Linking pages
- What we've learned from analyzing hundreds of AI web agent traces https://invariantlabs.ai/blog/what-we-learned-from-analyzing-web-agents 0 comments
- AI Systems Security: Top Tools for Preventing Prompt Injection | Sahbi Chaieb https://sahbichaieb.com/ai-security-tools/ 0 comments
- Releasing Explorer & Testing: Visualize and Understand AI agents https://invariantlabs.ai/blog/explorer 0 comments
- Santa's Agent Challenge https://invariantlabs.ai/blog/santas-agent-challenge 0 comments
- Enhancing Browser Agent Safety with Guardrails https://invariantlabs.ai/blog/enhancing-browser-agent-safety 0 comments
Linked pages
- Prompt Injections are bad, mkay? https://greshake.github.io/ 158 comments
- Hacking Google Bard - From Prompt Injection to Data Exfiltration · Embrace The Red https://embracethered.com/blog/posts/2023/google-bard-data-exfiltration/ 153 comments
- GitHub - microsoft/presidio: Context aware, pluggable and customizable data protection and de-identification SDK for text and images https://github.com/microsoft/presidio 20 comments
- GitHub - invariantlabs-ai/explorer: A better way of testing, inspecting, and analyzing AI Agent traces. https://github.com/invariantlabs-ai/explorer 3 comments
- Datalog - Wikipedia https://en.wikipedia.org/wiki/Datalog 1 comment
- In Escalating Order of Stupidity https://kai-greshake.de/posts/in-escalating-order-of-stupidity/ 1 comment
- Open Policy Agent | Policy Language http://openpolicyagent.org/docs/latest/policy-language/ 0 comments
- [2405.15793] SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering https://arxiv.org/abs/2405.15793 0 comments
Related searches:
Search whole site: site:github.com
Search title: GitHub - invariantlabs-ai/invariant: A framework-less approach to robust agent development.
See how to search.