To be meta about it, I would argue that thinking "generatively" is a craft in and of itself. You are setting the conditions for work to grow rather than having top-down control over the entire problem space.
Where it gets interesting is being pushed into directions that you wouldn't have considered anyway rather than expediting the work you would have already done.
I can't speak for engineers, but that's how we've been positioning it in our org. It's worth noting that we're finding GenAI less practical in design-land for pushing code or prototyping, but insanely helpful helping with research and discovery work.
We've been experimenting with more esoteric prompts to really challenge the models and ourselves.
Here's a tangible example: Imagine you have an enormous dataset of user-research, both qual and quant, and you have a few ideas of how to synthesize the overall narrative, but are still hitting a wall.
You can use a prompt like this to really get the team thinking:
"What empty spaces or absences are crucial here? Amplify these voids until they become the primary focus, not the surrounding substance. Describe how centering nothingness might transform your understanding of everything else. What does the emptiness tell you?"
or
"Buildings reveal their true nature when sliced open. That perfect line that exposes all layers at once - from foundation to roof, from public to private, from structure to skin.
What stories hide between your floors? Cut through your challenge vertically, ruthlessly. Watch how each layer speaks to the others. Notice the hidden chambers, the unexpected connections, the places where different systems touch.
What would a clean slice through your problem expose?"
LLM's have completely changed our approach to research and, I would argue, reinvigorated an alternate craftsmanship to the ways in which we study our products and learn from our users.
Of course the onus is on us to pick apart the responses for any interesting directions that are contextually relevant to the problem we're attempting to solve, but we are still in control of the work.
Happy to write more about this if folks are interested.
I'd be happy to be wrong, but this sure feels like another instance of a numbers/formulas/algorithm-oriented person wanting a shortcut to visual style. This site is full of these, in many areas of endeavor. As a musician, I particularly notice posts that do this kind of thing with music ("I've Invented a New Musical Notation That Makes Everything Easier!").
I just get sad for the designers who have to battle this stuff every day. No programmer would take "input" on their code from a nurse (say), but designers face "input" on their decisions and their craft at every turn. I've yet to meet a designer who was longing for a web form to input a bunch of numbers to generate some type sizes.
Not sure how you read that into my comment. I'm saying that trained, skilled designers don't need formulas and tools like this to achieve pleasing and functional results.
Maybe, but in this context on this site I think it's safe to assume a lot of people are going to look at this with "ah! another subjective judgment that can be marked Objectively Correct by using an algorithm."
There are plenty of GPT shell integrations, a quick Github search will reveal plenty. Check out this one, it seems rather new and integrates Dall-E as well as the ChatGPT API: https://github.com/0xacx/chatGPT-shell-cli
Yes, and I am fascinated to see what happens in this space as we go.
Terminal based applications have always had the advantage of playing nice with eachother. That's at play here. Produces an easy way to have multiple models interact.
Btw... Now that everyone is monkey typing prompts at got all day, is got going to start emulating a gpt user... autocompleting and auto generating prompt sequences?
I grew up playing Sim City 2k and 3k (never got around to the latest one, but wasn't really interested after reading reviews).
I'd like to see the entire city builder genre challenged by changing the perspective from city planner/god-mayor, to those whom they serve.
Imagine, instead of a birds eye view, you could only build from the perspective of a pedestrian.
Maybe in certain instances you'd have to see a wider swath of land for planning purposes (transit as an example), but it would be interesting to see how the forms of cities created by users change from this new perspective.
I think I'd prefer something more similar to a Factorio setting (e.g. still top-down, but the camera actions/limited to your area as the "pedestrian").
However, I'd also like the insertion of balance against the "god" part too - like eminent domain costing goodwill or stability points. Too unstable or not enough goodwill, and the citizens start acting antagonist against the player on some level (e.g. higher crime/fraud, causing less taxes, protests, people leaving, etc)
Almost like city-state on some level, but less about the political compass and more about city government interacting with the local population.
The problem with these city simulators is that they're relatively simplistic, and it's easy to work out a "formula" that lets you get basically infinite money and do whatever you want (the "city painter" mode). Which can be terribly fun, but it's not so much a game as more of an open-world building toy.
This is the problem with most strategy games too, like EU4. It's all about min-maxing against the stats.
As frustrating as it can be sometimes, I prefer playing with fuzzier logic based on randomness. There's a great breakdown on EU3 vs EU4 that highlights this.
In CS, it'd be like if the economy went up and down randomly, affecting taxes or expenses, or if citizens randomly changed behavior patterns (e.g. started driving more when previously walked or vice versa).
I've been enjoying Workers and Resources because of some of this fuzziness is introduced by construction taking time and resources.
Does anyone here actually use Framer on their team? I feel like every product designer I knew was excited and curious when it came out, filling a gap between engineer and designer, but then it just...fizzled.
Figma continues to be the standard across my org overtaking Sketch a little over a year ago.
I've used Framer Motion, but not Framer. The barrier to having a UX team switch to a new tool is significantly higher than an engineering team choosing an animation library.
> Figma continues to be the standard across my org overtaking Sketch a little over a year ago
Same experience here. I prefer Sketch, but Figma has won out. My only guess for why Figma has won is because they handle prototyping a lot better than Sketch. The performance (and the fact that it's a browser) makes it barely usable for me, but I don't know any team that doesn't use Figma.
Figma also wins on collaboration and extensibility.
I work in a large org (50+ designers) and the ability to collaborate on work, and also engage our internal teams to build very specific plugins and extensions very quickly and easily made this an easy switch from Sketch a little over a year ago.
Figma also just updated their mobile apps - looks like they're taking it much more seriously now. You can view any file on mobile, and I'm sure editing is coming down the line.
If they can make really great mobile apps (including iPad), then it'll be a really hard sell on anything else - especially from a collaboration perspective.
Being a web app that runs anywhere including Windows was a pretty significant difference back when it mattered and Sketch didn’t have web support. Turns out that was more important than being a purist native Mac app
Andres Duany is the architect/city planner giving this presentation. If you're interested in systems design, especially through the lens of city planning and architecture, he's an interesting character to follow.
Also, he and his firm wrote a book called "Suburban Nation: The Rise of Sprawl and the Decline of the American Dream", a good read!
