AI Software: The System Heavyweights

They each work more or less the same and deliver somewhat similar results. So which one is best? That question takes you down a rabbit hole. It’s a bit like asking which seaside town offers the best beach vacation, or which SUV is best for families. There is a huge amount of nuance in the issues and a vast amount of pride and prejudice filtering the responses.

So too with this seemingly simple but still enormously complex software. I’ve heard people argue that Claude has more conversational skills with language, or that ChatGPT is better with software code. Microsoft Copilot, though mostly a variation of ChatGPT, integrates well with the Microsoft software suite. Google Gemini can plug into Gmail, Google Maps and YouTube. Some of the differences are meaningful; many are slight. And they’re constantly changing with each new software release.

There are two top tiers of AI software. The first is what could be called the foundational software, software like ChatGPT and its competitors (aka Chat AI). That’s how most people experience AI today.

The next tier is all of the other software that provides what is essentially a window into the foundational software. Newcomers to AI chat will mostly not have encountered this software, though it is not rare or obscure. Some are familiar with Jasper (marketing software) or Perplexity (search). This software would simply not exist without ChatGPT and its brethren.

Keep in mind that mainstream software from Adobe, Microsoft, Grammarly, Zoom, at al., now incorporates AI tools, but this is different from software that’s built from the ground up based on LLM interfaces. (Others like Otter (for transcriptions) predate ChatGPT but are now imbued with large language model technology.)

Below we’ll look at publishing-specific software that capitalizes on generative AI’s abilities.

Way back when software was code and only engineers understood how it worked. What made personal computers succeed, beyond their relatively low cost, was software that was (relatively) easy to use. We don’t give much thought to all of this; it just surrounds us.

But consider, for a moment, Microsoft Word, a program that I can safely assume is used by 99% of the readers of this book. It takes about 10 minutes to show someone how to write a paragraph of text in Word. Then you can show them how to create bold text, and italics, and how to change the base font, perhaps from Calibri to Arial or Times Roman. Then, how to save the file and print the file. How to search and replace.

And then you leave them on their own.

Years later you find out that they’re still formatting their Word paragraphs with spaces and tabs. And still forgetting to save their files, or getting mixed up about which version they saved, sometimes having to recreate text from scratch. But they “know how to use Word.”

Word has hundreds of features, but a third of the time users employ only 5 commands: Paste, Save, Copy, Undo and Bold. It takes several weeks of training to properly learn Word’s advanced features; features that could help a publisher save many hundreds of hours of time. But most never do. I’ve been using Word since 1985, nearly forty years, and I’ve never taken a course. I don’t even know what I don’t know about how to extract the full power from the software.

I go on about this because it’s a helpful way to get your head around why AI software is so very different from any software you’ve ever worked with. It doesn’t come with a manual, not even a Quick Start guide. It comes with a blank screen and a question: “What can I help you with.”

There’s no menu bar, no button to push, no keyboard shortcuts. You ask a question, start a chat, and you get some answers. Let’s see what Claude thinks about this.

Claude’s response:

“There are several key differences between working with modern conversational AI like myself compared to traditional tools like Microsoft Word or Excel:

“1. Natural language interaction: With conversational AI, you can communicate your intent using everyday language rather than having to learn and navigate complex menus and functions. You simply explain what you want to accomplish conversationally.

“2. Contextual understanding: AI assistants maintain context and understand the flow of the conversation, allowing for more natural back-and-forth dialog. Traditional software has no contextual awareness from one command to the next.

“3. Adaptability: AI can dynamically adapt and respond to a wide variety of requests, while traditional tools are limited to a predefined set of functions. An AI assistant can help with writing, analysis, math, coding, ideation, and more within a single interface.”

That was useful, but I wanted something easier to grasp. So I ask:

Claude:

“Here’s a simple way to explain the difference to someone without a technical background:

“Think of traditional software like Microsoft Word or Excel as a tool, like a hammer or a calculator. It has a fixed set of functions that it can perform, and you need to learn how to use it properly to get the result you want.

“On the other hand, think of modern conversational AI as a smart assistant, like a knowledgeable colleague or friend. You can just talk to it using plain English, and it understands what you’re trying to do. It can help you with all sorts of tasks, from writing to math to coming up with ideas.

“You don’t need to learn any special commands or techniques—just chat with it naturally. It adapts to your needs and remembers the context of your conversation. Over time, it gets to know you and your preferences.

“So while traditional software is like a static tool that you use, conversational AI is more like an intelligent partner that you interact with naturally to get things done. It’s a more flexible, personalized and efficient way of working.”

Hmm. Not quite what I wanted. So I continued the conversation:

Claude:

“Sure, let me try again without using technical terms:

“Imagine you’re talking to a friend who is really knowledgeable and eager to help you out. You can just talk to them in plain English about what you’re trying to do, whether it’s writing an essay, solving a math problem, or brainstorming ideas for a project.

“Instead of having to learn and remember a bunch of specific steps or commands, you can just explain what you need in your own words. Your friend understands the context and adapts their help based on what you’ve already discussed.

“It’s a back-and-forth conversation, where you can ask questions, clarify things, and get advice. And the more you talk to this friend, the better they understand your unique needs and communication style.

“Now, imagine if you could have that same type of helpful, easy interaction, but with a computer program. That’s the basic idea behind new types of software you might be hearing about.

“Instead of the old style of software, where you have a rigid set of functions and have to learn the right way to use it, this new software is more like a knowledgeable friend. You can just talk to it conversationally and it figures out how to help you based on the natural flow of your discussion.

“So it’s a smarter, more personalized, and easier way to get help with all sorts of tasks on your computer, just by talking to it like you would a person. That’s the key difference from the older, more rigid style of software.”

Summary: I was trying to do two things with these examples. One was to offer a dead simple instance of why chatbot software is so different from any software we’ve ever used. And the other was to illustrate how a chat can evolve. It’s not just a single question and a single answer. It’s a conversation. That’s a big part of the breakthrough.

Chat AIs are ‘school-trained’, but inexperienced interns. You can’t assume that they know what you mean. You need to explain what you want, why you want it, and how they can be most helpful. (I’ll talk more about the related subject—prompting—below.)

The first, AI foundational platforms, like ChatGPT, are core AI technology. The second, let’s call them AI add-ons; software that’s been freshly built on top of the core platforms. You won’t have heard of many of these, tools like Jasper or Rewind.

My third category is software featuring AI tools perhaps crudely bolted onto their existing product. For example the Microsoft suite of software features new AI tools in Word, Excel and PowerPoint. Adobe has added AI technology to Photoshop and Acrobat. Grammarly is being rebuilt around the new generation of LLM-based technology. It’s mostly the same product, but with AI added.

It’s becoming clear that nearly all of the software you use today will soon enough incorporate AI features. You’ll have to make your own assessment of whether those tools are genuinely useful or just AI window-dressing.

I’m more interested in the new tools, built from the ground up, to provide the value that only AI can engender. That’s the next generation of software.