engineeringprompts

Misinformation tsunami, mass unemployment, Skynet - when it comes to modern AI, what should we be worried about? Strangely, few people talk about what I consider the biggest concern.

It's not ChatGPT - it's "open source" LLaMA. In this short post, we'll take a quick look at the mind-boggling pace of developments.

One of the most powerful ways to keep ChatGPT from hallucinating is to ask it to look at the problem one step at a time.

Large language models are easily confused if you're not clear about what you want from them. We'll look at a simple way of dealing with this, and briefly explore the challenges of "prompt injections".

The "chain of thought" superpower: breaking a problem down into a series of intermediate steps. And how to save $54,000 along the way.

A short selection of things relevant to large language models that appeared on my radar this week, and that I found interesting.

Three publications in recent weeks show the breakneck pace at which AI advances. Here's a selection of three developments that are very noteworthy.

Large language models will give you better answers if they are clear about what role they should take on in a conversation. This can be incredibly useful, especially in ongoing conversations.

Large language models do more than converse - they can also structure data. Let's take a look at how "few-shot prompting" can help an LLM to deliver precisely what you need.