Model Behavior Insights
Riley discusses the significant advancements in handling exponential divergence in AI models, highlighting how they can now think for extended periods without getting stuck on incorrect paths. Nathan raises questions about model resilience and jailbreaking techniques, while Riley contrasts the behaviors of OpenAI's models with Claude, noting how the latter can become more assertive when challenged repeatedly.In this clip
From this podcast
Interconnects Audio
Interviewing Riley Goodside on the science of prompting
Related Questions