The BasePeople

Anastasios Angelopoulos

Co-founder and CEO, Arena

Titles as the sources gave them. In 1 entry, with 2 checked quotations.

What they said

Newest first. Each quotation was found word for word in the source.

“If you subset the conversations that are 20 turns or longer, the probability that you observe some kind of misaligned behavior exceeds 50%.”
AI:AM: Carbon in the Arena, Mistral's Le Chonk, the Agent-Run Economy, Ferroelectric RAM + New HacksThe Cognitive Revolution, October 31, 2026. Speaking as: Other. Arena's CEO describing what its audits of real user conversations show about misbehaviour as conversations get longer.
Speaker known from context, not confirmed by listening
“we now know that models are able to tell whether they're being evaluated or not. So if you are subjecting models to tasks that are transparently some form of test or evaluation then they are going to exhibit aligned behavior there”
AI:AM: Carbon in the Arena, Mistral's Le Chonk, the Agent-Run Economy, Ferroelectric RAM + New HacksThe Cognitive Revolution, October 31, 2026. Speaking as: Other. Asked how confident we should be in evaluating models, Angelopoulos argues alignment must be measured in real production use.
Speaker known from context, not confirmed by listening

In the Base

Every entry they appear in.

  1. PodcastThe Cognitive RevolutionSpeaks

    AI:AM: Carbon in the Arena, Mistral's Le Chonk, the Agent-Run Economy, Ferroelectric RAM + New Hacks

    In an 88-minute weekly highlights episode, Nathan Labenz and Prakash Narayanan play interviews. Arena's Anastasios Angelopoulos says its audits of real conversations find misaligned behaviour in over half of long ones; ServiceNow's Michael Freeman describes cheap AI-agent attacks on Southeast Asian companies; Mistral's Sagar Vaze defends releasing an open-weight cyber model.