Tag Archives: politics

Phil 7.1.2025

The show went well! It should be up here soon. Send Jeff a thank you note, a link to the book, and see if he’d like to take a look at the TACJ proposal

Add the following two papers to P33:

The Dictator Dilemma: The Distortion of Information Flow in Autocratic Regimes and Its Consequences

  • Humans have been arguing about the benefits of dictatorial versus democratic regimes for millennia. Despite drastic differences between the dictatorships in the world, one of the key common features is the Dictator’s Dilemma as defined by Wintrobe [1]: a dictator will never know the true state of affairs in his country and is perpetually presented distorted information, thus having difficulties in making the right governing decisions. The dictator’s dilemma is essential to most autocratic regimes and is one of the key features in the literature on the subject. Yet, no quantitative theory of how the distortion of information develops from the initial state has been developed up to date. I present a model of the appearance and evolution of such information distortion, with subsequent degradation of control by the dictator. The model is based on the following fundamental and general premises: a) the dictator governs aiming to follow the desired trajectory of development based only on the information from the advisors; b) the deception from the advisors cannot decrease in time; and c) the deception change depends on the difficulties the country encounters. The model shows effective control in the short term (a few months to a year), followed by instability leading to the country’s gradual deterioration of the state over many years. I derive some universal parameters applicable to all dictators and show that advisors’ deception increases parallel with the decline of the control. In contrast, the dictator thinks the government is doing a reasonable, but not perfect, job. Finally, I present a match of our model to the historical data of grain production in the Soviet Union in 1928-1940.

The Tinpot and the Totalitarian: An Economic Theory of Dictatorship

  • I use basic tools of economic theory to construct a simple model of the behavior of dictatorships. Two extreme cases are considered: a “tin-pot” dictatorship, in which the dictator wishes only to minimize the costs of remaining in power in order to collect the fruits of office (palaces, Mercedes-Benzes, Swiss bank accounts), and a “totalitarian” dictatorship, whose leader maximizes power over the population. I show that the two differ in their responses to economic change. For example, a decline in economic performance will lead a tin-pot regime to increase its repression of the population, whereas it will lead a totalitarian government to reduce repression. The model also shows why military dictatorships (a subspecies of tin-pots) tend to be short-lived and often voluntarily hand power over to a civilian regime; explains numerous features of totalitarian regimes; and suggests what policies will enable democratic regimes to deal with dictatorships effectively.

And maybe this one? The Ascendance Of Algorithmic Tyranny. Note the book it references – Seeing like a Platform: An Inquiry into the Condition
of Digital Modernity

  • As today’s platforms become all-powerful, the metaphors we use to describe our digitally infused world exemplify a new, stealthier form of domination that is emerging.

Transformers are Graph Neural Networks

  • We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for representation learning on graphs. We show how Transformers can be viewed as message passing GNNs operating on fully connected graphs of tokens, where the self-attention mechanism capture the relative importance of all tokens w.r.t. each-other, and positional encodings provide hints about sequential ordering or structure. Thus, Transformers are expressive set processing networks that learn relationships among input elements without being constrained by apriori graphs. Despite this mathematical connection to GNNs, Transformers are implemented via dense matrix operations that are significantly more efficient on modern hardware than sparse message passing. This leads to the perspective that Transformers are GNNs currently winning the hardware lottery.

Tasks

SBIRs

  • 9:00 standup – done
  • Ping T about rates – nope, she’s away this week.

Phil 7.24.2024

RE tax! – done, and scheduled for Dec 23, too

Put up my first Bluesky thread. Not sure if I did it right

I also wrote another thing! Need to submit this somewhere.

SBIRs

  • Set up the project folder structure and put together an initial config JSON file. Beginning prompt, token buffer size, and the number of steps. Maybe the number of UMAP dimensions? Or do we always produce 2d and 3d versions?
  • To processing tests to CSV files. That way we can look at them in the IDE
  • Got the structure set up and the config file read in
  • Need to do some BD as high priority

GPT Agents

  • Based on the chat with Jimmy, I loaded the (for me anyway) unreadable versions of Das Kapital into Notebook LM and used the following prompt:
    • Extrapolate to concept of workers and machines to generative AI which is trained on the output of writers (the workers) and can be used to produce mediocre writing without workers, and faster, high-quality writing with them. On one side, generative AI can replace workers, but will produce largely unoriginal content that will lose appeal over time. On the other, workers have access to a mechanical co-worker that can accelerate and often improve what they produce. Is the technology of generative AI inherently capitalist? If so, why? Provide alternative, egalitarian perspectives as well. Use the form of a white paper
  • Here’s the response:
    • Is the technology of generative AI inherently capitalist?
      • To address this question, this paper extrapolates from the sources’ concepts of workers and machines to the context of generative AI, which, analogous to a machine, is trained on the output of writers (the workers)
      • Similar to the machines described in the sources, generative AI can produce output (in this case, writing) without the involvement of writers once it is trained on their work12.
      • However, also similar to the sources’ depiction of machines, the output from generative AI is likely to be of higher quality when it is used as a tool by human workers134.
    • Capitalist Perspective:
      • The sources, focusing primarily on the dynamics of capitalist production, offer compelling arguments for why the technology of generative AI, within the framework of a capitalist system, could be considered inherently capitalist:
      • Exploitation of Labor: A core tenet of the sources is that capitalist production inherently seeks to extract surplus value from labor. In the context of generative AI, this dynamic could manifest through:
      • Replacement of Workers: Generative AI could potentially replace writers, particularly in producing low-quality, formulaic content, mirroring how machinery replaced skilled artisans in the sources456. This replacement allows capitalists to reduce labor costs and increase profits.
      • Intensification of Labor: Generative AI, even when used as a tool by writers, can lead to an intensification of work78. This intensification could take the form of pressure to produce more content in less time or to compete with the output of AI, ultimately benefiting the capitalist through increased productivity.
      • Control Over Production: The sources emphasize how machinery, under capitalist control, consolidates the power of capitalists over the production process459. This control extends to generative AI:
      • Ownership of AI: Capitalists who own the AI technology hold significant power. They control the data used to train AI, influence the types of content produced, and determine how the technology is implemented—all of which can be leveraged to maximize profits.
    • Alternative, Egalitarian Perspectives:
      • While the sources primarily focus on capitalist applications of machinery and labor, they also offer insights that can be extrapolated to imagine more egalitarian applications of generative AI:
      • AI as a Tool for Empowerment: Generative AI, when viewed not as a replacement but as a powerful tool, has the potential to empower writers1011. It can:
      • Increase Productivity: AI can handle tedious and repetitive writing tasks, freeing human writers to focus on more creative and engaging work.
      • Improve Quality: AI can offer suggestions, refine language, and identify errors, ultimately contributing to the creation of higher-quality content.
      • Democratization of Writing: One could envision a scenario where access to generative AI is not limited to capitalists. Open-source AI models and collaborative platforms could allow a wider range of individuals to participate in the creation and dissemination of written content, potentially fostering greater creative diversity and reducing the dominance of large corporations in media and publishing.
    • Conclusion:
      • While the capitalist application of technology is a central theme in the sources, it is crucial to remember that technology itself is not inherently capitalist. The sources highlight that the capitalist exploitation of labor arises from social relations, not from the tools themselves1213. Similarly, the impact of generative AI will ultimately depend on how it is developed, implemented, and controlled. If these processes are driven by a focus on collective benefit, shared ownership, and the democratization of knowledge and resources, then generative AI can become a powerful force for a more egalitarian future.