Conceptual designer helping people make paths @Pathwright. Chaos mapper on the side.
Greenville, SC
Joined October 2008
- Tweets1.9K
- Following340
- Followers818
- Likes2.8K
Pinned Tweet
Bet on people who think the future will be better and that they might make it so.
Don’t expect much from people who think the future will be worse unless others do something about it.
the current state of working with agents feels like trying to cook an ambitious recipe where multiple chef helpers are mixing, adding ingredients, setting timers, etc. to help you cook.
you can either let them do all of it while you oversee and taste test,...
do almost all of it yourself, ...
or go some amount of crazy juggling which steps are yours/theres, done/not-done, right/not-right for the *entire* cook.
pretty cool to be able to get almost any kind of meaningful work done in between sets at the gym, on a walk, in the car....
also:
pretty uncool to be able to get almost any kind of meaningful work done in between sets at the gym, on a walk, in the car.
love the design of Kinto cupware generally, but I got annoyed that pouring hot tea into their teacup makes it unholdable.
superficially, it felt like form over function, until I realized I'm an idiot by wrapping it in a paper towel, sipping it, and (deservingly) scalding my own dang tongue.
in fact, there's an elegant natural design affordance designed into its handleless thin walls:
> too hot to hold = too hot to sip
love it even more now and wonder what other kinds of natural affordances/intrinsicly legible designs there are in classic objects like this that i'm too rushed to spot.
Reading even the most human-like AI prose still feels like listening to someone speak from a script.
It’s difficult to measure AI proficiency, but one clear signal is wether or not someone knows precisely when *NOT* to use it.
Perhaps the most meaningfully designed book cover I’ve come across (look up kintsugi).
Nicely done @stripepress and @stewartbrand
In daily LLM use since 2023, there's a gap I've never managed to bridge:
I've never successfully prompted a model to generate a single sentence for a piece of writing I care about that I'm happy with...
At best, it feels 1) "barely okay" — but never — 2) "just right." The "okay" results often give me a good idea, but...
^ Whatever that mysterious gap between 1—2 is, my intuition is that it has not closed *at all* despite the massive advancements in models over 3 years.
feels like @cursor_ai is beginning to replace @RoamResearch & chatgpt for me, I fear.
I think the next era of the Internet is headed in a different direction than many people think.
Made a map of it and would be curious to hear your thoughts.
Here's the long-read: pathwright.com/mapping-the-n…
(Thanks to @TheJustinHall for the images and interactions!)
The popularity of AI slop results from novelty overwhelming our internal quality standards. It's as true for a tweet as it is for the flashiest AI startups.
Novelty dominates bubble eras, but patient craftsmanship applied in novel ways succeeds in the long run.
My twin, @wmdmark, and I think the Internet is entering a new — yet strangely familiar — 3rd era.
If you'd like a clearer big-picture map of how we see design, learning, & teaching evolving, we'd love for you to join the conversation this Thursday at 12 pm EDT.
