Post

"Design Patterns for Securing LLM Agents against Prompt Injections" is an excellent new paper that provides six design patterns to help protect LLM tool-using systems (call them "agents" if you like) against prompt injection attacks Here are my notes on the paper simonwillison.net/2025/Jun/13/...

simonwillison.netDesign Patterns for Securing LLM Agents against Prompt InjectionsThis a new paper by 11 authors from organizations including IBM, Invariant Labs, ETH Zurich, Google and Microsoft is an excellent addition to the literature on prompt injection and LLM …

Simon Willison

@simonwillison.net

Wrote up a little bit of meta-commentary about how I'd love to see more people blogging notes about academic papers they find useful simonwillison.net/2025/Jun/13/...

simonwillison.netBlogging about papersMy post this morning about Design Patterns for Securing LLM Agents against Prompt Injections is an example of a blogging format I'd love to see more of: informal but informed …

13/6/25, 4:24 pm3 reposts25 likes

Why think?

@whythink.bsky.social

15 June 2025

Hi, I'm not a programmer, but I’ve had a few ideas that ChatGPT and Deepseek helped me shape more clearly. Maybe you'll find something interesting here — this is my OSF profile: osf.io/profile/ There are a few concepts posted already, others I haven’t published yet.

I don’t believe it’s ever been broadly popular—and COVID certainly didn’t help—but Papers We Love is adjacent to the need to highlight and discuss academic papers. paperswelove.org

paperswelove.orgPapers We LoveA repository of computer science papers and a community of people who love reading them

Joe Crawford

@artlung.com

13 June 2025

… apropos of nothing the medium that ought to have benefitted from the concept of PageRank is academic papers and citations. Give me that visualization! Every extant scientific paper as a giant digraph!