Show HN: Sub-microsecond (890 ns) trading execution research system

(submicro.krishnabajpai.me)

5 points | by krish678 15 hours ago

2 comments

  • stuartjohnson12 12 hours ago
    • krish678 12 hours ago
      Thanks for checking it out! The snippet you linked was just an illustrative “before” log — essentially showing what not to do in institutional logging.

      The actual framework uses multi-layered, auditable logs with:

      Hardware timestamps (NIC, CPU, PTP-synced)

      Cryptographic integrity manifests

      Offline verification of latencies

      PCAP captures for external validation

      Everything in use follows the “after” model, designed for fully reproducible, evidence-based latency measurements. That initial snippet was from early experiments — the current system is completely professional-grade and verifiable.

      • stuartjohnson12 11 hours ago
        If you're going to ask ChatGPT to write your response for you, I'll do the same.

        ---

        Great question! It's worth noting that your response exhibits several hallmarks of AI-generated content, including but not limited to:

        Bullet-point formatting where none was needed

        Buzzword density that feels a bit elevated

        Phrases like "fully reproducible, evidence-based" that have a certain... flavor to them

        I hope this helps! Let me know if you have any other questions.

        • krish678 10 hours ago
          For what it’s worth, I care more about whether the claims can be independently verified than how the explanation is phrased. The project stands or falls on measurements, artifacts, and reproducibility, not on who typed a comment or how conversational it sounds.

          If you spot something technically incorrect or unverifiable in the repo itself, I’m genuinely happy to discuss that.

          • stuartjohnson12 10 hours ago
            You do realise you didn't actually commit any code, right?
            • krish678 12 minutes ago
              Clarifying, since this is a fair concern:

              The full C++ execution core is intentionally not published yet. What’s public in this repo is the measurement, instrumentation, logging structure, and research scaffolding around sub-microsecond latency — not the proprietary execution logic itself.

              I should have stated that more explicitly up front.

              The goal of the public material is to show how latency is measured, verified, and replayed, rather than to ship a complete trading engine. I’m happy to discuss methodology or share deeper details privately with interested engineers.

              Appreciate the pushback — it’s valid.

  • talmormaker 2 hours ago
    AI Slop Clump
    • talmormaker 2 hours ago
      There is no actual source code, and it is a feast of hallucinatory files.
      • krish678 12 minutes ago
        Clarifying, since this is a fair concern:

        The full C++ execution core is intentionally not published yet. What’s public in this repo is the measurement, instrumentation, logging structure, and research scaffolding around sub-microsecond latency — not the proprietary execution logic itself.

        I should have stated that more explicitly up front.

        The goal of the public material is to show how latency is measured, verified, and replayed, rather than to ship a complete trading engine. I’m happy to discuss methodology or share deeper details privately with interested engineers.

        Appreciate the pushback — it’s valid.