Building High-Performance AI Engineering Teams with Mike Conover, Co-founder & CEO of Brightwave
Deployed: The AI Product Podcast
Complexity of Defining Goodness
Understanding what is considered 'good' requires individuals to develop an internal model shaped by societal expectations, which is inherently complex. This complexity challenges the capacity of language models (LLMs), as they excel at identifying typical patterns rather than discerning insightfulness or surprise. Evaluating goodness can be broken down into specific criteria, such as factual entailment and grammatical coherence, which are more aligned with the capabilities of LLMs. Recognizing the limitations of LLMs is vital; they can address certain sub-characteristics that indicate insightful analysis but cannot grasp the broader, nuanced concept of what is genuinely 'good.'
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
