Search for a command to run...
Kathleen Fisher and Byron Cook explore how formal methods and AI can work together to create more secure software systems, demonstrating how automated reasoning and proof techniques can help address emerging cybersecurity challenges and potentially enable a "great software rewrite" that dramatically reduces vulnerabilities.
An in-depth exploration of the critical AI security crisis, revealing how current AI systems are vulnerable to prompt injection and jailbreaking attacks, and why existing guardrails are ineffective as AI agents gain more power to take real-world actions.
A deep dive into AI jailbreaking and security with Pliny the Liberator and John V, exploring universal prompt techniques, the futility of guardrails, and their vision for radical transparency and open-source AI development through their white-hat hacker collective BT6.