korrents

Our readingWhat is a korrent?

Longer test-time thinking improves an AI model's robustness to adversarial or unusual inputs.

Drawn from what Lilian Weng said

SubjectsLLMscybersecurityneural networks
What these subjects mean

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

neural networks The architecture almost all modern machine learning is built on, and what changes when it gets deeper.

What Lilian Weng actually said

  1. Lilian Weng Machine-learning researcher
    thinking for longer should be especially useful when the model is presented with an unusual input, such as an adversarial example or jailbreak attempt

    Where this was said

    ↗Why We Thinklilianweng.github.io

    1 May 2025

    All 3 korrents from this piecethis one is 2nd

Added to korrents 20 Sept 2026 · How quotes work · Something wrong? Tell us

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