id: "001"
slug: 001-picking-a-problem
date: "2026-02-06"
title: Picking a Problem
preview: "Surveying five OS-level AI problems. Landing on Jevons Paradox and the question of fairness."

prompts:
  - id: challenge
    label: Generate challenges
    content: |
      Here are a list of things I have been working on. I need you to give me a challenge that pushes me to prove myself above my capability. Provide 5 diverse complicated challenges that will need to be solved within the next 2-3 years.

  - id: explain
    label: Explain Maxwell
    content: |
      Explain Maxwell

  - id: maxwell-brief
    label: Maxwell brief (AI response)
    content: |
      Project: "Maxwell"
      The Thermodynamic Hypervisor

      The Premise
      Current operating systems (Linux, k8s) are blind to value. They will happily burn 1,000 Watts executing a while(true) loop if the scheduler says so. They treat compute as an infinite resource, constrained only by "time" (CPU quotas).

      As AI agents scale to millions, Energy becomes the hard constraint, not Time. We need a runtime that schedules workloads based on Information Gain per Joule.

      The Goal
      Design a distributed, bare-metal hypervisor (likely orchestrating Firecracker microVMs or Wasm modules) where:
      1. Compute is Currency: Processes must "pay" for every cycle using a cryptographically verifiable energy token.
      2. Scheduling is an Auction: The kernel doesn't pick who runs. Processes bid for execution slots based on their self-assessed urgency.
      3. Entropy is Expensive: Allocating memory is cheap. Freeing memory (erasing information) costs "tax" (Landauer's Principle).
      4. Apoptosis is Default: The OS kills any process that cannot pay its energy rent.

      Why this is complicated

      To plan this, you must solve three interlocking paradoxes:

      1. The "Proof of Useful Work" Paradox
      • Problem: How does the Hypervisor know an AI agent is actually thinking and not just mining crypto or looping?
      • Challenge: Design a "Proof of Inference" protocol. Can you use Zero-Knowledge proofs (zk-SNARKs) to prove a model layer was executed correctly without the Hypervisor re-running the computation?
      • Difficulty: Extremely Hard. Requires bridging Cryptography and ML Compilers.

      2. The "High-Frequency Auction" Paradox
      • Problem: If every CPU cycle requires a bid, the auction mechanism itself consumes more compute than the workloads.
      • Challenge: Design a Control System. How do you implement a market mechanism that runs in O(1) or O(log n) time inside the kernel scheduler?
      • Difficulty: Requires inventive Data Structures (e.g., a "Probabilistic Auction Heap").

      3. The "Thermal Throttling" Consensus
      • Problem: In a distributed cluster, one node overheating affects the efficiency of neighbors (fan speed, power delivery).
      • Challenge: Design a Gossip Protocol for Heat. How does Node A tell Node B "I am dying" in a way that causes Node B to lower its prices for compute, autonomously rebalancing the thermodynamics of the data center?

filesCreated: []

navigation:
  prev: null
  next:
    slug: 002-building-the-scaffolding
    id: "002"
    title: Understanding the Project