I am so tired of this saying.
It's not true, in general. Systems almost universally have unintended consequences and result in side effects their designers did not foresee.
Designing benchmarks resistant to adversarial attempts to exploit the benchmark software is just something no one was thinking about when they created SWE-bench.
You are misunderstanding the saying. It is entirely about unintended consequences and viewing the system for what it actually does and not any stated intentions of the designers.
That's not "true" in any demonstrable sense, but it can be a useful form of analysis. As it is with "purpose of a system"
Also worth remembering that most systems POSIWID is said about, and in fact ~all important systems affecting people, are not designed in the first place. Market forces, social, political, even organizational dynamics, are not designed top-down, they're emergent, and bottom-up wishes and intentions do not necessarily carry over to the system at large.
I think it's also trying to be too cute. The first two definitions of purpose on Wiktionary[A]:
1. The end for which something is done, is made or exists.
2. Function, role.
People (uselessly) talking about the purpose of a system are often referring to #1, while POSWID is using it to mean #2. The real point of POSWID is that only definition #2 matters. POSWID is a terrible phrase not because it is wrong, but because is is an equivocation -- I suspect that Beer intended it as a pun, but the difference between the two is if one gets the joke. POSWID gets used incorrectly because people don't get the joke.
The exact definition of "purpose" doesn't matter much here.
The particular version of the heuristic used here is that the stated purpose and the actual purpose often differ. POSIWID being the observation that the actual purpose is reflected by the outcomes of the system, because if that isn't the case the system gets changed.
Thus, the observation about AI benchmarks. AI companies have had years now to stop using unreliable benchmarks as advertising material. There's been years of piece after piece about the problems with these benchmarks. And yet the AI marketing continues as is.
I fundamentally disagree with this, and it seems to differ from how other proponents of POSIWID in this thread view POSIWID.
It also seems trivially false; systems are dynamic what was the purpose of the system just before it was changed because people didn't like the outcomes?
IMHO the saying is meant to make you reflect.
1. We must ignore the intentions of the designers (your claim), and instead see what the outcomes are
2. Therefore we should ignore Beer's intentions when designing the phrase POSWID, and instead see how it is used.
3. The overwhelming majority of people using it on the internet (including the GP comment) is to imply that the people perpetuating the system actually desire the outcome.
So the purpose of POSWID is clearly to imply intent.
The intent of those creating or perpetuating a system.
If a gun is developed with the intention of hunting only bears and someone uses it to shoot people, you don’t have to constantly preface things by talking about how it’s supposed to be used only on bears. Sometimes that fact, depending on the context of the conversation, is simply not relevant.
To cover my bases here: yes it often is relevant and maybe even critical info, but it often isn’t either of those things.
That seems like a major oversight. "AI does whatever maximizes reward/minimizes loss, not what you actually want" is one of the biggest challenges in ML in the last two decades (relevant here because researchers selecting architectures and training regimens that maximize public benchmarks are just a bigger training loop with those benchmarks as reward function). And the analogous issue post-training in AGI-like systems is well studied as the alignment problem, the core issue of classical AI safety
If cheating the benchmark is easier than passing it, you expect the cheating strategy to emerge and win. (Just like you would with humans btw)
You’d think that for you to become “so sick of” a saying, you might actually at some point read up on what it means.