Dexa
/
Interconnects Audio
Learn more
Follow
Model Refusals Analysis
Nathan delves into testing model capabilities and the system's refusal patterns. Despite attempts to jailbreak the system, clear refusal patterns emerge, hinting at underlying safety filters.
Add to Radar
Share
In this clip
Nathan Lambert
From this podcast
Interconnects Audio
DBRX: The new best open LLM and Databricks' ML strategy
Related Questions
How are prompts used in AI models as discussed in the episode How to Use ChatGPT as a Copilot for Learning - Ep. 4 with Nathan Labenz and the clip Effective Prompting Techniques?