Specification Gaming
Within the world of software development, the term “specification gaming” refers to a behavior that literally fulfills the requirements of a task without achieving the underlying intended purpose.
In practice, this might mean that a piece of software is told to figure out how to get the high-score in a video game, and decides to utilize a flaw in the game’s code to put its name at the top of the high-score list, rather the figuring out how to get better at the game.
This is a real example, by the way.
Other examples include software agents that have been told to get better at winning in-game races opting to grow very long legs so they can simply fall over and cross the finish line before their competitors, and a robot vacuum cleaner that was instructed avoid bumping into things deciding to thenceforth only move backwards, since there were no collision-detecting bumpers on the back of the device.
There’s also the case of the Tetris-playing bot that was instructed to avoid losing. The bot decided that the optimal way to accomplish this feat was to pause the game and never unpause it: mission accomplished.
The premise of all these examples is that while the goals, as stated, were technically met, the actual, intended outcomes were not.
Yes, pausing your game of Tetris will ensure you never lose, but presumably the true intended outcome of that instruction was for the bot to get better at Tetris, and thus, to lose less frequently over time.
Similarly, the developer who programmed his Roomba to avoid bumping into things was hoping to improve its collision-detection algorithm, but what he got instead was a backward-moving robot vacuum cleaner. The digital race-running software agent’s creators, likewise, probably didn’t want a tall competitor that was only good at falling over: they wanted a fast, nimble, race-running agent.
None of these bits of software cheated or failed, they just took the instructions they were given literally.
We humans are capable of recognizing the difference between implied and literal instructions, typically understanding that there’s a meta-context for the guidelines we’re provided and the tasks we’re assigned: the spirit of the rules, compared to the rules in isolation.
That doesn’t necessarily mean, however, that we’ll act upon those underlying intentions.
When we can get away with it, we’ll sometimes grow tall and fall down rather than learning how to run fast and dodge obstacles because that’s the most energy-efficient way to do precisely what we’ve been told to do.
Seeking these sorts of shortcuts, consciously or unconsciously, is an impulse that many of us will recognize, I think—even when it comes to goals we set ourselves and desperately want to achieve.
A desire to learn something new can lead to a sequence of learning-flavored habits and behaviors that don’t actually help us acquire new knowledge or hone our skills; they merely allow us to feel that we’re in the process of learning.
Perhaps we take a trip to expose ourselves to new things, but focus on the photo-evidence we can collect or the stories we can tell, rather than the potentially perspective-shifting experience that we told ourselves was the point of the journey.
Our relationships, too, can become a sequence of performative motions rather than intentional acts: things that superficially gesture at care and affection, but fail to provide either.
Few of us aim for these sorts of outcomes; they’re often subconscious and reflexive.
In many cases, we fall into a specification gaming-rhythm because we haven’t stopped to ask ourselves why we want what we want, and whether what we’re doing will actually help us achieve those ends.
If you want to travel to accumulate photos of yourself in exotic locales, that’s perfectly legitimate. But if you’re keen to expand your horizons and all you get in exchange for the time and money spent is a bunch of photos, that may be evidence of a miscalibration of intent and outcome: optimizing for a literal goal, rather than the underlying purpose of that goal.
Periodic reassessments of our habits and routines, and figuring out how to optimize for that more fundamental aim, can help us avoid such pitfalls. Though even the most ardent intentionalist will succumb to this sort of empty ritualization some of the time.
It’s prudent, then, to check in with ourselves semi-regularly, to tweak what we can to bring our actions into better alignment with our intentions, and to forgive ourselves for these sorts of subconscious missteps when we discover ourselves making them.
If you enjoyed this essay, consider supporting my work by buying me a coffee.
The observatory at Banff in Alberta, Canada.
Updates
This week on Brain Lenses, I published an essay about the flawed perception that What You See Is All There Is, and a podcast episode about Morning Rituals.
This week’s episode of Let’s Know Things is about space mirrors and Orbital Power.
That episode marked the 4th anniversary of LKT, by the way: I’ve been writing, editing, hosting, producing, and publishing the show every week since May of 2016, if you can believe it, and I feel incredibly fortunate to have an audience of enthusiastic, thoughtful, supportive people on the receiving end of that broadcast.
Thank you very much to everyone who has listened, subscribed, shared, reviewed, and financially supported the show over the years. You’re the reason I’m able to commit (a not inconsiderable amount of) time to the podcast each week, and I’m immensely grateful for that :)
On the app front, your feedback has pointed me in a more refined direction for Curiosity Gadget, and I’ll be working on that this upcoming week.
The response to Authorcise has also been super-valuable (and wonderful), and I’ve been making tweaks to that over the course of the previous week.
If you’re keen to give the new iteration a spin, you can find it at Authorcise.com: it’s intended to serve as a quick, daily writing exercise/sprint (a random-word prompt is provided, if you, like me, find that sort of thing useful), but I’ve had people tell me they’re using it as a sort of mental-adjustment tool throughout the day, as well, to help them pivot from one task/rhythm to another, which I think is really cool.
And as usual, if you have any thoughts/ideas/general feedback, I’d love to hear it! Thanks in advance!
Community
I’m loving what’s happening over on the forum!
To everyone who’s already participating in the discussions over there: thanks for making it such a kind, welcoming, and interesting place.
Stop by and check it out if you’re keen to lurk and/or participate in the discussion: NeverNotCurious.com/forum
This week’s prompt is to share a lesser-known app or other tool you use and enjoy.
Interesting & Useful
Some neat things worth checking out:
The Psychology of Design(list of cognitive biases)
How to Make a Paper Airplane Jet(simple how-to, paper-folding video)
This Word Does Not Exist(new words & definitions generated by AI—glorious)
Virtual Tour of Frank Lloyd Wright Houses(no relation)
Astronaut(a tour of YouTube’s least-viewed videos—fascinating)
How to Make a Telescope(quite the project!)
Chair Times(documentary about chairs & chair design)
St. Louis, Missouri, USA.
Outro
I’ve been occupying part of my time plotting out what I’ll do as soon as it becomes safe to engage in some roadtripping. The tricky part, I’ve found, is determining what “safe” means in this context, and what metrics I should use to measure it.
There’s a lot of intentionally or accidentally incorrect or misleading information out there right now, and it’s a good idea to maintain a sense of skepticism and curiosity as we attempt to educate ourselves in a metaphorically foggy intellectual space.
Assessing the incentives and intentions of those providing us with information is a good place to start, but is not, unto itself, sufficient to avoid or counter all misleading info, unfortunately.
How’re you faring this week? Has anything changed in your outlook, recently? Making any plans for the future? How’re you spending your time, at the moment?
I respond to every email I get, so feel free to send me one if you’re keen to say hello, to tell me something about yourself, or simply have an interesting link to share.
If you’re struggling, you’re not alone and it’s okay and normal to feel that way. Times are tough, the world is weird, and all any of us can do is keep on keeping on to the best of our ability, within the confines of our circumstances. You’re doing great.
Feel free to say howdy via Instagram, Twitter, Facebook, or maybe, you know, via some non-screen-related medium for a while; just for a while.
If you’re finding some value in what I’m doing here, consider supporting my work by becoming a patron of my writing, buying a book, or becoming a supporter of Let’s Know Things or Brain Lenses. You can also buy me a coffee if you’re keen.