Dream cycles

Humans process information absorbed during the day in a good night’s sleep. Important things get put in long-term memory, details that are less important go to the “forget bin”. Stress and noise gets reduced. When we get up, we feel refreshed and ready to get going again.

Memory is a big issue in AI at the moment. A few months ago, it was about remembering your last 3 prompts (sentences). Today, these “context windows” can span novels, to the point where this memory actually starts to confuse the model. A technical solution: dream cycles where the AI model peruses its information, selectively forgets details, and stores important data for future reference.

When it comes to presentation design, it is important to give your thoughts rest as well. Coming back to a story line after a few days makes your realize what actually is the best way to communicate the message.

And a fresh pair of AI eyes can help as well. Clear the context of your model, or open an entirely different one, upload your draft and ask whether this is actually the best way to tell your story…

ChatGPT Images 2 beats Nano Banana

Another day, another model improvement. The latest visual model by OpenAI is now the gold standard for creating realistic image, beating Google’s Nano Banana (August 2025).

I prompted a “911 in Hoogeveen” back in an earlier post to Nano Banana (left), and the ChatGPT result today to the right. Nano Banana figured out Hoogeveen was a town in the Netherlands, and created a historical Dutch town as the backdrop, ChatGPT got the actual details of the town (which I recognize very well), but created its own mashup version of the city.

Text rendering is now great. Look at the traffic sign: correct spelling and places relevant to the town. The model is actually incredibly good at making slide in consistent on-brand format. Below the result of a request to transform a slide in a 1960s Swiss graphic design style. The catch: you get pixels not a file you can edit…

It achieves these results not by just being a better pixel generation model. The response to a prompt now involves reasoning about it, sketching a few raw options, ‘seeing’ (an LLM cannot see) the intermediary results, picking the best one, then producing the final result in pixels.

ChatGPT Images 2 is now the default model in ChatGPT, it will be used when you ask it to create an image. Set the model effort to ‘thinking’ to add more reasoning effort in the processing.

To be continued.

Codex Computer Use - control any app on your machine

Another day, another presentation AI tool. Codex Computer Use is a plugin for OpenAI’s Codex desktop app. It enables control of any app on your machine using the regular human interface: ‘seeing’ screen and making clicks. (Mac only, and not available in the EU/UK because of regulatory restrictions).

Its powers are phenomenal. SlideMagic is a quirky app with a small user base. In a few minutes I got it to insert a profit and loss table, add a year to it, and then take the last year of the table and turn that into a horizontal waterfall chart.

In PowerPoint for example, this tool will be much more useful than the Claude PowerPoint plugin, which “fights” complex PPTX file formats (a huge amount of nexted XML tags) to make simple edits like moving a box. The Codex Computer Use plugin can simple drag the box.

This feature is extremely token-hungry though, probably because of the screenshot data that gets send back to the server.

Claude Design is here, what does it mean for presentations?

I was waiting for this announcement, and Anthropic did announce a few hours ago: Claude Design. There are many demo and review videos online that show the features, I will focus on a few specific issues.

The big issue for enterprises when it comes to presentations and documents is to keep all employees “on brand”. The designer of the corporate web site gets it right, but what about the new analyst who works late at night to prepare the quarterly revenue update presentation? Claude Design does a great job here to capture fonts, colors, and style guidelines in one place.

For enterprise AI workflows and systems, context is everything. And the Claude set up makes it easy to access files, information, data, anything.

The current Claude Design application is a web app, that has not been integrated in the desktop all yet (it will probably happen soon). For presentations, its a wrapper around Claude’s ability to manipulate and create slides. At the moment, Claude Design treats presentation slides as HTML. (Unlike Claude Code/Cowork that can work directly with PPTX). As you interact with Claude Design your presentation comes out beautifully, but will have a “web site” look and feel. (Maybe that is actually a better feel than corporate PowerPoint?). Your presentation is HTML with a 16:9 aspect ratio without the resizing options.

When you are done, you can export to many formats, of which PPTX is one. Once exported, Claude Design can no longer edit the resulting PPTX file. (Obviously you can ask Claude Code/Cowork to take over from there, but that app will miss the context that you created before).

The underlying design engine of Claude does not seem to have changed. Running a few tests, I still see the same things it is really good at, and the ones it really struggles with.

We are getting close to where AI can handle design of presentations. What has not been solved (yet), is the workflow of tweaking/updating/modifying decks among multiple people, where enterprises have the culture baked in of making edits to a shared document in a 1990s file format that gets emailed around between junior staff, senior managers, and everyone in between.

But that could change as well. The way people write code has more or less changed overnight sometime mid January 2026, maybe the same will happen to presentation creation sometime this year.

None of the tools were right, so I quickly wrote one...

This is 2026… I needed a super basic text editor for Google Drive. If you double click a text file in Google Drive, it will convert it to a bloated Google Doc for you. You can install text editor apps, but they all come with a catch: too many features, 1990s UI design, ads, paid plans. So i used Codex to write me one… Writing the app took 10 minutes, configuring the Google Cloud Console a few hours (but now I know the drill).

I have requested Google to approve it to get rid of warnings when you install it. The primary user is me anyway, so I won’t put it out in the add-on market place.

You can try it: drivedraft.slidemagic.com. Sign in with your Google Account. Now go to Google Drive and right-click a .txt or .md file and choose ‘Open With’ DriveDraft.

PowerPoint via Whatsapp

I have been experimenting with OpenClaw, a 24/7 personal AI assistant. It is an open source project that was created over the past month, created almost by accident as a hobby project by a developer. Late last year, developers discovered that using an AI coding tool for non-coding applications really works, especially if you can give it access to local files (rather than chatting). Next step: keep the AI agent running 24/7. Next step, find a way to let the AI agent keep some context about you. (Context memory is a big issue in AI, it fills up at some time, so storing bits of context for future reference enables persistent awareness). Next step, implement recurring instructions. Next, make the AI assistant available from any channel, including Whatsapp. This, combined with full system access, creates an incredibly powerful AI assistant (that can also be incredibly destructive). “It’s 2AM, I have a 12 hour to do list and full shell access, lovin’ it”. What can possibly go wrong.

So it requires some technical knowledge to run this thing in a vaguely responsible way. I put it on AWS EC2 in a completely isolated virtual network, with an access tunnel that only I control, plus a number of prompt injection filters running on yet another server. (OpenClaw’s founder has joined OpenAI exactly for that reason, to get the financial resources to fix the complexity and security issues)

Working with it, enables me to get a feel for the future. Direct instructions to applications (code editors, presentation design software, spreadsheets, food takout apps) will become increasingly irrelevant.

We will move from well-designed, beautiful, easy to understand, visual user interfaces that humans can interact with directly to clear and transparent API endpoints that an agent can call on behalf of a human.

Interesting times.

AI images are the new stock images

People are starting to develop a pretty good sense of whether an image “smells like AI”. The audience will notice when you use them just as visual fillers like you used to use stock images. (“Life-style conscious gen-z person working from the local cafe”).

Completely obvious AI renderings are comparable to clip art of the earlly 2000s. Hyper realistic AI images are similar to stock images, “something is off here”.

Apply the same approach to AI images as you did to stock images.

"Files are so back"

The past decade with spend a lot of energy moving all our files into the cloud, and accessing them through a browser-based application. That is going to reverse in the era of AI.

A good old desktop folder is the perfect context for an AI agent. All information in one place. Different formats, different applications, all accessible and editable.

I started experimenting with a spreadsheet/presentation workflow that mirrors the way I write code. Pointing Claude Code at a directory with files and let it orchestrate analysis and design under my supervision.

PowerPoint -> rendering engine

Programming languages have always been a necessary evil. A way to translate human intent into something a machine can execute. Strict syntax, rigid rules, brackets in the right place.

Presentation software has had the same problem. You want to communicate an idea, but first you need to learn how to manipulate shapes, align text boxes, format charts, pick colors, fiddle with layouts. The tool sits between you and your intent.

AI is changing this. You can now describe what you want in plain language, the way you would have briefed a graphic designer ten years ago. "Put the revenue chart on the left, key takeaway on the right, keep it clean." The difference is that the result comes back in seconds, not days.

And here is the interesting bit: it does not really matter which application your AI assistant uses under the hood to build the slides. The end product is a flattened file, a PDF, an image. The mechanical production of the slides is becoming invisible.

PowerPoint is not going away, but its role is shifting. It is moving from being a user interface for a human designer to being a rendering engine for an AI. The way a browser renders HTML that no one writes by hand anymore.

We are going back to a more natural way of working. Talking to a person (or an AI) about what you want to say, and getting a visual result. The detour through complex software UI was a historical accident, not the destination

The "wait for AI" workflow

As AI gets more and more capable and I use it for more and more things in my daily workflow, it creates a new problem: waiting for AI. Most tasks now take 1-3 minutes for which you have to wait for the result. Most takes would have taken you much much more than that if you were to do them yourself, so a big productivity gain, but, 1-3 minutes is too short to go and do something else, so you wait, get distracted, break your flow, and find yourself getting back to what you were working on 30 minutes later. “Ah small mistake, let’s do fix that. Click. 1-3 minutes wait.

I have not found a solution yet, and am experimenting:

• Running lots of agents in parallel, so it is like a plate-on-stick catching game

• Running the tasks in parallel of an activity that is easy to interrupt (watching a tutorial video)

• Writing a quick blog post…

• Etc.

A new world

Claude plug-in for PowerPoint

This has gone under the radar screen for me. The Claude plugin for PowerPoint is available for Claude Max, Team, and Enterprise users. It links to your existing Claude account (to burn tokens) and does exactly what you expect it to do. More information here.

On the "danger" of AI

Recently, people start getting really concerned about autonomous AI doing its thing with your passwords and credit cards. But I think that not that much has changed since the first emergence of computers. Computers trade billions in stocks and currencies, run nuclear powerpoint plants.

The difference, these systems are carefully monitored and are predictable and well-understood. It is not about the intelligence of the software, it is about the level of control you give it. People wanting “to push the boundaries” and see how far AI can go seem to be putting a 10 year with Microsoft Flight Simulator experience at the controls of a real 747.

I have started to use AI tools heavily in my day-to-day work. Not for email and calendar management, but for coding and document production. All seems reasonably under control, things being sandboxed on my own machine. “Reasonably” What is not, is the chaotic user interface when it comes to giving permissions to things on your file system. Many of these questions will not be understood by the IT layman.

Everyone is raving about Anthropic’s Cowork tool to automate knowledge work. Many incumbent database/information providers and consultancy firm’s stock prices get hammered. The real revolution for Anthropic might be an acquisition that did not get a lot of press. In December, they acquired Bun, a software development platform. My sense is that Anthropic is developing a trusted platform that can build and run code safely on your computer without the constant flow of questions whether it is OK to install package x, y, and z. I think AI models will become a commodity, the real winner in the next generation of computing will be the player that offers this trusted platform that can keep AI in check.

Let’s read this post in 2036 again and see what happened :-)

Pondering SlideMagic 5.0

I had a backlog of feature improvement for SlideMagic in the back of my mind for a long time (SlideMagic 4.0). Started working on it, but never pushed them to a final end product. I am actually glad I didn’t. The path I was going down on was a “hand-held” guidance of AI combined with a dramatically improved graphical user interface. The development of AI models have made this approach obsolete.

i am starting now to tweak and customize the recently released knowledge workflow productivity tools so they work for me. Strangely enough, my decision to build SlideMagic 2.0 as a desktop app with local file access, will come in handy now to build a tool that wraps the raw engine and makes the underlying engine accessible to the average user.

Let’s see where this goes.

Cliche alert: the AI "watershed moment" in presentations....

In my ‘spare time’ I have been working on newer versions of SlideMagic to include more AI. The tricky bit is that LLMs are designed to manipulate words, rather than working with 2 dimensional layouts. So my approach was some sort of step-by-step guided process, where I take the LLM by the hand and instruct it to create pretty decent slides.

A promising approach, but it would still require a lot of development work. The lines of code, would have to be replaced by lines of prompts….

I am just now playing around with the latest AI tools from Anthropic (Claude). They are designed to help you write software. But I decided to throw SlideMagic files at it. And the result is in credible. With a few instructions, you get working .magic files that perfectly capture your intent.

I suspect the average SlideMagic user is not yet ready to edit .magic files in a command prompt environment though. So there is work for me to do, but I can drop my work from the last few months and start using a completely new paradigm….

AI Mental Drift

AI is very poor at navigating context history. “Go back to the previous version”, “change this”, “replace that”, will almost always lead to confused, diluted responses. You need to “freeze” progress in your work. You got to a good version. Asked for an improvement but did not get it: open a new chat windows and start fresh without the last message exchange.

I am sure it is a matter of months before this issue gets resolved in most AI applications.

When not to use AI...

Triggered by a post by Nate Jones on Substack (might be paywalled).

I am working on a next big update for SlideMagic, where I am trying to push AI-supported slide generation to the next level. Especially when it comes to layouts with data and text in them, AI is not there yet. The more I start experimenting, the more I realize that AI should not be used everywhere: hallucinations, unpredictable (non-repeatable) outcomes, long wait times, LLM model changes that can completely trip up the tool you have written on top of it.

Nate identifies 4 use cases:

1. Traditional data processing (adding up last month’s sales by product)

2. Traditional machine learning (predicting machine failure base on historical data)

3. Generative AI (summarizing stuff using a chatbot)

4. AI agents (planning your holiday by optimizing and matching lots of constraints)

Work in progress.

More Nano Banana

I worked with Google’s Nano Banana a bit more over the past days, and I think I understands what it is doing under the hood.

“Regular” imaging LLMs predict pixels, you give a prompt, the prompt gets translated into a series of tokens, and the model predicts the best matching pixels given the token input. A flat “soup of pixels” is the result. And because of that, it is hard to make small adjustments to an image, editing one particular aspect and leaving everything else as is.

I suspect Nano Banana works with layers. The model tries to understand what aspect of it refers to the bottom of the pile (the background) and what elements go on top. As a result, it is possible to make very precise edits to individual objects in the overall composition of the image.

In order to make a coherent image, the model needs to have a good understanding of the 3D perspective of the background, and all the objects above it. Like the example about the Porsche in a Dutch town in my previous post, the car gets rotated, and pasted back into the background image with the correct vanishing point in mind.

Vanishing point is preserved when making edits to the image

What the model cannot do is change camera position. view the entire image from a completely different angle. Zooming in and zooming out works. An example is the cover image of this post, where I took an image from the band of my son (Project71) and put them on a big stage. I could not get the model to produce a view from the audience given the image it already produced. (Starting from scratch with an explicit prompt for an audience view would have worked of course).

Note the small glitch in the keyboard of the synth

This is a limitation I can work with for the moment though.

PS. I work with Nano Banana via Google AI Studio, not via its own web site

Nano Banana

I just played around with Google’s “Nano Banana” AI image generator, and it is incredibly good and useful for presentation design.

Current AI image generators take a prompt and predict pixels. Ask for a modification, and a whole new bunch of pixels get generated, redoing the entire image. Nano Banana (we need a better/shorter name), seems to work with layers and objects, and keeps things consistent.

Below 2 quick examples:

“White Porsche in Hoogeveen”

“Turn it around”

Some observations:

• Super fast, the first image was an almost instant response

• Hyper realistic image, does not look cartoonish

• Correct text: the name of the cafe, the license plate, the branding of the car

• (That town looks Dutch, but it is not Hoogeveen)

• But most importantly: isolated editing, changing one thing and leave everything else the same

Photoshop, it was nice meeting you…

I will study the API structure of Nano Banana and see whether I can swap out the image generator in SlideMagic.

Impressive! You can try it out in Google AI Studio

SlideAudit - Academic research to improve slide layouts

I am following academic efforts to use LLMs to improve / automate slide design with great interest. Each takes a slightly different approach. SlideAudit was recently published by Zhuohao Jerry Zhang and others.

SlideAudit teach LLMs what good design is by teaching it rules and principles. A lot of effort goes into building a bank of slides, identifying design flaws for training, synthetically introducing slides, letting the model run and evaluate the results.

I think this approach can work well for publications that resemble print: designs with lots of text in smaller fonts, and images / graphics that are placed in some sort of grid. Books, magazines, newspapers, but also web sites.

Presentation slides are trickier. It is harder to describe what makes a slide a good slide. You know when it when you see a good one (or a bad one), but pinpointing and automating the steps to go from bad to good is tricky.

Visual coincidence

Photographer Ray Giubilo snapped this image at the current US Open Tennis tournament. Searching for “Jasmine Paolini” might come up with this result for the next few years….

View this post on Instagram

A post shared by RAY GIUBILO (@raygiubilo)