-
Their words
it's it's literally we're looking at neurons in the model's brain that light up when prompt injection happens. So the model won't even tell you but we can actually see those neurons and we can figure out and diagnose that it's happening. And then you combine that with the auto mode classifier and with these three layers we just cannot demonstrate prompt injection anymore.
Related posts
Jeff Geerling Site
NTP, an atomic clock, and having a great time at the world's largest VCF
The the words it uses that this site has seen least often elsewhere. Posts are matched on those words alone — nothing here is a summary of this one.
Top people
Showing Profile →
Hiding
Hiding
27 July
1 July
-
Their words
we're accumulating code faster than we're accumulating trust and that sense of trust comes from me struggling to understand some domain concept I get it. I represent it in the code. I have I write tests that demonstrate that I really did understand it. And now I trust my program.
16 June
15 April
-
Their words
Nvidia's computing stack is the best performance per TCO in the world, bar none. Nobody can demonstrate to me that any single platform in the world today has better performance TCO ratio. Not one company.
7 April
-
Their words
So, as seniors, I figure it behooves us to demonstrate not just how to use these tools effectively, but how to figure out how to use these tools effectively, cuz that's a whole different set of skills.
26 October 2023
-
Their words
Despite evaluations, we cannot consider coming powerful frontier AI systems "safe unless proven unsafe". With current testing methodologies, issues can easily be missed. Additionally, it is unclear if governments can quickly build the immense expertise needed for reliable technical evaluations of AI capabilities and societal-scale risks. Given this, developers of frontier AI should carry the burden of proof to demonstrate that their plans keep risks within acceptable limits.
31 December 2022
-
Their words
Easier said than done, but one of the best ways to prove you’re not a predictive language model is to demonstrate critical and sophisticated thinking.
13 July 2022
1 January 2009
Nothing matches.
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.