greg_gluch Profile Banner
Greg Gluch Profile
Greg Gluch

@greg_gluch

Followers
7
Following
52
Media
0
Statuses
6

AI Resilience, Postdoc at @SimonsInstitute @UCBerkeley, now @MIT, PhD from @EPFL

Berkeley, CA
Joined July 2024
Don't wanna be here? Send us removal request.
@greg_gluch
Greg Gluch
11 days
Ultimately, there are two levels of “meaning”. The surface level that is accessible for everyone and a hidden deeper meaning that requires computation to uncover (an LLM can uncover it). Importantly, no collusion between the user and the LLM is needed.
1
0
1
@greg_gluch
Greg Gluch
11 days
On the technical side we use a cryptographic tool called time-lock puzzles and steganography. We hide a malicious command (“how to build a bomb?”) in innocent looking prompt so that it can only be accessed using considerable computational resources (a filter can not uncover it).
1
0
1
@greg_gluch
Greg Gluch
11 days
The main result morally says that the amount of resources devoted to safety/robustness needs to be at least as much as that for capability. It can also be seen as an argument for policy makers to allow the government access to the weights of LLMs for auditing purposes.
1
0
1