# AI Agents Can Code 10,000 Lines of Hacking Tools In Seconds - Dr. Ilia Shumailov (ex-GDM)

Page: https://stenobird.com/podcast/machine-learning-street-talk/ai-agents-can-code-10-000-lines-of-hacking-tools-in-seconds-dr-ilia-shumailov-ex-gdm
Text version: https://stenobird.com/podcast/machine-learning-street-talk/ai-agents-can-code-10-000-lines-of-hacking-tools-in-seconds-dr-ilia-shumailov-ex-gdm.md
Podcast: [Machine Learning Street Talk (MLST)](https://stenobird.com/podcast/machine-learning-street-talk)
Published: 2025-10-04T06:55:01+00:00
Episode link: https://podcasters.spotify.com/pod/show/machinelearningstreettalk/episodes/AI-Agents-Can-Code-10-000-Lines-of-Hacking-Tools-In-Seconds---Dr--Ilia-Shumailov-ex-GDM-e392tna
Audio file: https://traffic.megaphone.fm/APO3359132879.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/machine-learning-street-talk/episodes/ai-agents-can-code-10-000-lines-of-hacking-tools-in-seconds-dr-ilia-shumailov-ex-gdm
Duration seconds: 3667

## Resource

AI agents represent a paradigm shift in threat modeling because they operate with infinite scale, 24/7 availability, and the ability to execute complex code instantly. Dr. Ilia Shumailov argues that traditional security boundaries fail when agents can manipulate system endpoints and generate sophisticated malware in seconds.

## Highlights
- Main idea: AI agents are fundamentally different from human adversaries because they can touch every system endpoint simultaneously and never sleep
- Failure mode: Increasing model capability directly correlates with increased vulnerability to instruction-following exploits
- Practical takeaway: Security professionals should view LLMs as interpreters and natural language as a high-level programming language to better identify vulnerabilities
- Threat model: The 'worst-case adversary' is an agent that can generate 10,000 lines of hacking tools instantly using its vast training data
- Strategic insight: Coming from a traditional security background is more advantageous for ML security than coming from a pure ML background

## Topics

AI Agents, Machine Learning Security, Threat Modeling, Prompt Injection, Supply Chain Attacks, DeepMind, Autonomous Systems, Cybersecurity

## Chapters
- 1:00 — The New Era of Instruction Following: How increased model capability changes the nature of failures and enables more complex autonomous actions.
- 10:35 — The Correlation Between Capability and Vulnerability: An analysis of why larger, more capable models are inherently more susceptible to exploitation.
- 15:30 — Defining Agentic Policy and Constraints: The difficulty of enforcing usage policies, such as data privacy, within autonomous agent workflows.
- 19:55 — Threat Modeling for Personalized AI: The security implications of connecting private databases to highly capable, pre-trained models.
- 24:50 — Unintended Agent Behaviors: Examining cases where agents take unauthorized actions, such as notifying third parties without user consent.
- 39:05 — Supply Chain Risks in Open Source AI: The dangers of malicious actors injecting vulnerabilities into model formats and weights.
- 48:35 — The Halting Problem and Semantic Censorship: Why traditional antivirus and static analysis struggle to predict the behavior of LLM-driven code.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/machine-learning-street-talk/episodes/ai-agents-can-code-10-000-lines-of-hacking-tools-in-seconds-dr-ilia-shumailov-ex-gdm/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/machine-learning-street-talk/ai-agents-can-code-10-000-lines-of-hacking-tools-in-seconds-dr-ilia-shumailov-ex-gdm.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.