Tag Archives: philosophy

Phil 12.6.2025

Time, space, memory and brain–body rhythms

  • Time and space are crucial concepts in neuroscience, because our personal memories are tied to specific events that occur ‘in’ a particular space and on a ‘timeline’. Thus, we seek to understand how the brain constructs time and space and how these are related to episodic memory. Place cells and time cells have been identified in the brain and have been proposed to ‘represent’ space and time via single-neuron or population coding, thus acting as hypothetical coordinates within a Newtonian framework of space and time. However, there is a fundamental tension between the linear and unidirectional flow of physical time and the variable nature of experienced time. Moreover, modern physics no longer views space as a fixed container and time as something in which events occur. Here, I articulate an alternative view: that time (physical and experienced) is an abstracted relational measure of change. Physical time is measured using arbitrary units and artificial clocks, whereas experienced time is linked to a hierarchy of brain–body rhythms that provide a range of reference scales that reflect the full span of experienced time. Changes in body and brain circuits, tied to these rhythms, may be the source of our subjective feeling of time.

Neurophysiology of Remembering

  • By linking the past with the future, our memories define our sense of identity. Because human memory engages the conscious realm, its examination has historically been approached from language and introspection and proceeded largely along separate parallel paths in humans and other animals. Here, we first highlight the achievements and limitations of this mind-based approach and make the case for a new brain-based understanding of declarative memory with a focus on hippocampal physiology. Next, we discuss the interleaved nature and common physiological mechanisms of navigation in real and mental spacetime. We suggest that a distinguishing feature of memory types is whether they subserve actions for single or multiple uses. Finally, in contrast to the persisting view of the mind as a highly plastic blank slate ready for the world to make its imprint, we hypothesize that neuronal networks are endowed with a reservoir of neural trajectories, and the challenge faced by the brain is how to select and match preexisting neuronal trajectories with events in the world.

If I’m reading this right, bias is a function of neurophysiological alignment. Which is wild, but makes sense

Tasks

  • Email to hotel – done
  • Chores – done
  • Laundry – done
  • Groceries – done
  • And a COLD, short ride.

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.