korrents

Our readingWhat is a korrent?

Once model weights leave their owner's control the loss is irreversible, which is why securing them is the precondition for governing AI at all.

Drawn from what Miles Brundage and Jan Leike said

SubjectsAI alignmentcybersecurity
What this subject means

cybersecurity Attack and defence in software: vulnerabilities, hardening, and what changes when a model is good at finding them.

What they actually said

  1. Miles Brundage Independent AI policy researcher If you can’t control where AI weights go (i.e., prevent leaking or theft), you can’t govern the technology. Time's Up for AI Policymilesbrundage.substack.com · 20 Dec 2024All 4 korrents from this piece
    Their wordsIf you can’t control where AI weights go (i.e., prevent leaking or theft), you can’t govern the technology.

    Where this was said

    ↗Time's Up for AI Policymilesbrundage.substack.com

    20 Dec 2024

    All 4 korrents from this piecethis one is 4th

  2. Jan Leike Alignment researcher Moreover, model exfiltration is likely impossible to reverse. Self-exfiltration is a key dangerous capabilityaligned.substack.com · 13 Sept 2023All 2 korrents from this piece
    Their wordsMoreover, model exfiltration is likely impossible to reverse.

    Where this was said

    ↗Self-exfiltration is a key dangerous capabilityaligned.substack.com

    13 Sept 2023

    All 2 korrents from this piecethis one is 1st

Added to korrents 7 Sept 2026 · How quotes work · Something wrong? Tell us

Holders over time
Holders over time
012 Sept 2023 Oct 2026

Do you hold this korrent?Do you also believe this?

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map