2 | AI Reliability and Humans Testing Language Models (Anastasios Angelopolous of LM Arena) - - 20-AUG-2025 episode artwork

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

Episode metadata supplied by the publisher feed · Published Aug 20, 2025

Embed this episode

NOW PLAYING

2 | AI Reliability and Humans Testing Language Models (Anastasios Angelopolous of LM Arena) - - 20-AUG-2025

0:00 57:00

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Variance?

This episode is 57 minutes long.

When was this Variance episode published?

This episode was published on August 20, 2025.

Can I download this Variance episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!