∗ This is part one of a two part series, please also take a look part two, the Cobus Quadrant of NLU Design.

The service is however only available for applicants from the U.S. and U.K. with a rollout to more regions and languages being imminent. — Google has made a number of announcements recently with focus on Generative Apps. With products like Google Vertex AI, Google Generative AI App Builder and the concept of Gen Apps. As seen in the image below, users can ask Bard to generate a new response on a question…

Like so many others, I received access to OpenAI GPT-4 during the past week. Here is what to expect… —

How can prompt engineering be used to stop LLM hallucination and what defines a good LLM prompt? How are OpenAI’s modes changing this? — Prompts and prompt engineering are integral to successful Large Language Model (LLM) implementations. The beauty of LLMs are the variations in response, creating a sense of liveness…. However, these variations can become too big and turn into false and inaccurate data. This phenomenon is often referred to as hallucination.

OpenAI has introduced the concept of modes to their playground and development interface. Each mode has a dedicated LLM assigned to it. — An area of prioritisation for OpenAI is the concept of modes… OpenAI is gradually introducing structure into their LLM environment. This introduction of structure is taking place in two areas…Prompt Engineering. I wrote extensively about this aspect, please read more about it here.

ChatGPT will be advanced by Whisper due to the disfluency of speech, the creation of more data for ChatGPT to access & the notion of LLMs moving towards Multi-Modal Foundation Models. —

How did we go from LLMs, to Foundation Models and now Multi-Modal Models, with GPT-4 being described as a Multi-Modal Model? — Let’s first address the parameter size of GPT-4, there is incredible hype around the subject; I have addressed it in detail in a prior article. You will see there is a clear progression of parameter size which serves as a good indicator in terms of sheer parameter size. Secondly, Large…

There has been an emergence of a new software genre for building conversational interfaces/applications based on Large Language Models. This collection of applications are often referred to as prompt chaining applications. —

If you don’t, you are jeopardising any production implementations you might have. The moderation endpoint is free to use for monitoring inputs and outputs of OpenAI API calls; this excludes third-party traffic. — If OpenAI find that a product or usage does not adhere to their policies: OpenAI may ask API users to make necessary changes. Repeated or serious violations can lead to further action from OpenAI and even termination of your account.