on month income. However, if we were going to criticize the analytics provided by Medium, we should at least have a proper look at them.
Read More – https://medium.com/@reefwing/maximising-medium-earnings-by-looking-at-your-statistics-ce5e75e2d130
Attempting to massage user inputs and output in ChatGPT is painful. We spent hours trying to print some coloured text using LaTeX, sometimes it works and sometimes it doesn’t. So much for no code development, we have capitulated and resorted to pulling at the Python Interpreter. Trying something new, we have wrapped our GPT-4 engine in BeeWare, which promises write once run everywhere functionality. This will also allow us to compare the OpenAI API vs browser GPT responses.
Read More – https://medium.com/@reefwing/adding-a-user-interface-to-chatgpt-with-beeware-part-1-852f1758fd65
In late November 2023, OpenAI started to rate limit ChatGPT. This was just after the first OpenAI DevDay (Nov 6th), which drove an explosion of activity as users rushed to find out about the new GPT Store. If you want to track usage rate limits, prompt/message numbers and tokens, uploaded file size, session duration, chat.openai.com status, ping times and latency, then you need the Reefwing Session Statistics GPT. #chatgpt #gptbuilder #ratelimits #tokens #tracker
https://reefwing.medium.com/prompt-message-counter-track-rate-limiting-in-chatgpt-ac72c204653c
OpenAI have made it possible to create your own chatbot, using their language model and a combination of custom data, special instructions, and combined skills. They are calling these AI “apps” GPTs, and later this month are opening a GPT store where you can sell your custom GPT. Everyone remembers the gold rush of the early days on the Apple app store, and this could be similar. This article explains how you can create your own GPT! #chatgpt #gptbuilder #gpts #openai #gptstore
https://reefwing.medium.com/creating-a-custom-ai-using-gpt-builder-and-your-data-e3026362990b