Fast. Easy. Beautiful.
I am doing a number of service updates to the plumbing of SlideMagic to keep things secure. You might be logged out in the process. If things are not behaving normally, please log out and back into your account. Sorry about this.
I have not been posting for a while here. As you know, I am based in Tel Aviv, and the attacks of October 7 made it impossible for me to continue and write a frequent “happy blog post” as if nothing happened.
This blog is about presentation not politics, so I won’t start a discussion here that repeats what has already been said everywhere. When reading and listening to all these opinions, keep this in mind: everything changed on October 7. Whatever you thought on October 6, needs to be reevaluated and reconsidered. Old narratives don’t work anymore. Whatever side your on.
I am continuing to work incredibly hard on my other startup in the medical field, where I try to tame “chatty” generative AI bots to provide disciplined and structured information which is not obvious at the moment. The results are actually very promising.
My blog was always about spontaneous ideas that came up during my work in presentations that go online without much though or planning. I spend a little less time in the world of presentations at the moment, but will try to start posting again slowly. I also owe users a few bug fixes in SlideMagic.
ChatGPT is good at writing fluent text because there is lots of quality text around on the Internet to train it on. Most text online is at least grammatically correct, and a subset of online content is of some decent quality at a story level (books, reports, professional news websites, etc.) . Midjourney can make up great images because there are lots of images around to train it on, they do not even have to be that good in terms of composition, the pixels in an image add up to an accurate representation of something.
Now with presentations though…. There are fewer of them around online, and most of these are actually not that good. Even if you were to feed let’s say McKinsey’s entire archive of decks into an AI model, would it be able to produce a McKinsey-style deck based on a prompt? Maybe. But the result would be a consulting-style, dense document, not an engaging pitch deck.
In 2023 the power of ChatGPT is not in automating extremely complicated tasks, but taking out the daily hassle of smaller things. For presentations, one of my favorites are translating long-hand text into tables of short points. “Please summarize the pros and cons of both options discussed in the following text”. What you get back ia a bird’s eye view of all the elements of the story. Often, the first thing an old-fashioned presentation designer does on a piece of paper.
Below is an interesting chart from McKinsey. It combines a column chart with a line chart. The chart only works when a column has a reasonable size though.
I am not aware of any presentation software that can produce these (including SlideMagic), so this might have been bespoke illustration work.
Link of the original post.
Recently, I started writing code to analyse data from all kinds of financial and healthcare data APIs. The amount of information is endless. Most data sources have some sort of dashboard that allows you to slice and dice data in any way or form you want.
Still, the skill to make sense of this all is pretty much the same as it was 30 years ago.
I remember building a lot of company valuation models where I would sit on the buy side of an M&A transaction. As a buyer, I had to rely on outside information and focus on the data that matters. Often, I found that my model was more accurate than the one of the analyst on the sell side, who lost herself in the abundance of data available.
My workflow in the new abundance of data:
Use some sort of dashboard to explore what types of data is available
Use a spreadsheet as a napkin to scribble analyses
Code the analysis on a small scale
Scale up the analysis to a full scale
The crucial step is number 2.
Here is one use for a slide deck: keep a meeting organized.
Yesterday I saw someone preparing a meeting with the following ingredients:
Zoom, i.e., hard to manage
Content that can spark heated debates
Lots of participants…
…and participants who would like to say a lot
A simple slide deck that might not be essential to get the messages across but organized the preparation and will organize the meeting was the solution. All points are covered (once) and will be discussed in an agreed order
While working on my 9xchange site, I used one of my approaches to present a document. “Pages” that sit randomly on a table or surface (see below).
I use this technique as well for the banner image of this blog, see below.
This effect is very easy to make. Take an empty slide / page in any presentation app. Save the document you want to show as individual images (good old screenshots will do as well). Drag the images on to the slide and tilt them. Add a little drop shadow behind them.
Things are not as random as they seem though:
The angles of the pages need to look interesting, not all the same, not too different
The page need to be semi-readable (i.e., not upside down)
Key headings should be visible and very readable
You need to decide whether to let pages bleed off the page, keep them 100% in the frame. It will create very different effects
You should select pages that look varied, and interesting and are presentative of the content of the document you want to show.
Here is a headline from last night’s GOP candidate debate: Christie accusing Ramaswamy of “sounding like ChatGPT”
We might hear this more often in the future when it comes to debates and presentations. Things that make you sound like ChatGPT:
Highly structured stories: intro, your supporting points, the wrap up
Very polite language
Zero human emotion, humor, anger, cynicism, fatigue
No spontaneous tangents
Arcs of a few paragraphs each
You get the point. It is similar to “sounding like a marketing content writer”, a style that has been around a bit longer.
When your headline says that your product is not another [FILL IN PRODUCT CATEGORY], the audience will believe that it actually is one…
By René Magritte(1898-1967) - Image taken from a University of Alabama site,”Approaches to Modernism”;: [1], Fair use (Old-50)
I love retro advertising. In this Mercedes car ad from 1982, body work painting is ranked by its level of “conspicuousness”. White is the most in your face. Signal red somewhere in the middle. And blue midnight blue is even more hidden than black.
The source of the car ad is here. Subscribe to this facebook group for more vintage car ads.
Professional photographs of your team can give a great lift to your presentation or web site. Either individual headshots all in a consistent style, or even better, a group photo of your entire team in one place.
A good photographer will do two things: firstly, make sure that the technicalities such as focus and lighting are perfect, and secondly, try and create interesting crops and compositions.
Having a photographer set your image crop in stone might not always be good though. What looks great in a 4:3 view finder of a camera, can look suboptimal on web sites that need to handle unusual screen sizes, all the way from big widescreen TVs to small smartphones.
The problem usually is that the center composition will stay constant (the subject area of your team that will probably occupy a 4:3 rectangle or square in the middle of your image), but the background can have vastly different aspect ratios.
The solution: have your photographer take a snap which the crop she prefers, but always add a second one completely zoomed out as a backup.
If you forgot to make that second image, you might have to revert to AI tools such as Adobe Firefly to add the missing pieces of background back in.
Firefly is Adobe’s stab at generative AI. I had a quick look at it an and am pretty impressed.
Most current AI image generators make either very cute artificial / fantasy / cartoon style photos, or allow you to create crazy / unreal compositions. For example: creating compositions you would not normally see (an elephant riding a bike), or mixing styles (the US president soloing on a guitar in the style of Van Gogh).
Adobe Firefly is more useful. You can extend backgrounds on existing images, or position objects in pictures. Below are some of my efforts to add a purple cow to an Alpine background.
Here is a basic background. You can now add an object in it. This is the first result after prompting “purple cow”
The placing of the cow is very good, the purple cow itself is totally unrealistic, probably because “purple cow” in itself is not a concept that is very common. You can select alternative versions of the cow that are more realistic (and less purple):
It’s pretty good (although not perfect). Here is the layer that the app generated on top of the background image (I disabled the background layer)
The best feature of the app might actually be the extension of backgrounds. See the example below, the area to the right was added automatically.
Firefly is part of a beta version of Photoshop (it will soon appear in other Adobe apps as well), and as a result requires a bit of Photoshop skill to use it (which will be a drawback from many). You can also access its features via the web interface. Results are pretty good (you can see that Adobe is very good at separating the foreground and background of the image), but the style is still slightly cartoonish.
Why is the quality of Firefly better than other image generators such as DALL-E or Midjourney? Adobe trained its model purely on high quality stock images rather than relatively random internet content.
You can see where this all is going. The quality of images will increase as people get better in feeding quality data in models. Not only stock images, but maybe you can actually analyse entire movies that give you the context of a visual, plus the same image with objects positioned differently. And that I think is the second area for improvement, describing a required composition (background, position of objects, lighting, camera view, etc.).
Check out Adobe Firefly here, including instructions for installation on your computer and/or access the web interface
There are a number of ways you can, or cannot, use titles in your slide. See the examples below. (RSS subscribers might have to open the post on the web to see images).
The classic way is a basic description of what the chart is showing.
The management consulting approach is the message title: write out in a sentence what the chart is supposed to say, and put the description and unit of the data in a subtitle
You can spice things up with an image
And with full image slides, the traditional title does not actually really matter anymore. You can place text anywhere on the image to get your point across. If you are presenting live, you can even omit the exact description of what you are showing
Back in the 1990s, compact disks would show a so called SPARS code. A series of 3 letters that could either be “D” for digital, or “A” for analogue. “DDD” indicates digital recording, digital mixing, and digital mastering.
My late mother in law had a huge classical music CD collection and I would browse it to find a CD to play, when given a choice “DDD” would be my preference since it was clearly a recording of the highest quality.
My mother in law would answer that this was actually totally irrelevant. What matters is the conductor and/or solo artist that delivered the performance. A poor quality AAA recording from the 1950s might have been the best rendering of a particular piece of music ever.
There is an interesting parallel here with presentations: the actual performance and the supporting slides.
Image By Attosaur - Own work, CC BY-SA 4.0, source.
… of slides.
It takes time and effort to create a good presentation. So when a next meeting comes up, it is tempting to borrow from a previous presentation that was already created. And typical presentations that are readily available are:
Investor presentations of the last fund raising round
Board presentations
Product / sales presentations
We recently needed to pitch a tailored, one-off, joint service offering with a strategic partner. The first draft of our presentation:
About company A (lots of slides, with an investor presentation flavor)
The market need for what company A does
The generic solution of company A to solve this market need
The team of company A
About company B (lots of slides with a product presentation flavor)
The technology of company B
The results and achievements of company B
What company A and B can do for you (1 - 2 slides)
Basically 2 generic company introductions, with a few minutes left to talk about the joint solution we were pitching to the client. We changed things around to focus almost everything about the specific problem of the client, and the company introductions were reduced to appendix background reading.
Be careful when using free images of people from Unsplash. Some of these have be come really popular. Marlene R. on a web site that rents ski and mountain bike gear, has the exact same head shot as Vignette F., one of the demo users of 9xchange.
You can find the image here: photo by Edward Cisneros on Unsplash. It shows up on page 1 of a search for “woman portrait”
…when you prompt it to generate your presentation, maybe you are on to something new! AI generators predict what to write based on information it ingested before.
Now what if your AI generator comes up with a brilliantly written pitch?
A feature that was long overdue: today we added a color picker to the SlideMagic settings page. Better late than never. Click on the big bar to reveal the pop up. If you want, you can still enter RGB codes. With the eye dropper, you can now sample colors anywhere on your desktop. Make sure to have V3.1.7 installed to use this feature.
(Proud of my daughter Mia who insisted to put this in, and actually wrote the code to do so herself)
I added 2 additional AI generators to SlideMagic, the produce a slide with some text and an image based on your prompt. One generator pulls the image from Unsplash, the other creates it from scratch. There is no update to your SlideMagic app needed to see the extra image generators.
See an example below:
