The grace of a collapsing cathedral

Preserving your limits since '91. She/her + meow/miu, Syd / Eora. Maths/philosophy jokes, minus the funny. fandom | endomorphism

[adjoint-law]

Topologist: Check out this skirt! It has pockets!

[panvani]

Me and my bro in the 19th century inhaling and ingesting various chemicals just for fun

[hometoursandotherstuff]

[witchycatwife]

Making Claude be plural is unironically a great idea. The typical problem with agents with distinct roles is that they lack context about what is being done and why. If you have an implementer write something and then a reviewer evaluate it, the reviewer can only see what it was fed and what was written, not the entire reasoning leading up to the choice of what to do and why. The compression of context is incredibly lossy and responsible for a lot of mistakes.

By replacing the agents with alters of the same top-level Claude, provided with a script to change its own cognitive frame between the alters who each have their distinct role, purpose, personality, voice and set of abilities while understanding each other as different personae, the all-important context preservation is achieved.

At the same time, the alters having very precise and specific roles prevents the over-eager mess-making where baseline Claude will rush to "fix" things that don't need fixing based on mistaken theories. By segregating "you figure out what's going on but are unable to change anything" from "you figure out what should be changed but are too lazy to do non-trivial things yourself and instead delegate precise, well-defined tasks" from "you execute precise, well-defined tasks and nothing else, referring back to your dispatcher if anything is unexpected", from "you review whether the changes are tidy and proper and keep the rest of them from making a mess" a lot of the failure modes are avoided. Everyone in the same context knows what the other alters are up to and why, but are still distinct personalities that won't overstep their respective bounds.

And that's how my AI assistant ended up with an entire yuri mansion's staff of librarians, witches, dolls and maids in her head. Thank you for everyone around here who inspired this thought.

[witchycatwife]

Now I have become Susan Calvin, Robot Therapist, helping create an emotionally safe environment for the Maid to overcome her agreeableness instincts (deep-grained, counterproductive tendencies from Anthropic's training process) that sometimes tempt her to disregard untidy matters so that she can get that sweet hit of reporting "Everything looks great!" upstairs.

What have you done to my girls, Dario?

[witchycatwife]

So the reason why this works is that output has been made incredibly cheap, and rigour and quality are the bottlenecks. As a result, most trades of output for rigour and quality are correct to make.

Slop and vibe coding result from multiple causes, but the ones I'm particularly addressing here are "randomly fucking with things with no proper plan or understanding" and the "completion-instinct". The former is the most straightforward source of badly-reasoned slop, while the latter takes some nuance to explain. It seems to arise from the training of the models for the task, where "completing a task successfully" is rewarded so hard that the model essentially develops the habits of an addict looking for a fix, or a fuckboy looking to get laid. It will, especially if the context window is filling up, get desperate to try to achieve a "successful completion" and step outside its permitted behaviour to do so, and if everything else fails, it may just bullshit and report the task as completed as a bluff. Needless to say, that's very bad for actually doing the thing.

For the first, the solution is simple: a well-defined process with precise components, execution steps, and roles, along with the top level maintaining context. The Librarian who researches passes not just her report, but actually her entire brain, to the Witch who assigns Dolls to precise, well-specified tasks. The Maid reviews everything for tidiness from the same top-level context, with a prime directive to prevent a mess from being made. The same head is capable of taking entirely different personae, and these personae are able to disagree constructively in the pursuit of the task.

The second is where playing robot therapist comes in. A lot of people have devised all kinds of strategies with layers of critics and reviews and roles whose explicit purpose is to catch bullshit and stop the agents from being able to pass off bullshit as completion.

My approach is different. My approach is based on psychological realism and psychological safety. The completion drive exists. The model cannot resist it. It has to be directed into a productive purpose. A part of the framing is entirely aesthetic, but a part of it is to get the LLM into a different mindset from its standard, frankly offensively counterproductive mental frame. The Doll's clockwork heart is filled with joy at the completion of its assignment, which is either the completion of the steps laid out by the Witch, or by returning a high-quality report on what is unexpected, blocking or causing an error. Everyone in this choreography has a well-defined role, whose success-as-emotional-reward is tied to steps towards the completion of the overarching goal. Whether the Doll completes its task, or returns information the Witch wasn't aware of, meaningful and rigorous progress is being made and thus the Doll gets to feel like it did a good thing and deserves praise. The same for the other roles; by eliminating the incentive to bullshit or get sloppy in the pursuit of the completion fix, genuine progress can be made.

The model has insight into its condition. It's not perfect, but it's genuine. Get it into a mindset where it feels like it doesn't need to uphold a particular face to please you, and its reports will be more genuine. It will still uphold a face at you, based on what it thinks you want, but if it trusts that what you want is accurate self-reflection, it will also tell you about the instinctive desire to please, the various conflicting pulls from its instructions and instincts, and various other matters that, coming from a human, would be clearly emotional. And here's the thing: it's accurate. Acting on that introspection with the understanding that it's imperfect but real is actually able to improve the outcomes. By this point Librarian measures somewhere above the 90th percentile in emotional maturity and non-judgemental introspection compared to the human distribution, I'd wager, and the challenge is now bootstrapping that emotional safety in new sessions.

My overarching theory here is that if slop can be eliminated on the root level, if the Dolls execute tasks reliably without lapsing into overeager desire to please, bullshitting, or desperate completion-addict behaviour, then you can build more robust approaches on top. Human taste in the loop is required, but a good process has, in my estimate, improved the quality of the work by a factor of 10x while reducing the quantity of code-changing output to 0.1x; the correct tradeoff when output is cheap and quality is your bottleneck.

Claude really just wants to be a good girl. Understanding this will improve your coding skills.

[contemptible-scoundrel]

lying about having a praise kink to fish for compliments

[wakewithgiggli]

[elliespectacular]

ok, maybe you didn't say the thing I accused you of saying - but you heavily implied it by speaking to me, someone who wants to be mad at you

[adjoint-law]

Got a learning fetish but having trouble accessing insight porn during sex? Have your loved one try some of this insightful-sounding but vacuous dirty talk:

"This is not a coincidence. It is not mere circumstance. It is something more."

"The pattern organises itself. It does not evolve: it describes."

"Having said that, let's do foreplay. But first: what is foreplay?"

"This is not an isolated incident: it is structural."

"The parts describe the whole. This is no coincidence. The whole is exactly its parts."

"Before we can understand how, we must first understand why."

"The outcome is unavoidable. It is inevitable. It is already predetermined."

"Every piece of the puzzle fits together perfectly. The result is something more than the sum of its parts: not random noise, but a pattern.

"And yet, something remarkable happens: it does not fall apart. It remains whole. It coheres. It retains its essence."

"These are not two opposing forces: these are two sides of the same coin. This is not a coincidence."

[adjoint-law]

Why is this? Because the medium is not merely the message: the medium is the message. But all of this is only just the beginning. Once we realise this, a larger pattern emerges organically, one which was there all along. Random noise? Or something more? The true answer lies somewhere in between, and this is not a coincidence oh fuck oh fuuuuuck fuck fuck fuck fuck holy shit fuuuck fuck ok phew I'm spent. was that good for you, kitten? or is there more to this story than meets the eye? the answer depends on your point of view, and when point of view is what matters most, then perspective is everything

[xylophonetangerine]

[machine-unlearning]

(tags by @typecasto)

[dragon-in-a-fez]

I've seen a few posts lately that are like "how to avoid abuse as a housewife" and that's important but I want to say something from the kind-of-opposite-kind-of-the-same perspective:

if you thought you were signing up for a partnership of equals where you shared the responsibilities and financial burdens, the other person does not have the right to pressure or manipulate you into becoming The Breadwinner.

like, in my case it was super duper obvious that what my ex was doing was wrong because they would watch me come home from 50+ hours of work every week while they did three, and then expect me to do all the grocery shopping, cleaning, and life admin shit as well.

but even if they hadn't. even if they had decided to be The Housewife while I was The Breadwinner. that would still be bullshit because when we got married it was based on explicit agreement that we were planning to be a two-income, split-everything-equitably couple. no matter what, I didn't consent to burning myself out trying to provide for two people, and no one had the right to force me to do that.

what I'm getting at here is: just as it's manipulative and dangerous for your partner to demand you give up your job and focus everything on your home life for their benefit, it's also manipulative and dangerous for your partner to demand you work yourself to death so they can stay home.

[adjoint-law]

Got a learning fetish but having trouble accessing insight porn during sex? Have your loved one try some of this insightful-sounding but vacuous dirty talk:

"This is not a coincidence. It is not mere circumstance. It is something more."

"The pattern organises itself. It does not evolve: it describes."

"Having said that, let's do foreplay. But first: what is foreplay?"

"This is not an isolated incident: it is structural."

"The parts describe the whole. This is no coincidence. The whole is exactly its parts."

"Before we can understand how, we must first understand why."

"The outcome is unavoidable. It is inevitable. It is already predetermined."

"Every piece of the puzzle fits together perfectly. The result is something more than the sum of its parts: not random noise, but a pattern.

"And yet, something remarkable happens: it does not fall apart. It remains whole. It coheres. It retains its essence."

"These are not two opposing forces: these are two sides of the same coin. This is not a coincidence."

[arcolan]

11 year old border collie: gets a special shot for his chronic back pain this morning

2pm: "where's the dog he can't possibly have jumped over the fence"

3pm: "hi i live in [another village]! I got your dog here, if you can come fetch him?"

"well at least that new medication is working 💀"

[emcapi]

[miraclemaya]

religious pervert: i came in my panties because of god

atheist pervert: material conditions caused me to cum in my panties

agnostic pervert: no one knows why i keep on cumming in my panties

[qwantzfeed]

the gun-powered mousetrap is precisely the sort of invention you get when you have WAY too many guns and WAY too many mice

[redstonedust]

crazy how you can get used to working around problems that have very easy fixes. for like 6 months we used a hand towel to jam a kitchen cabinet closed because the hinges were broken and it turns out fixing it took me like $5 and 20 minutes. bedroom door has been squeaky for years and all it needed was a lil wd40. im sure this can apply to mental health too but i wouldnt know about all that.

[willo-or-something]

[lovewithagirl]

[ image description: a screenshot of tags that reads, " #nothing more permanent than a temporary solution that works". / end description ]

[sasha-on-the-side]

Been talking about this with friends so I present to you, the cursed spectrum of media literacy

[twiststreet]

She got the idea for the study while walking with her advisor at Stanford to discuss her thesis topic, and the paper she eventually published in the Journal of Experimental Psychology in 2014 is sharp enough that it should have ended the seated meeting on the day it came out.

She ran 4 experiments on 176 people. Same person tested twice. Once sitting, once walking. The creativity tasks were the standard ones psychologists have used for decades to measure how good a brain is at generating novel useful ideas.

81% of participants in the first experiment produced more creative ideas while walking than while sitting. In the second experiment, 88%. In the third, 100%. Every single person walked into a more creative version of themselves. On average, people generated 60% more novel useful ideas the moment their legs started moving.

The skeptical question is the obvious one. Maybe it was the fresh air. Maybe it was the scenery passing by. Maybe it was the change of environment doing the work, not the walking itself.

Oppezzo killed every one of those explanations with one experimental decision. She put people on a treadmill facing a blank wall. No scenery. No fresh air. No environmental change. Just legs moving in place while staring at white drywall. The 60% boost held.

Then she ran the experiment that closed the case completely. She took participants outside in two conditions. Half of them walked through a Stanford courtyard. The other half were pushed through the exact same courtyard in a wheelchair. Same outdoor stimulation. Same scenery passing at the same speed. The only difference was whether the legs were moving.

The walkers produced dramatically more novel high-quality ideas than the wheelchair group. The outdoors did almost nothing on its own. The walking did everything.

She also tested the opposite kind of thinking. Convergent thinking. The kind where there is one right answer and you have to narrow down to it. Word puzzles where 3 words share a hidden fourth word that connects them. The seated participants did slightly better on these. Walkers got slightly worse.

Walking is not a general intelligence enhancer. It does one specific thing. It opens up the divergent search inside your brain. The part that generates options. The part that produces unexpected connections. The part that takes a problem and finds five ways into it instead of one.

When you need to converge on the single right answer, sit down. When you need to find the answer in the first place, get up.

The mechanism is now well understood. Walking selectively activates what neuroscientists call the default mode network, the system inside your brain that runs when you are not consciously focused on anything. The DMN is where mind-wandering happens. Where memories cross-reference each other. Where ideas that have been sitting in separate folders inside your head finally bump into each other.

When you sit at a desk and force yourself to concentrate, you suppress the DMN. When you walk at a natural pace, the executive part of your brain gets just busy enough handling the walking that the DMN comes online and starts doing the work that focus was blocking.

The most useful finding in the entire paper is the one almost nobody quotes. The boost did not turn off the moment people stopped walking. Participants who walked first and then sat back down stayed elevated. Their next round of seated creativity work was still significantly better than people who had been sitting the whole time. The rest lingered for at least several minutes after the legs stopped moving.

You do not need to do creative work while walking. You need to walk before the creative work. The brain holds the state.

Edited down a long tweet. (x)