Previously I thought that if you ask better questions then you will get better at solving problems. However questions are the shadows or reflections cast from the actual framing of the problem. If you have a well framed problem you will naturally ask better questions. If you haven’t framed the problem well, then you will ask bad questions.
Bad questions are still useful because they are a signal that you are “barking up the wrong tree” or that you need to reformulate the problem.
What marks a bad question and therefore signals a framing of the problem that is unconducive to solving it?
There’s probably a myriad of ways a question can be bad. It appears that most of the questions which signal a failure to frame a problem well are vague. Imagine someone who wants to become a Academy Award winning Cinematographer asks “has anyone every won an Academy Award for Cinematography without going to film school?” the answer is of course “yes”, especially in the early days of the award. But it is not a useful question in that it doesn’t narrow down which actions this aspiring cinematographer should take, avoid, nor clarifies which factors will most impede or expedite their journey. It is only useful in that it shows they are not asking useful questions and therefore their entire formulation of the problem needs work. Better questions are more useful questions.
Much like measures better questions are ones that influence decisions—if a change in answer to a question doesn’t change your decision, then it’s not a useful question.
Popular wisdom encourages us to ask open ended questions, especially those which ask “why?” or “how?”. While this is true for seeking advice or having discussions with experts or building consensus. Better questions even in these circumstances tend to be specific. (i.e. asking for vague help “how can I be a great cinematographer?” versus asking for specific advice “how did Michael Ballhaus light this scene in the nightclub in Under the Cherry Moon? How does it differ to his colour nightclub cinematography in Lola? Why did he make those decisions?” ). However open ended questions may not be better questions in the absence of an expert to ask, however specific they may be.
It is less Socratic, more something out of Yes, Minister, in that I don’t know what I don’t know—so if I ask myself rather than an expert “Why does this problem pervade?” all I can answer is a sort of tentative guess or what I believe is not a likely answer. Whereas an expert may be able to plug my knowledge gaps.
I am undecided whether this means why/how questions potentially better suited for assessing our knowledge or at least our confidence in our knowledge concerning the framing of the problem, but in the absence of an expert, not particularly useful.
Counterpoint: the circumstances where the questions appear to be “good” or “better” questions but you’re still solving the wrong problem? They are good for the problem you are mistakenly trying to solve.
Problem solving with Verbs: This came up when I was trying to think about how to better frame questions with the form “How should I X?”
When outlining stories or screenplays I find action or visual verbs immeasurably useful in creating more interesting scenes. Instead of “Joe talks to Bill” he can negotiate, remonstrate, beg, plead, mock, pontificate etc. Each of which makes the scene much more specific. “Maria goes to the store” is too vague, she may either meander to the store, sprint to the store, or even search for the store. These action verbs not only give us a sense of the character’s intentions and allow us to (appropriately enough for film) imagine visually how it plays out, but are more interesting and useful.
Why doesn’t the same apply to practical questions?
At the risk of going meta, take the question “Should I make a short film?”. There are surprisingly few action verbs that describe being a filmmaker[1] other than ‘make’ and off the top of my head you can either film, direct,”do a pitchya[2]”. If you want to be more specific about how it will be done, you can say you will improvise a film or you can say you will “go vertie”. I’m sure you can use Denominal verbs based off of directors with distinct processes:
“I’m going to Altmann this film” (i.e. lots of overlapping dialogue)
“I’m going to Malick this film” (i.e. lots of improvisation in natural light)
“I’m going to Maysles this film” (i.e. “direct cinema”[3]- long form documentary filmmaking with an observational “fly on the wall” approach to shooting)
“I’m going Kapadia/Morgen this film” (i.e. documentary assembled from archival material)
It kind of works with the question “How should I get to the party?”—rather than “get” I can drive, or I can walk, or I can carpool, I can rideshare, I can bike etc. I may even opt to describe my entrance, I can sneak in, I can explode and make an entrance.… In deed, if I choose to sneak in then I may opt to arrive on foot or rideshare so no one notices my car.
Yes, there are a plethora of department specific verbs—you can lens or shoot a film, score it, colour it, mix it, dub it, cue it, do foley, light it, dress it, design it, (location) scout it, produce it, cut or edit it etc. etc.
I noticed in interviews with Classic Hollywood directors Raoul Walsh and John Ford, they don’t call them “films” or “movies” but “picture”, pronounced more like “pitch-ya” as in “motion picture”.
Most people when they say Cinéma vérité mean “Direct Cinema”—the classic device of Cinéma vérité is the Vox Pop. The proverbial ‘man on the street’ is pulled in front of the camera—often looking down the barrel, already an artificial and performative situation, to give a honest opinion or barometer of public feeling.
I did consider adding “Kubrick it” as a example but I couldn’t decide if “do a lot of takes and wait for something strange or weird to happen as the actors get exhausted/bored” was sufficiently identifiable as a filmmaking process. Many directors do a lot of takes. Chaplain did a lot of takes. You can’t be Kubrick if you do a lot of takes, however there is something unusual and distinct about the way Altmann handled scenes with many characters.
The key here is it should describe both the manner and means in which the task is done. Going or getting to a party or store is too vague. Making or shooting a film tells me nothing about the style, genre, or logistics of filming.
What is the functional difference between Agency and having social power? This is likely a question that reflects my ignorance of the connotations of ‘Agency’ in Rationalist circles. When people say “he’s a powerful man in this industry” does that imply he is greatly Agentic? Can one be Agentic without having social power? Is one the potential and the other the actuality?
I’ll need some clarification: Does that mean that someone who habitually starts new processes or projects but seldom is able to finish them or see them through to completion has lots of (Rationalist sense) Agency?
But also, does that mean in a hypothetical organization where one person has the means to veto any decision others man, but the veto-holder seldom exercises it despite very easily being able to, the veto-holder would not be Agentic?
No. Initiative is, well, it’s an ordinary English word with a generally understood meaning. Pulled from the web:
“The ability to assess and initiate things independently”, “the power or opportunity to act or take charge before others do”, “the ability to use your judgment to make decisions and do things without needing to be told what to do”, synonyms “ambition, action, enterprise, drive, spirit, aggressiveness, vigor, hustle, energy, go, gumption, grit, spunk, assertiveness” etc. I think that paints a pretty clear picture.
This is what I have always understood by the word “agency” in the LW-sphere, at least when applied to people. The LW coinages “agenty” and “agentic” mean having agency in that sense.
So habitually starting things and letting them wither doesn’t cut it, and neither does nominally having some role but never executing it. It’s an inner quality that by its nature must manifest in outward actions.
The word “Agency” also has specific other, more technical uses. Here it is in philosophy, where it means something distantly similar but far broader. It’s a “porridge word” (Edward de Bono’s coinage), a hazy concept with little content that, like porridge, takes up the shape of whatever container it is put in. “Fake explanations” often consist of calling the thing to be explained by a porridge word.
Then there is “Agency” in the context of AIs having it, or being Agents. This is something that I don’t think the users of the word understand themselves. They’re trying to project human agency in the sense described above onto these giant weight matrices without having a non-mentalistic characterisation of the phenomenon they’re trying to find there. Not knowing what you’re looking for makes it difficult to find. From time to time I’ve suggested that control systems, hierarchically organised in a specific way, are the concept they need, but haven’t got much traction.
Thank you for taking the time to try and give me a broad overview of the different nuances of the word, unfortunately here the student has failed the teacher. I’m still very confused.
I previously have understood the porridge sense of agency (tangent—I like that phrase ‘porridge word’, reminds me of Minksy’s ‘suitecase word’) to be “an entity that has influence or can affect change”. Here on LW I have been brought to believe it just means acting, verging on thoughtlessly, which I understood to be since acting is the only way to catalyze change (i.e. change towards one’s goals).
So habitually starting things and letting them wither doesn’t cut it, and neither does nominally having some role but never executing it. It’s an inner quality that by its nature must manifest in outward actions.
I failed to explain my confusion: It’s not so much “letting them wither” let me put it another way: if you are in a bunker, there’s a armed conflict overhead, and therefore the smartest thing to do is “nothing” by staying put in the bunker, are you being agentic/acting agentically? The only things they can initiate at that point are unnecessary risk.
Likewise, I don’t mean nominally having some role. Not nominally but actually having the means, the power, the authority, the social status, the lack of negative repercussions to exercise the means, the knowledge but choosing not to exercise it because they evaluate it as not being worthwhile. They could initiate changes, but they rarely see the need, not from fear or reluctance, but from weighing up the pros and cons. Are they being agentic?
Agency here is not “change for the sake of change” but presumedly “acting in a way that materializes the agent’s goals” and that requires initiative, analogous to Aristotle’s Kinoun (Efficient) Cause—the carpenter who takes the initiative of making wood into a table. However the connotation of spunk, hustle, ambition etc. etc. and generally acting with energy and enthusiasm towards goals—knowing that these are not golden tickets to success (Necessary factors? Probably. Sufficient? Probably not.) -- confuses me what this quality is describing.
You’re looking at edge cases in order to understand the concept. I think looking at the centre works better than mapping out the periphery, which was my reason for giving those definitions and synonyms of “initiative”. If someone is in a situation where circumstances forestall any effective action, then to ask whether they are being “agentic” in doing nothing is like asking whether an unheard falling tree makes a sound.
I’m afraid I just have to give up on understanding what Agency means then. Thank you for trying though.
If someone is in a situation where circumstances forestall any effective action, then to ask whether they are being “agentic” in doing nothing is like asking whether an unheard falling tree makes a sound.
Unlike initiative because you can take initiative and it not deliver intended results. But it’s still initiative. While is being Agentic a potential or an actuality? I don’t know.
Agency has little to do with social power. It’s kind of hard to describe agency, but it’s characterized by deliberateness: carefully and consciously thinking about your goals as well as having conscious models for how they help you achieve your goals, in contrast to unthinkingly adhering to a routine or doing what everyone else is doing because it is what everyone else is doing. Also has some aspect of being the kind of person who does things, who chooses action over inaction.
So by that definition would you consider trickster archetype characters (you can see why I have been wondering) like Harpo Marx or Woody Woodpecker who appear to be very impulsive, albeit not bound by routines or what everyone else is doing because everyone else is doing it would not have Agency because he is highly reactionary and doesn’t plan?
Let me write out my current assumptions as it might make it easier to correct them:
Analysis Paralysis is not Agentic because while it involves carefulness and consciously plotting moves towards goals, it lacks action towards them.
Hedonic and Impulsive activity is not agentic because while it does involve action towards one’s goals, it lacks careful planning.
Agency then is making plans and acting upon them irrespective of whether one is able to see them through to completion, provided one has the intention and will, and the forethought.
“Babbling Better” this is a work in progress -and still requires more thinking
In short—need a methodology or at least heuristics for identifying the “right problem” to solve, and noticing when one is solving the “wrong problem”. Better problem framing leads to better and more focused answers to questions and hopefully eventual resolving of problems. I’ve come across two techniques: The Five Whys to understand problems better, and using adverbs of manner to babble more constructively.
So far:
It is easy to babble, babies do it. It is still quite easy to babble comprehensible but wrong sentences, such as LLM hallucinations. Your pruning is only as good as your babble.
With regards to problem solving, low quality babble doesn’t contribute to resolving the problem. For example, let’s say the problem is “camera autofocus doesn’t focus on eyes” a low quality “babble” answer might be “Burn a stick of incense and pray to Dionysius”. The acts themselves are feasible and the sentence is comprehensible. But any desired change in the camera’s autofocus performance will be pure coincidence.
My hunch is that to babble better not only do you need better methods of babbling, but you need to better understand what goals you are trying to babble towards. And that requires better understanding of why the problem is a problem.
5 Why’s on yourself: Asking “why I think this is a problem?” to at least 5 levels
Not to be mistaken for the Burger joint. The “Five Whys” technique was apparently invented at the Toyota Corporation as a system for uncovering the root causes of production faults.
The choice of “why” falls into broader pattern which takes me back to documentary filmmaking and interviewing: you learn more through open ended questions, usually those where the key interrogative is “why” or “how” than through close ended questions. These, as Wittgenstein pointed out, basically seek to affirm or negative a proposition or conditional: “Do you like him?” “Is he still there?” “Would you call that green or turquoise?”.
If I am a manager or investigator, trying to ascertain the cause of a fault on a production line, open ended questions make sense since I will not be in possession of all known or knowable facts. This still holds if I am a novice or just someone enquiring to an expert for help in achieving some goal. If I ask an experienced cinematographer “how would that scene be light?” even if they don’t know specifically, they have a large body of experience and knowledge that would mean they could probably make useful guesses on how to replicate the effect.
If i intend on asking for advice from an expert, I can’t give them the responsibility of figuring out the kind of help I need. The better I can define the problem myself the better and more informative the question I can ask them. Be too vague about your problem and you can only hope to get generic responses like “be confident”.
It seems ridiculous though, doesn’t it? Socratic or even from Yes, Minister: Why should I ask myself open ended questions if I don’t know what I don’t know? While I may not understand the problem, what I can do is at least explain why it’s a problem and how I see it. And one effective way to do that I’ve found is to use the Five Whys Technique.
It is often exceedingly difficult to know what the right problem to solve is, what we may have a better chance of defining is why we perceive it as a problem and why we expect it to cause conflict.
To—Do: add more techniques to my arsenal to better defined problems… the step before babbling
Adverbs and Creativity? Strategically Efficaciously Productively Babbling
I have recently come across a technique for higher-quality babble, at least for creative purposes. It is as simply as employing a Adverb of Manner to modify a verb. This is a minor variation on a technique used to allow mime artists to create a character—you take a situation or process like “make breakfast” and do it with an attitude: happy, hungover, lovelorn.
It is surprisingly easy to come up with scenarios and even stories with arcs—goals, conflict, and comedic pay-offs complete with a character who has distinct mannerisms—by just cycling through adverbs. Compare these three adverbs: grumpily, overzealously, nervously.
He bartends grumpily—he tries to avoid eye contact with customers, sighs like a petulant teenager when he does make eye contact, he slams down glasses, he spills drinks, on his face a constant scowl, he waves customers away dismissively. Even a simple glass of beer he treats like one of the labours of Herakles
He bartends overzealously—he invites customers to the bar, he slams down glasses too, he spills them, he accidently breaks glasses in his zeal but always with a smile on his face, he’s more than happy to do a theatrical shake of the mixer, throw it even if it doesn’t quite make it’s landing. He’s always making a chef’s kiss about any cocktail the customer asks for
He bartends nervously—he doesn’t realize when a customer is trying to order, giving a “who me?” reaction, he scratches his head a lot, he takes his time, he fumbles with bottles and glasses, he even takes back drinks and starts again.
These scenarios appear to “write themselves” for the purposes of short pantomime bits. This is the exact type of technique I have spent years searching for.
To do—Does this technique of better babbling through adverbs of manner apply to non-creative applications? If not then develop methodology or at least heuristics for identifying the right problem, noticing a “wrong problem”
To think about: Shannon Information and cataloguing ‘rushes’ from a documentary. This is not about the actual amount of entropy in any given frame of a uncompressed video. Rather the entropy of all the metadata from all the footage.
Eisenstenian film theory was an attempt to marry Marxist Dialectic with film editing. The “highest” type of film cut was “Intellectual Montage” the bone to nuclear-satellite cut in 2001: A Space Odyssey is perhaps the most iconic example in film history. Eisenstein himself used the more on-the-nose approach of showed crowds of protesters being mowed down by Tsarist troops being interspliced with footage of animals being slaughtered in an abattoir.
The Dialectic of cuts, the juxtaposition between image A and image B—be it the Kuleshov experiment—the actor appearing to look at either soup or a corpse lying in state thereby changing the inferred emotion of the actor—is a critical film language technique.
Documentary Rushes of similar thematic content—i.e. “Shot 1 - mid shot children playing” “Shot 2 - mid shot different children playing” and lower entropy. “Shot 1 - mid shot children playing” “Shot 87 - close up of old man smiling”. We want to avoid homogenous sets.
The problem for a film editor, especially a observational documentary film editor or someone working with archive material (think of the films of Bret Morgan and Asif Kapadia) is every time you create a sequence you have to watch all of the material, again, hoping to find the dialectic or invent a narrative that combines at least two shots together.
Binary Search algorithms are also relevant here.
CLIP and visual Semantic Networks can automate part of the search if the editor has something specific in mind. I want to cultivate serendipity—unforseen juxtapositions.
Previously I thought that if you ask better questions then you will get better at solving problems. However questions are the shadows or reflections cast from the actual framing of the problem. If you have a well framed problem you will naturally ask better questions. If you haven’t framed the problem well, then you will ask bad questions.
Bad questions are still useful because they are a signal that you are “barking up the wrong tree” or that you need to reformulate the problem.
What marks a bad question and therefore signals a framing of the problem that is unconducive to solving it?
There’s probably a myriad of ways a question can be bad. It appears that most of the questions which signal a failure to frame a problem well are vague. Imagine someone who wants to become a Academy Award winning Cinematographer asks “has anyone every won an Academy Award for Cinematography without going to film school?” the answer is of course “yes”, especially in the early days of the award. But it is not a useful question in that it doesn’t narrow down which actions this aspiring cinematographer should take, avoid, nor clarifies which factors will most impede or expedite their journey. It is only useful in that it shows they are not asking useful questions and therefore their entire formulation of the problem needs work. Better questions are more useful questions.
Much like measures better questions are ones that influence decisions—if a change in answer to a question doesn’t change your decision, then it’s not a useful question.
Popular wisdom encourages us to ask open ended questions, especially those which ask “why?” or “how?”.
While this is true for seeking advice or having discussions with experts or building consensus. Better questions even in these circumstances tend to be specific. (i.e. asking for vague help “how can I be a great cinematographer?” versus asking for specific advice “how did Michael Ballhaus light this scene in the nightclub in Under the Cherry Moon? How does it differ to his colour nightclub cinematography in Lola? Why did he make those decisions?” ). However open ended questions may not be better questions in the absence of an expert to ask, however specific they may be.
It is less Socratic, more something out of Yes, Minister, in that I don’t know what I don’t know—so if I ask myself rather than an expert “Why does this problem pervade?” all I can answer is a sort of tentative guess or what I believe is not a likely answer. Whereas an expert may be able to plug my knowledge gaps.
I am undecided whether this means why/how questions potentially better suited for assessing our knowledge or at least our confidence in our knowledge concerning the framing of the problem, but in the absence of an expert, not particularly useful.
Counterpoint: the circumstances where the questions appear to be “good” or “better” questions but you’re still solving the wrong problem? They are good for the problem you are mistakenly trying to solve.
Problem solving with Verbs:
This came up when I was trying to think about how to better frame questions with the form “How should I X?”
When outlining stories or screenplays I find action or visual verbs immeasurably useful in creating more interesting scenes. Instead of “Joe talks to Bill” he can negotiate, remonstrate, beg, plead, mock, pontificate etc. Each of which makes the scene much more specific. “Maria goes to the store” is too vague, she may either meander to the store, sprint to the store, or even search for the store. These action verbs not only give us a sense of the character’s intentions and allow us to (appropriately enough for film) imagine visually how it plays out, but are more interesting and useful.
Why doesn’t the same apply to practical questions?
At the risk of going meta, take the question “Should I make a short film?”. There are surprisingly few action verbs that describe being a filmmaker[1] other than ‘make’ and off the top of my head you can either film, direct,”do a pitchya[2]”. If you want to be more specific about how it will be done, you can say you will improvise a film or you can say you will “go vertie”. I’m sure you can use Denominal verbs based off of directors with distinct processes:
It kind of works with the question “How should I get to the party?”—rather than “get” I can drive, or I can walk, or I can carpool, I can rideshare, I can bike etc. I may even opt to describe my entrance, I can sneak in, I can explode and make an entrance.… In deed, if I choose to sneak in then I may opt to arrive on foot or rideshare so no one notices my car.
Yes, there are a plethora of department specific verbs—you can lens or shoot a film, score it, colour it, mix it, dub it, cue it, do foley, light it, dress it, design it, (location) scout it, produce it, cut or edit it etc. etc.
I noticed in interviews with Classic Hollywood directors Raoul Walsh and John Ford, they don’t call them “films” or “movies” but “picture”, pronounced more like “pitch-ya” as in “motion picture”.
Most people when they say Cinéma vérité mean “Direct Cinema”—the classic device of Cinéma vérité is the Vox Pop. The proverbial ‘man on the street’ is pulled in front of the camera—often looking down the barrel, already an artificial and performative situation, to give a honest opinion or barometer of public feeling.
I did consider adding “Kubrick it” as a example but I couldn’t decide if “do a lot of takes and wait for something strange or weird to happen as the actors get exhausted/bored” was sufficiently identifiable as a filmmaking process. Many directors do a lot of takes. Chaplain did a lot of takes. You can’t be Kubrick if you do a lot of takes, however there is something unusual and distinct about the way Altmann handled scenes with many characters.
The key here is it should describe both the manner and means in which the task is done. Going or getting to a party or store is too vague. Making or shooting a film tells me nothing about the style, genre, or logistics of filming.
What is the functional difference between Agency and having social power? This is likely a question that reflects my ignorance of the connotations of ‘Agency’ in Rationalist circles.
When people say “he’s a powerful man in this industry” does that imply he is greatly Agentic? Can one be Agentic without having social power? Is one the potential and the other the actuality?
“Agency” is rationalist jargon for “initiative”, the ability to initiate things.
I’ll need some clarification:
Does that mean that someone who habitually starts new processes or projects but seldom is able to finish them or see them through to completion has lots of (Rationalist sense) Agency?
But also, does that mean in a hypothetical organization where one person has the means to veto any decision others man, but the veto-holder seldom exercises it despite very easily being able to, the veto-holder would not be Agentic?
No. Initiative is, well, it’s an ordinary English word with a generally understood meaning. Pulled from the web:
“The ability to assess and initiate things independently”, “the power or opportunity to act or take charge before others do”, “the ability to use your judgment to make decisions and do things without needing to be told what to do”, synonyms “ambition, action, enterprise, drive, spirit, aggressiveness, vigor, hustle, energy, go, gumption, grit, spunk, assertiveness” etc. I think that paints a pretty clear picture.
This is what I have always understood by the word “agency” in the LW-sphere, at least when applied to people. The LW coinages “agenty” and “agentic” mean having agency in that sense.
So habitually starting things and letting them wither doesn’t cut it, and neither does nominally having some role but never executing it. It’s an inner quality that by its nature must manifest in outward actions.
The word “Agency” also has specific other, more technical uses. Here it is in philosophy, where it means something distantly similar but far broader. It’s a “porridge word” (Edward de Bono’s coinage), a hazy concept with little content that, like porridge, takes up the shape of whatever container it is put in. “Fake explanations” often consist of calling the thing to be explained by a porridge word.
Then there is “Agency” in the context of AIs having it, or being Agents. This is something that I don’t think the users of the word understand themselves. They’re trying to project human agency in the sense described above onto these giant weight matrices without having a non-mentalistic characterisation of the phenomenon they’re trying to find there. Not knowing what you’re looking for makes it difficult to find. From time to time I’ve suggested that control systems, hierarchically organised in a specific way, are the concept they need, but haven’t got much traction.
Thank you for taking the time to try and give me a broad overview of the different nuances of the word, unfortunately here the student has failed the teacher. I’m still very confused.
I previously have understood the porridge sense of agency (tangent—I like that phrase ‘porridge word’, reminds me of Minksy’s ‘suitecase word’) to be “an entity that has influence or can affect change”. Here on LW I have been brought to believe it just means acting, verging on thoughtlessly, which I understood to be since acting is the only way to catalyze change (i.e. change towards one’s goals).
I failed to explain my confusion: It’s not so much “letting them wither” let me put it another way: if you are in a bunker, there’s a armed conflict overhead, and therefore the smartest thing to do is “nothing” by staying put in the bunker, are you being agentic/acting agentically? The only things they can initiate at that point are unnecessary risk.
Likewise, I don’t mean nominally having some role. Not nominally but actually having the means, the power, the authority, the social status, the lack of negative repercussions to exercise the means, the knowledge but choosing not to exercise it because they evaluate it as not being worthwhile. They could initiate changes, but they rarely see the need, not from fear or reluctance, but from weighing up the pros and cons. Are they being agentic?
Agency here is not “change for the sake of change” but presumedly “acting in a way that materializes the agent’s goals” and that requires initiative, analogous to Aristotle’s Kinoun (Efficient) Cause—the carpenter who takes the initiative of making wood into a table. However the connotation of spunk, hustle, ambition etc. etc. and generally acting with energy and enthusiasm towards goals—knowing that these are not golden tickets to success (Necessary factors? Probably. Sufficient? Probably not.) -- confuses me what this quality is describing.
You’re looking at edge cases in order to understand the concept. I think looking at the centre works better than mapping out the periphery, which was my reason for giving those definitions and synonyms of “initiative”. If someone is in a situation where circumstances forestall any effective action, then to ask whether they are being “agentic” in doing nothing is like asking whether an unheard falling tree makes a sound.
I’m afraid I just have to give up on understanding what Agency means then. Thank you for trying though.
Unlike initiative because you can take initiative and it not deliver intended results. But it’s still initiative. While is being Agentic a potential or an actuality? I don’t know.
Agency has little to do with social power. It’s kind of hard to describe agency, but it’s characterized by deliberateness: carefully and consciously thinking about your goals as well as having conscious models for how they help you achieve your goals, in contrast to unthinkingly adhering to a routine or doing what everyone else is doing because it is what everyone else is doing. Also has some aspect of being the kind of person who does things, who chooses action over inaction.
So by that definition would you consider trickster archetype characters (you can see why I have been wondering) like Harpo Marx or Woody Woodpecker who appear to be very impulsive, albeit not bound by routines or what everyone else is doing because everyone else is doing it would not have Agency because he is highly reactionary and doesn’t plan?
Let me write out my current assumptions as it might make it easier to correct them:
Analysis Paralysis is not Agentic because while it involves carefulness and consciously plotting moves towards goals, it lacks action towards them.
Hedonic and Impulsive activity is not agentic because while it does involve action towards one’s goals, it lacks careful planning.
Agency then is making plans and acting upon them irrespective of whether one is able to see them through to completion, provided one has the intention and will, and the forethought.
Is that correct?
“Babbling Better” this is a work in progress -and still requires more thinking
In short—need a methodology or at least heuristics for identifying the “right problem” to solve, and noticing when one is solving the “wrong problem”. Better problem framing leads to better and more focused answers to questions and hopefully eventual resolving of problems. I’ve come across two techniques: The Five Whys to understand problems better, and using adverbs of manner to babble more constructively.
So far:
It is easy to babble, babies do it. It is still quite easy to babble comprehensible but wrong sentences, such as LLM hallucinations. Your pruning is only as good as your babble.
With regards to problem solving, low quality babble doesn’t contribute to resolving the problem. For example, let’s say the problem is “camera autofocus doesn’t focus on eyes” a low quality “babble” answer might be “Burn a stick of incense and pray to Dionysius”. The acts themselves are feasible and the sentence is comprehensible. But any desired change in the camera’s autofocus performance will be pure coincidence.
Yet, sometimes low quality babble appears to be high quality babble because we simply are not solving the right problem but it appears to be perfectly suited for the problem. Especially if incentives are involved.
My hunch is that to babble better not only do you need better methods of babbling, but you need to better understand what goals you are trying to babble towards. And that requires better understanding of why the problem is a problem.
5 Why’s on yourself: Asking “why I think this is a problem?” to at least 5 levels
Not to be mistaken for the Burger joint. The “Five Whys” technique was apparently invented at the Toyota Corporation as a system for uncovering the root causes of production faults.
The choice of “why” falls into broader pattern which takes me back to documentary filmmaking and interviewing: you learn more through open ended questions, usually those where the key interrogative is “why” or “how” than through close ended questions. These, as Wittgenstein pointed out, basically seek to affirm or negative a proposition or conditional: “Do you like him?” “Is he still there?” “Would you call that green or turquoise?”.
If I am a manager or investigator, trying to ascertain the cause of a fault on a production line, open ended questions make sense since I will not be in possession of all known or knowable facts.
This still holds if I am a novice or just someone enquiring to an expert for help in achieving some goal. If I ask an experienced cinematographer “how would that scene be light?” even if they don’t know specifically, they have a large body of experience and knowledge that would mean they could probably make useful guesses on how to replicate the effect.
If i intend on asking for advice from an expert, I can’t give them the responsibility of figuring out the kind of help I need. The better I can define the problem myself the better and more informative the question I can ask them. Be too vague about your problem and you can only hope to get generic responses like “be confident”.
It seems ridiculous though, doesn’t it? Socratic or even from Yes, Minister: Why should I ask myself open ended questions if I don’t know what I don’t know? While I may not understand the problem, what I can do is at least explain why it’s a problem and how I see it. And one effective way to do that I’ve found is to use the Five Whys Technique.
It is often exceedingly difficult to know what the right problem to solve is, what we may have a better chance of defining is why we perceive it as a problem and why we expect it to cause conflict.
To—Do: add more techniques to my arsenal to better defined problems… the step before babbling
Adverbs and Creativity?
Strategically EfficaciouslyProductively BabblingI have recently come across a technique for higher-quality babble, at least for creative purposes. It is as simply as employing a Adverb of Manner to modify a verb. This is a minor variation on a technique used to allow mime artists to create a character—you take a situation or process like “make breakfast” and do it with an attitude: happy, hungover, lovelorn.
It is surprisingly easy to come up with scenarios and even stories with arcs—goals, conflict, and comedic pay-offs complete with a character who has distinct mannerisms—by just cycling through adverbs. Compare these three adverbs: grumpily, overzealously, nervously.
These scenarios appear to “write themselves” for the purposes of short pantomime bits. This is the exact type of technique I have spent years searching for.
To do—Does this technique of better babbling through adverbs of manner apply to non-creative applications? If not then develop methodology or at least heuristics for identifying the right problem, noticing a “wrong problem”
To think about:
Shannon Information and cataloguing ‘rushes’ from a documentary. This is not about the actual amount of entropy in any given frame of a uncompressed video. Rather the entropy of all the metadata from all the footage.
Eisenstenian film theory was an attempt to marry Marxist Dialectic with film editing. The “highest” type of film cut was “Intellectual Montage” the bone to nuclear-satellite cut in 2001: A Space Odyssey is perhaps the most iconic example in film history. Eisenstein himself used the more on-the-nose approach of showed crowds of protesters being mowed down by Tsarist troops being interspliced with footage of animals being slaughtered in an abattoir.
The Dialectic of cuts, the juxtaposition between image A and image B—be it the Kuleshov experiment—the actor appearing to look at either soup or a corpse lying in state thereby changing the inferred emotion of the actor—is a critical film language technique.
Documentary Rushes of similar thematic content—i.e. “Shot 1 - mid shot children playing” “Shot 2 - mid shot different children playing” and lower entropy. “Shot 1 - mid shot children playing” “Shot 87 - close up of old man smiling”. We want to avoid homogenous sets.
The problem for a film editor, especially a observational documentary film editor or someone working with archive material (think of the films of Bret Morgan and Asif Kapadia) is every time you create a sequence you have to watch all of the material, again, hoping to find the dialectic or invent a narrative that combines at least two shots together.
Binary Search algorithms are also relevant here.
CLIP and visual Semantic Networks can automate part of the search if the editor has something specific in mind. I want to cultivate serendipity—unforseen juxtapositions.