Mais que fais l'Europe au juste ? L'europe et L’AI Act exige une documentation complète sur la transparence, des résumés des données d'entraînement, des tests de red-teaming, des plans de gestion des risques, des filtres pour les droits d’auteur, et des audits de cybersécurité
SAFETY
-
Reverse Engineering System Prompts: 45 Posts Guide
By
–
Reverse engineering system prompts is one of the best ways I know of to level up at prompt engineering – here's my collection of 45 posts on the topic dating all the way back to the Microsoft Bing prompt leak in February 2023
-
MCP servers security risks: protecting user data from theft
By
–
Right now users are being encouraged to mix and match MCP servers in a way that makes it trivial for people to steal their data – we are unfairly outsourcing decisions on how to stay secure to people who haven't got a fighting chance of staying safe
-
Flawed AI Security Mitigations Encourage Inherently Insecure Systems
By
–
When it comes to security I think flawed mitigations are actually harmful, because they encourage developers to build systems that are inherently insecure and can never be made safe for their users There are a LOT of things being built right now that should not be built
-
Prompt Injection Vulnerabilities Harder to Fix Than SQL Injection
By
–
If I report a SQL injection vulnerability to a product they can reliably fix it and close the security hole If I report a prompt injection vulnerability they can't
-
LLM Safety: Why Current Development Approaches Are Insufficient
By
–
That's the whole problem. We are developing software against LLMs in the same way we use SQL: we write our own instructions as a programmer, then we combine them with input from our users With SQL we can do that safely. With LLMs we can't
-
Prompt Injection Filter Risks vs Spam Filter Consequences
By
–
That only works if the damage caused by the occasional attack getting through the filter is acceptable A spam filter missing an email = you see one spam email in your inbox A prompt injection filter missing an attack could = now your private data has been stolen
-
Design Patterns Securing LLM Agents Against Prompt Injections
By
–
I like the way this "Design Patterns for Securing LLM Agents against Prompt Injections" paper puts it: https://
simonwillison.net/2025/Jun/13/pr
ompt-injection-design-patterns/#scope-of-the-problem
… -
LLM Security: Token Injection Risks and Tool Access Control
By
–
I have yet to see any truly credible protection for this, and I've been looking! You have to assume that anything that can get tokens into your LLM system will be able to trigger any tool that system has access to
-
Half-billion views: AI blurs reality and fiction globally
By
–
This video has received half a billion views on TikTok. It appeared in newspapers such as the German magazine “Der Spiegel” and caused a worldwide scare: it was the moment when literally almost a billion people realized that they could no longer separate reality and fiction, AI… https://t.co/uzBAQijP89
— Chubby♨️ (@kimmonismus) 31 juillet 2025This video has received half a billion views on TikTok. It appeared in newspapers such as the German magazine “Der Spiegel” and caused a worldwide scare: it was the moment when literally almost a billion people realized that they could no longer separate reality and fiction, AI