EPISODE · Aug 20, 2025 · 57 MIN
2 | AI Reliability and Humans Testing Language Models (Anastasios Angelopolous of LM Arena) - - 20-AUG-2025
from Variance · host Arun Rao and Jake Kraft
How fast is AI really improving, and how do we know? What guarantees can we expect from AI systems to be robust and reliable? What is AGI and have we gotten there? Can AI systems show creativity or even sentience? Join Anastasios Angelopoulos as he lays out his thoughts to these hard questions, as he and his partners build the world's most sophisticated ways to test LLMs as they get better faster than everyone expects. Show Notes: Anastasios's Personal WebsiteConformal Prediction (Science of AI reliability)LM Arena (Humans testing LLMs)DeepSeek and DeepSeek R1
Embed this episode
NOW PLAYING
2 | AI Reliability and Humans Testing Language Models (Anastasios Angelopolous of LM Arena) - - 20-AUG-2025
No transcript for this episode yet
Similar Episodes
No similar episodes found.