I will add: the Wordle Revolution (no longer a “fad” since a dedicated minority among us have turned it into a healthy daily habit) belongs here. A nugget of accessible step-by-step thinking to warm up a mindfully step-by-step day. I wrote this about it
Conversation
Step-by-step-ism (needs a better name) is exactly the antidote we need to a bunch of unhealthy things:
- vibing as a bad substitute for sense-making
- derangement syndromes as a chronic state of mental ill-health
- uncritical brute-force trial-and-error that learns nothing
4
4
61
I think we’re about to discover that there are “10x teachers” and that prompting skill is fat-tailed
Prompting and step-by-stepping is basically skilled teaching, whether it’s silicon or living neural nets. Except in the former you can also do some “brain surgery”
3
1
44
Thanks for reminding me of this piece. Yes, Blue Origin “gradatim ferociter” might have a moment again. I forgot I wrote this. Much as I admire SpaceX, long-term I think I trust this philosophy more, whatever the execution troubles.
4
1
31
In general, I guess this is a swing away from both “one-shot” intuitionism where you get from A to B via a stroke of illegible genius AND away from the move-fast-break-things mode of inefficient learning where you get a high learning rate at the cost of high waste and risk
1
2
24
A more “slow is smooth, smooth is fast” approach to mindful learning.
1
2
39
There is also going to be a tendency to deny there us anything new here and an effort to identify this development with a favored old tradition. I’d suggest resisting that temptation.
There’s more than “Socratic method, you invented the Socratic method!” here.
3
16
Oh, the big upside here is that only the *original* discovery of effective prompt patterns is a rare skill. Once discovered, others can easily copy. An ordinary gym teacher should be able to copy that clever backflip teaching method.
1
2
21
There’s a potential for a network effect here, and good prompt patterns driving out weak ones.
And of course, a clever architecture may allow AIs to discover good prompt patterns to. PromptGAN?
1
1
20
“Cueing” is another good aspect with subtly different connotations from prompting
Quote Tweet
Replying to @vgr
How about "cueing". Good yoga guides can elicit the desired behavior with super-spare verbal code.
1
1
19
Also “scaffolding”
Replying to
I have a fair amount of college teaching experience. Enough to know I’m not naturally talented at this. Once I know something, I find it hard to put myself in the shoes (motherboards?) of someone who does not know. But when I’m in a patient mood I can sort of do it okay.
3
13
Some connections from an experienced educator
Quote Tweet
Replying to @vgr
On the off-chance you aren't familiar, I think there are nice connections between this and (a) Perice's notion of "continuity" in learning, (b) Piaget's assimilation/accommodation loop, and (c) a wide variety of perspectives on the power of REPLs (e.g. vimeo.com/223309989)
1
1
15
Stub to think about debugging and decompiling
Quote Tweet
Replying to @aresnick and @vgr
(I also find it interesting that in many cases, you can think of debugging as decompiling a behavior, i.e. something of a dual/inverse of the "step by step" construction.)
2
9
I’m registering an Official Interest™ in this stebystepism trend so tag me if you spot anything interesting that’s related.
It’s also the single most positive development I’ve seen in the zeitgeist in a couple of years. Step-by-step is how you work your way out of shit times.
5
3
31
Threshold concepts
1
2
19
Another example. This helped me clearly understand something I never quite understood when learning it officially. Step-by-step from a counting problem to Riemann hypothesis
Quote Tweet
1
2
11
Oh shit, Asimov called this... this is robopsychology!
2
13
Also, this is the n-step version of google and twitter prompting
1
10
There is something here about growth rates. Stepbystepism is slower initially but accelerates to big momentum if it works. Uncritical trial and error is fast initially but either plateaus or crashes. And just vibing in one-shot ways just finds clever intutions without growing.
1
17
Zooming out to extreme macro, the growth vs. degrowth may be ill-posed. What if step-by-step is the DNA of tortoise like growth that doesn't backslide or crash as much? What if net, the tortoise IS faster than the hare?
4
12
Hmm... now that I think of it, my "sparring partner" approach is a step-by-step alternative to trying to "do" one-shot strategy. Instead of a fully-formed strategy being designed out of 2 days of leadership retreat BS, it emerges gradually, contour by contour
3
7
In any single sparring conversation, you might take 1-2 steps at most, but they add up over time. The strategy "takes shape" at the rate of actual alpha being uncovered in the situation, like a thing gradually revealing its full structure.
1
8
I'm unhappy with the term stepbystepism. I need to know the True Name of this thing.
Possibly asynchronous sequentialism, as an antidote to the growing synchronous parallelism of the last few decades.
12
1
6
Prompt thread of examples
Quote Tweet
What’s a thing you do mindfully “step by step” very often?
Eg: making pour-over coffee
6
4
Oh shot just figured out the True Name of this thing. It’s not step-by-step, it’s loop-by-loop! Or better still, loopchaining.
You don’t move to the next loop until current loop gets to 99.9% and you retest all atomic and subchain loops each time you extend the loopchain.
2
1
12
This is easily NP complete. To add loop n+1, you have to requalify minimum n loops again and max 2^n loops. If you don’t have nonlinear payoffs and/or “loop fusion” where substrings chunk-up somehow, it’s an intractable way to learn.
1
3
Worse. Each loop is an OODA loop, and the chain only works when the orientations are aligned. Which means potentially n^2 or higher misalignment modes. And this is under non-adversarial supervision.
3
1





