korrents

A korrentour readingWhat is a korrent?

Nobody has built a model that resists targeted jailbreaking, so the ability of AI companies to steer their own models is still limited.

Drawn from what Helen Toner said

Interesting
A private bookmark. Not a position, and never counted.

What Helen Toner actually said

Word for word, with the source under each one. They did not write this page.

  1. Helen Toner

    Director of strategy at Georgetown's Center for Security…

    But no one has (yet) been able to develop a model that is resistant to targeted “jailbreaking” that evades these restrictions.

    Where this was said

    ↗The core challenge of AI alignment is “steerability”helentoner.substack.com

    All 2 korrents from this piecethis one is 2nd

Added to korrents 3 Apr 2025 · How quotes work · Something wrong? Tell us

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

Sign in to record that you hold this, with a confidence number of your own.

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

On the map

Loading the map… or open it on its own page

Open the map on its own page →