causal
Smarter Models Resist Prompt Injection
The latest generation of models have extensive post-training that makes them more resilient to prompt injection, so simple 'ignore all previous instructions' attacks no longer work and weak or cheap local models should be avoided because they are very gullible and easy to inject.
causalpending
Speaker
Peter SteinbergerEvidence Quote
“the latest generation of models has a lot of post-training to detect those approaches”
Created: 6/13/2026, 12:16:16 AM
Your notes
Loading notes...