Owning ideas with copyright and patents is what separates the United States from communism.
The first time a saw a documentary about Tetris it really hit me what communism is -- nobody owned anything they invented or created. [0] It was a long time ago and I remember feeling sad watching the story. In the Soviet Union, a group of ~15 people, Politburo, controlled everything including any thought written to paper.
It is this one line, Article 1 Section 8 Clause 8, that separates the United States from the disaster that was the Soviet Union:
> To promote the Progress of Science and useful Arts, by securing for limited Times to Authors and Inventors the exclusive Right to their respective Writings and Discoveries;
I don't think it is far fetched to call ignoring and disregarding the Copyright Clause a communist revolution, violent or not. That is the one thing the communists -- there have been many over the years inside the United States -- would change to make the United States a communist country.
In the Soviet Union the state owned all media (de facto) and you had to get permission from a party official before you published or copied anything. It's not the same thing as a free for all.
It's actually the first sentence from your quote. One state owned company had a monopoly on software exports. Soviet citizens were not allowed to write code and export it themselves, or import software from Western countries. They had heavy censorship and centralized control over everything.
In a way it's the ultimate endpoint of copyright. One {person, state, company} owns everything and you have to ask them for permission to do anything with it.
In a communist society there is no profit (or incentive for), thus no need for copyright laws.
It's not abolishing copyrights that would turn the US into a commie country, communism is about abolishing private ownership to the means of production.
In the United State, the individual or corporation owns the invention. In the Soviet Union the state automatically owned the invention. That clause is what ensures private ownership.
The clause is what ensures profits from market sales or licensing of ideas go to the creator.
Removing (or ignoring in the case of AI companies) that clause in the US Constitution is what abolishes private ownership.
Well it's worth reading the linked wiki article section, which includes a link to another article "Copyright law of the Soviet Union", flatly contradicting you unless you maintain that the USSR wasn't truly communist.
A couple weeks ago, Neil deGrasse Tyson had neuroscientist David Eagleman as his guest on Star Talk. David discussed his friend and co-founder of Pixar, Ed Catmull, has aphantasia and that Catmull tested the directors and animators at Pixar, discovering that many of its top artists are also aphantasic! [0]
They have a theory that artists who have to struggle more during the training and developing of being able to express on medium develop into better artists.
Or maybe seeing things in front of your mind's eye is not an essential quality for animating or computer graphics
Personally I do have aphantasia, but I am great at reasoning about how things relate to each other in 3d and over time. From the little research that exists there are some hints that people with aphantasia might on average be better at this than people without it, and those seem like much more important qualities to me than being able to see a rabbit on some imaginary 2d display
I am also a member of this club, and I think it's _very likely_ that aphantasics as a class have better 'spatial' skills/memory than typical, simply because we are forced to exercise that capability constantly.
Spatial mappings are essentially how I express memories that others seem to hold as mental images of some kind, many of those _essential to function_, like "how do I drive from A to B", "how do I accomplish this complex task", "how do I recognize a place I've been before" (that last one is.. an interesting issue, because it turns out the things I use to recognize a scene are _almost_ sufficiently unique, but _not quite_; I occasionally get locations confused entirely because their streets meet at the same angle/distances, or the hedge and building are similar heights).
There is some truth in this, but evidence sometimes suggests worse visuospatial memory, at least under some very specific operationalizations. E.g. less detail can be remembered overall, even though crucial details remembered are the same: https://pmc.ncbi.nlm.nih.gov/articles/PMC10598423/
More likely than not there are tradeoffs to using strictly visual vs. visual+ vs. strictly non-visual mental models in all domains, and there is no universally optimal strategy (and that teams of mixed cognitive styles are best overall). You know, no free lunch.
They asked people who survived jumping from the Golden Gate Bridge what they were thinking on the way down. They all said they felt instant regret the moment they let go of the rail.
About 30% of survivors try again and ~7% eventually succeed according to https://hsph.harvard.edu/research/means-matter/means-matter-... , "Nine out of ten people who attempt suicide and survive will not go on to die by suicide at a later date. This has been well-established in the suicidology literature. A literature review (Owens 2002) summarized 90 studies that have followed over time people who have made suicide attempts that resulted in medical care. Approximately 7% (range: 5-11%) of attempters eventually died by suicide, approximately 23% reattempted non-fatally, and 70% had no further attempts."
I believe this, and it mirrors what I have heard from suicide attempt survivors in my personal life too.
I do wonder what the story would be if we could somehow ask the people who didn't survive. Likely a purely philosophical question with no answer, but I wonder how many of the people who do end their own lives don't regret it at all.
Most likely the dead are not capable of regret, but if there is some manner of afterlife where people can contemplate their actions, I do wonder how many of them would regret their suicides
Only the ones you could ask afterwards;) This is propaganda pretending that suicide is an impulsive decision. That's a category error because in many cases, it is not.
If there was more focus on screening for impulsive thoughts and disrupting people who suddenly change behaviour, modern suicide prevention would do much better. The people who really want to die do not engage with therapy or mental health services because they know they'll be having their freedom taken away if they mention their thoughts to anyone else. That's why many of these stories go like "oh he looked so happy! no one could have known" - yeah because he was smart enough not to say anything;)
Improbable to be very significant, but it might actually be. The way/where they jumped off the bridge or how they hit the water may have influenced their chances of survival.
Edit: Implied is that how determined they were to commit suicide influenced their behavior before survival/death was fully out of their control.
The single best animated data visualization to demonstrate the stochastic nature of LLM models: an animation of the probability of solving a long multiplication problem over several runs. [0]
I bring 13 years of full-stack UI development experience alongside deep expertise in browser automation and agents, which I've been engineering since 2018. This blend makes me particularly strong in QA automation engineering and complex frontend architecture.
Notable projects include event ticket inventory management and a drag-and-drop CRM email builder for social marketing campaigns. As a consultant and full-time engineer, I’ve led 0-to-1 product development across streaming, real estate, edtech, marketing, and media. Having worked at companies ranging from a 130-person AI organization to a scrappy 7-person team, I thrive most in fast-paced, high-ownership environments.
I find once there is one poisoned line of text it negatively affects everything else downstream. Instead, I use a temp/ folder with documents and use different files for different agents and models. Then I have to constantly prune and delete the files. Any information that can be extrapolated is just noise which negatively affects the agent. If you have a definition of a database structure and it has been implemented, that information should not be contained in any text document -- it is noise, will drift, and be impossible to debug why the agent keeps producing undesired behavior.
I have a ~/Projects folder. For example, I use Playwright with Chrome DevTools Protocol in order to do performance testing and leak detection. There is a script that handles this. My prompt is "Search ~/Projects for perf testing with CDP and Playwright and implement here". Point being, if I need anything I point to a resource or ask to search a resource and it will find it quick and, most importantly, tends to improve it every iteration.
If I was in an institution, I would have a repository and would rather just point the resource and say use that than have memory of it locally.
Your experience mirrors my own. I don't know if he coined the term, but Steve Yegge talks about 'heresies' that creep in to a system -- untrue things that stick around and permanently influence its behavior. I still find that these happen regularly and stopped using self-managing memory systems because they make heresies even harder to diagnose and remove.
Within projects, I make heavy use of path-scoped rules to intentionally bring context where it's needed, and also make heavy use of temp directories. LLMs are more than happy to produce ad-hoc memories/summaries/context docs that I can then point a session to, but I can be selective and intentional about it.
I like that memoryfield is portable, intentional and composable. I'm not convinced that sharing memoryfields between users will be practical, but I keep isolated virtual environments for absolutely everything. I like the idea of being able to intentionally bring collections of managed context around with me. There are other ways to do that, but will keep an eye on this.
This is a real problem, and it’s not just in markdown files and docs. Claude loves to write things we’ve “discovered” in comments and then later in treats the comments as gospel truth.
You have to constantly tend the garden and weed these things out.
Whenever Claude makes some error ask it where and why? And then dig out the weed.
And of course if it’s in the context, probably time for a handover doc (which will need weeding) and started fresh.
> This is a real problem, and it’s not just in markdown files and docs. Claude loves to write things we’ve “discovered” in comments and then later in treats the comments as gospel truth.
There's a simple fix for this: do not let it write comments. Ever. This also has the nice property that there's much less AI slop to clean up afterwards.
I have memory disabled in all my Chat UIs (even though it tends to creep in, looking at you ChatGPT). It’s very helpful until it scales with time, at which point it becomes useless due to staleness or mis-application across contexts.
That being said, in coding over a longer time horizon, having the agent continually re-derive decisions/laws/facts/etc from your code is wasteful of tokens and time, and if your code doesn’t consistently apply them you can’t know the agent will make the correct choices.
You need memory of these important facts to avoid this expense or potential incorrectness. Memory does not itself scale though, without maintenance and pruning, and that has its own impacts on cost and correctness like the Chat memory.
“Damned if you do, damned if you don’t” at least until the agent can itself maintain its memory accurately - or some other non-human effort can achieve that.
e.g. docs/decisions/README.md (index with a blurb about each decision), docs/decisions/01-some-lesson.md (some architectural decision/pattern that you or the agents discovered).
ADR files have important sections like "rejected solutions" and "acceptable risks", and they're live files that can be refined and pivoted over time or retired to docs/decisions/archive/.
It's also nice to give each top-level bullet point some stable ID like "R1" for rejected solution #1, I3 for invariant #3. Agents use this stuff intelligently all the time like "This could be a time to reconsider D4/R2" = ADR #4, rejected solution #2.
The essential part being that your system ratchets into increasingly better decisions and invariants over time, and there's a place to actually put this stuff.
It's essential for automating high-quality software and something we couldn't be arsed to do much less update before AI.
What I propose is only a very slightly more formal version of what you describe.
Just to start with: memoryfields are possible to use in a server/client system. That was a key aim and I do already use them over Amazon S3 (though not always).
I started, like you did, with a personal library of prompts. But the issue is that as your library of little pieces of prompts increases a) you get tired of constantly editing them yourself b) you have no easy way to export and share them with others c) it's frustrating that the agent doesn't "automatically" find your little bit of prompt on X even when clearly it is relevant - hence sem search.
I think a lot of people are still using the "personal library of bits of prompt" model. It is ok. But I wanted to propose an minimal, interchangeable standard for sharing them. So the idea of being an institution and having a shared memoryfield: that's something I want as well!
It keeps documentation from going out of date by embedding re-runnable verification checks directly inside markdown files (that the agents use, not humans). I use it with a handoff workflow to force Claude/GPT to re-verify facts before handing off documentation to the next session.
Memory is prone to poisoning. Also, I want to be able to take my toys and go elsewhere.
My method is seven layers of files, administered differently: meta-knowledge, project seed, LLM wiki, code, tickets and todos, chat logs, artifactory.
Ordered idea-to-reality. All git repos.
That outgrows any context window pretty soon. My way out of that trap is to use links, both wiki links and git permalinks.
I keep it on for my web chats, but I think I dislike it more than it helps. I'll ask a question about something and it'll find a way to tie it back to something from three months ago thinking it was a deep project I was working on, instead of what it really was: an inane question I was curious about.
I turn it off for local agents because I bounce around a few and I really don't like the mostly implicit nature of it. I want to write my instructions in version control if I have anything to say consistently to an agent.
I have mine self record into Supabase for my projects and a local sqlite for work. It determines a method of record keeping which I audit every week to hone the process. Really makes it so I can move to any provider I want and I have a queryable memory store. Also really helps when someone asks about why some feature was implemented a certain way. I also have it learn from corrections in PRs and comments made overtime in a repo to get the shape of what is important to the team at work.
You may be interested in my No3371/projex repo, which is a whole solution based in this idea, I wonder how much do people do differently in this direction
The first time a saw a documentary about Tetris it really hit me what communism is -- nobody owned anything they invented or created. [0] It was a long time ago and I remember feeling sad watching the story. In the Soviet Union, a group of ~15 people, Politburo, controlled everything including any thought written to paper.
It is this one line, Article 1 Section 8 Clause 8, that separates the United States from the disaster that was the Soviet Union:
> To promote the Progress of Science and useful Arts, by securing for limited Times to Authors and Inventors the exclusive Right to their respective Writings and Discoveries;
I don't think it is far fetched to call ignoring and disregarding the Copyright Clause a communist revolution, violent or not. That is the one thing the communists -- there have been many over the years inside the United States -- would change to make the United States a communist country.
[0] https://en.wikipedia.org/wiki/Tetris#Spread_beyond_the_Sovie...
reply