Rendered at 16:19:01 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
_puk 7 hours ago [-]
The obvious fork is "can frontier models stack a dishwasher to my wife's exacting standards".
I can't. So that would surely be proof of AGI.
mrweasel 7 hours ago [-]
"In every partnership, there is a person who stacks the dishwasher like a Scandinavian architect and a person who stacks the dishwasher like a raccoon on meth." - Someone online.
At home I'm the architect, my wife's the raccoon. I don't actually believe that you can stack the dishwasher wrong as such, but you can make it hard for yourself to unload, if you don't sort the items correctly.
dekhn 4 hours ago [-]
In my dishwasher (some bosch almost identical to the model in the simulation), if you put plastic storage containers upside down on the bottom rack, the force of the jets flip them over and they fill up and don't get clean. They also end up using more water (I think?) because there is water trapped in the dishwasher at the end of the cycle, and things don't dry. Also, if you put large things in particular places they prevent the jet arms from rotating.
Dishwasher physics matter. But I would never criticize a person in my family for loading the dishwasher the "wrong" way; I just sneak in and reorganize when nobody's looking.
wffurr 4 hours ago [-]
>> just sneak in and reorganize when nobody's looking.
This is the way. I am just happy when someone else, anyone else, actually puts dishes in the dishwasher.
fxwin 7 hours ago [-]
> I don't actually believe that you can stack the dishwasher wrong as such
There are definitely more and less correct ways, but personally i think it's "wrong" to load it in a way that leaves the arms blocked or (not) tilt pieces that get excessive water pooling on top
viceconsole 2 hours ago [-]
My favorite wrong way is when someone completely covers a small item (ramekin, espresso cup) with a larger item (bowl, food storage container).
mlukewizard 1 hours ago [-]
I would totally do this, is this wrong? It still gets sprayed from the bottom no?
vforgione 3 hours ago [-]
> but you can make it hard for yourself to unload if you don’t sort the items correctly.
I learned a long time ago that the ability to recognize and exploit a structured system is the most emotionally satisfying thing in the world.
publlus_enigma 2 hours ago [-]
The question becomes: is it faster to sort during packing, or to sort during unpacking?
freecodeio 6 hours ago [-]
shouldn't stacking like a raccoon on meth be the most optimal way though? since if they're too well stacked you risk water being unable to enter tight places
DougN7 3 hours ago [-]
The stacking regime is meant to maximize water flow and surface exposure to water jets, at least when optimized.
embedding-shape 6 hours ago [-]
> I don't actually believe that you can stack the dishwasher wrong as such
You most definitely can, they're not magic! The water must hit the right spots and obviously stacking three plates without any space between leads to stuff not getting properly cleaned.
If you try to teach a kid to put the dishwasher you'll learn a ton of wrong ways of doing it! :)
notrealyme123 6 hours ago [-]
I think putting cups with the opening facing upward is very close to "technically correct, but very wrong"
jojogeo 7 hours ago [-]
Never have truer words been spoken, I too score poorly on DishwasherBench wife mode. Drives her up the wall.
teekert 7 hours ago [-]
At our place it's opposite, I guess when you do it often enough you get a preferred method though a relentless optimization loop, which in the end ensures it's all clean, the plates are well separated only in 1 particular order, the glasses are placed to the left so all small pans fit at the right, deep plates are placed half over cutlery rack so they are supported and more fit in, small plates in front so all lids fit before them... etc etc etc.
stoneman24 7 hours ago [-]
Yep, I have a more optimised model of stacking than my wife’s ideas. This has lead to “discussions” (still at a friendly level) and the dish washer being placed in my list of responsibilities.
I think optimal configuration is very much a NP complete problem.
lambdaone 4 hours ago [-]
Just because a problem is NP-complete doesn't mean it's infeasible to produce "good enough" approximate solutions. The traveling salesman problem is a great example of this.
stoneman24 2 hours ago [-]
Apologies, my OCD was showing.
It’s an interesting problem to pack the dishwasher with as many objects as possible and maintain the highest level of cleanliness. Sometimes, there’s an small thing leftover so then repack in a different configuration.
mvdwoord 7 hours ago [-]
Try explaining this to a raccoon.. on meth.
I did, once ;)
ce4 6 hours ago [-]
You're already loading it perfectly according to The Oatmeal :-D
Are our wives' standards impossible to reach or are our husbands weaponising incompetence?
mlukewizard 8 hours ago [-]
Inspired by Joma Tech's new YouTube video
Stacked loads are run against a dishwasher simulation calibrated to my own Bosch dishwasher
Playable by both humans and AI
Currently a WIP, simulations need refining before running a full benchmark, but keen to hear some feedback!
vessenes 4 hours ago [-]
Very cool and fun idea. This is a meta comment about the repo readme - there is an immense amount of what I would call ‘complaint smuggling’ / diffidence in the readme - basically Claude is uncomfortable about some of the claims vis a vis the status and embeds those negative feelings everywhere.
I suggest you have it scrub all of this from the readme; you’ll likely need to give it a few examples. It will improve readability a lot, and be less fatiguing to read. Plus if you scrub it all you won’t reprompt that attitude every time an agent reads the readme.
Btw I got Claude to give me the name “complaint smuggling” by giving it ten examples and asking it for a name. it’s an error pattern that’s so common I wanted to know what the model thought of it as - makes communicating about it really simple.
mlukewizard 2 hours ago [-]
Mmmm yea interesting, thanks for the feedback will push an update :)
codeulike 4 hours ago [-]
Can anyone confirm whether it simulates the spinning arm getting stuck on an item that juts downward through the top tray - thereby stopping the whole load from being washed properly.
Thats the most common problem in my dishwasher. It kindof looks like it would simulate that but they dont spell it out.
Come to think of it, if the players dont have an option to "spin the spinner by hand to make sure its not catching on anything" they're going to be in for a rough ride.
mlukewizard 2 hours ago [-]
100%, users check before kicking off a run whether the drawers close and the spinner spins
codeulike 1 hours ago [-]
Fantastic
sandblast 4 hours ago [-]
> A verdict cannot be trusted for:
> A spray arm held still by an item: the plates above it keep their verdicts
dom96 6 hours ago [-]
I love these novel ways to benchmark LLMs. I created one myself, I figured creating a programming language designed to confuse LLMs would be a good test, and it does seem to be: https://bench.killswitch-lang.org/.
I wonder if anyone has crafted a LLM benchmarks list website/github.
comrade1234 6 hours ago [-]
Years ago after my wife filled the dishwasher I commented that it looked like a 12-year-old filled it. I said it as a joke but it really hurt her and I still feel bad about it. That said, it no longer looks like that when she fills it...
lambdaone 4 hours ago [-]
Perhaps a better question would be "can frontier models write a program to effectively stack a dishwasher?"
mlukewizard 1 hours ago [-]
yea super interesting q
my feeling is that stacking a dishwasher involves enough image processing and computer-use (or more realistically robotics) that it's a frontier model job rather than a 'write a program to do it' job
but keen to hear if you disagree
dekhn 3 hours ago [-]
I have to admit that for many years I assumed a dishwasher physically filled the entire chamber with hot water to wash dishes. Then, one day a person opened up a dishwasher while it was running, took out a plate, clicked start, and closed the washer. My mental model literally changed in an instant.
mlukewizard 1 hours ago [-]
ahahhaa
nastrofa 7 hours ago [-]
This is so cool!
Imagine creating real simulated env for every physical task and using RL to train robots. That will be a game changer.
It was the future many years ago, today it's standard practice :)
judetechdevs 6 hours ago [-]
Both models’ loads came out 84-100% clean, so is the score mostly just how much they fit?
mlukewizard 6 hours ago [-]
Totally the opposite, there's a detailed dishwasher simulation under the hood: ray tracing, splash simulation, soak, heat, enzyme action
I calibrated it against my actual dishwasher by doing some test runs with baked egg
judofyr 6 hours ago [-]
As we know from physics, even the most sophisticated mechanisms (e.g. friction) often ends up having a very simple model (proportional to the normal force).
Sooo, the score is maybe mostly just how much they fit?
mlukewizard 5 hours ago [-]
Question for both: do you think that is also the case with a real-world dishwasher (it's mostly about getting stuff to fit), or do you think it's an issue with the current sim?
The sim needs work, for sure
TuringNYC 3 hours ago [-]
I love this! Cant wait to try this.
dist-epoch 6 hours ago [-]
The real story of how Navier Stokes was solved involved a dishwasher:
I hadn't seen it before, funny. OP mentioned in a top level comment that this Joma Tech video was part of their inspiration.
kolinko 6 hours ago [-]
Came here to post this :)
walrus01 6 hours ago [-]
For added difficulty, have it 'stack' a 3D rendered volumetric plastic model of a pelican riding a bicycle, like if it were putting a child's toy in the dishwasher.
laruss5 6 hours ago [-]
[flagged]
squidmaster 3 hours ago [-]
[dead]
l1n 7 hours ago [-]
[flagged]
mlukewizard 7 hours ago [-]
sure the code isn't hand-written and it's a work in progress, but it's designed to be modelled and calibrated around my own dishwasher so it's verifiably non-slop
I can't. So that would surely be proof of AGI.
At home I'm the architect, my wife's the raccoon. I don't actually believe that you can stack the dishwasher wrong as such, but you can make it hard for yourself to unload, if you don't sort the items correctly.
Dishwasher physics matter. But I would never criticize a person in my family for loading the dishwasher the "wrong" way; I just sneak in and reorganize when nobody's looking.
This is the way. I am just happy when someone else, anyone else, actually puts dishes in the dishwasher.
There are definitely more and less correct ways, but personally i think it's "wrong" to load it in a way that leaves the arms blocked or (not) tilt pieces that get excessive water pooling on top
I learned a long time ago that the ability to recognize and exploit a structured system is the most emotionally satisfying thing in the world.
You most definitely can, they're not magic! The water must hit the right spots and obviously stacking three plates without any space between leads to stuff not getting properly cleaned.
If you try to teach a kid to put the dishwasher you'll learn a ton of wrong ways of doing it! :)
I think optimal configuration is very much a NP complete problem.
It’s an interesting problem to pack the dishwasher with as many objects as possible and maintain the highest level of cleanliness. Sometimes, there’s an small thing leftover so then repack in a different configuration.
I did, once ;)
https://theoatmeal.com/comics/dishwasher
Stacked loads are run against a dishwasher simulation calibrated to my own Bosch dishwasher
Playable by both humans and AI
Currently a WIP, simulations need refining before running a full benchmark, but keen to hear some feedback!
I suggest you have it scrub all of this from the readme; you’ll likely need to give it a few examples. It will improve readability a lot, and be less fatiguing to read. Plus if you scrub it all you won’t reprompt that attitude every time an agent reads the readme.
Btw I got Claude to give me the name “complaint smuggling” by giving it ten examples and asking it for a name. it’s an error pattern that’s so common I wanted to know what the model thought of it as - makes communicating about it really simple.
Thats the most common problem in my dishwasher. It kindof looks like it would simulate that but they dont spell it out.
Come to think of it, if the players dont have an option to "spin the spinner by hand to make sure its not catching on anything" they're going to be in for a rough ride.
> A spray arm held still by an item: the plates above it keep their verdicts
I wonder if anyone has crafted a LLM benchmarks list website/github.
my feeling is that stacking a dishwasher involves enough image processing and computer-use (or more realistically robotics) that it's a frontier model job rather than a 'write a program to do it' job
but keen to hear if you disagree
Imagine creating real simulated env for every physical task and using RL to train robots. That will be a game changer.
I calibrated it against my actual dishwasher by doing some test runs with baked egg
Sooo, the score is maybe mostly just how much they fit?
The sim needs work, for sure
https://www.youtube.com/watch?v=ofdMfljL360