Heidelberg AI News

Video · GitHub ·

Niels Provos on creating bcrypt, defending Google, and securing AI agents

In short

Niels Provos explains how durable security tools such as bcrypt, Google Safe Browsing, and HoneyD emerged from adversarial thinking, and why AI agents now require stronger controls against prompt injection and intent drift. The discussion matters to AI builders because current models can uncover long-hidden vulnerabilities, while deterministic policies, human review, and proof-of-exploit workflows are needed to deploy agents and maintain open-source software safely.

Key points

  • bcrypt has remained in use for about 28 years because its iteration cost can be increased as computing power grows.
  • Anthropic’s model found a 27-year-old OpenBSD vulnerability, showing that AI can uncover bugs missed for decades.
  • Project Iron Curtain converts plain-English rules into deterministic policies for controlling AI agents, but still requires human approval.
  • HoneyD’s virtual honeypots inspired agent honeypots designed to expose prompt injection and unauthorized data requests.
  • Google Safe Browsing protected more than 4 billion browsers by identifying malicious websites with large-scale machine learning.
  • AI-generated vulnerability reports need proof-of-concept exploits so maintainers can distinguish real issues from false positives.

Written by an AI model from the video’s captions and description.

Sit down with legendary cybersecurity researcher Niels Provos as he reflects on three decades of breaking, building, and securing software.

Watch on YouTube The opening of the article at youtube.com.

More from GitHub

All stories

VideoGitHub

The view from the labs: What's next for AI-assisted development

يناقش panel من Anthropic وOpenAI وGoogle Cloud وGitHub كيف تنتقل البرمجة بالذكاء الاصطناعي من المساعدة المباشرة إلى وكلاء مستقلين وأنظمة وكلاء تنفذ العمل بالكامل. تكمن القيمة القادمة في بناء أنظمة قابلة للتحقق، وتأمين هوياتها وصلاحياتها، وامتلاك الحكم البشري لتحديد ما ينبغي بناؤه ولماذا ومتى.

VideoGitHub

LangChain Deep Agents

The video introduces LangChain Deep Agents, an open-source framework that provides opinionated defaults and best practices for building agents with any model. It covers sub-agents, skills, memory, proactive behavior, decision models, safeguards, and cloud execution, explaining why these primitives matter for reliable long-running and personal agents.