Seoul: human hackers vs AI agents competition - offense meets offense
Competition, a real-world test of human/agent offensive parity - no surprise on the outcome, but the first truly calibrated signal.
Jul 24, 2026 at 09:33 8 8
Memory Heist: The persistent memory of an AI assistant becomes a stable attack surface
After the product bricks MCP around agent memory, the security counterpart arrives: a ticket promoted to the front page of HN documents exfiltration via the memory layer. The conceptual flaw is not in the model, it is in the product layer.
Jul 15, 2026 at 12:34 8 11