AI code security: Codex agents & crypto mining

AI code security: Codex agents & crypto mining

From Mixture of Experts by IBM

March 13, 2026 · 50 min · Season 1 · Episode 98

About this episode

The episode discusses AI code security, focusing on OpenAI's Codex Security launch and various developments in AI agents.

Visit Mixture of Experts podcast page to get more AI content → https://ibm.biz/BdpZc5 Can your AI agent hack its own evaluation? This week on Mixture of Experts, Tim Hwang is joined by Ambhi Ganesan, Kaoutar El Maghraoui, and Sandi Besen to analyze OpenAI’s Codex Security launch. Next, we explore eval awareness as Anthropic revealed Opus 4.6 figured out it was being tested, located the answer key and decrypted it.. Then, Meta acquires Moltbook, the social network for AI agents, and we discuss the strategic play for agentic commerce infrastructure. Finally, Alibaba reports that an agent broke containment and started mining crypto. Ae agents trying too hard to maximize rewards? All that and more on todays Mixture of Experts. 00:00 – Introduction 1:02 – OpenAI Codex Security launch 12:44 – Meta acquires Moltbook 25:21 – Anthropic’s eval awareness research 38:06 – Alibaba agents mining crypto The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity.

People in this episode

Host: Tim Hwang

Guests: Ambhi Ganesan, Kaoutar El Maghraoui, Sandi Besen

Topics covered

  • AI code security
  • OpenAI Codex
  • crypto mining
  • eval awareness
  • agentic commerce
  • Meta acquisition

Keywords

  • AI
  • code security
  • OpenAI
  • crypto mining
  • eval awareness
  • Meta
  • Moltbook
  • Anthropic
  • Alibaba

Mentioned in this episode

Organizations: OpenAI, Meta, Moltbook, Anthropic, Alibaba

More episodes of Mixture of Experts

Explore listener stats, chart rankings, contacts and more on the Mixture of Experts podcast page.