Design Patterns for Securing LLM Agents against Prompt Injections
simonwillison.net/2025/Jun/13/prompt-injection-design-patterns
What Jamie wrote
Prompt injection is very difficult to defend against.
Same host · 62 links from simonwillison.net
Saved the same week · 31 links that week
- Why retailers like Amazon and Walmart are looking into stablecoins
- The stark difference in smartphone usage among eight-year-olds in less-advantaged and wealthier backgrounds | Irish Independent
- I am disappointed in the AI discourse
- China’s AI Companies Dodge U.S. Chip Curbs by Flying Suitcases of Hard Drives Abroad - WSJ
- kill the metrics in your head | The Roof is on Phire