Hacker News
- A single rogue token can erase production in 43 ms https://mercurialsolo.substack.com/p/no-safe-words 0 comments
Linked pages
- [2303.11366] Reflexion: an autonomous agent with dynamic memory and self-reflection https://arxiv.org/abs/2303.11366 189 comments
- AI Risk Management Framework | NIST https://www.nist.gov/itl/ai-risk-management-framework 38 comments
- Adding payments to your LLM agentic workflows | Stripe Dot Dev Blog https://stripe.dev/blog/adding-payments-to-your-agentic-workflows 2 comments
- GitHub - NVIDIA/NeMo-Guardrails: NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. https://github.com/NVIDIA/NeMo-Guardrails 1 comment
- GitHub - guardrails-ai/guardrails: Adding guardrails to large language models. https://github.com/guardrails-ai/guardrails 0 comments
- [2503.13657] Why Do Multi-Agent LLM Systems Fail? https://arxiv.org/abs/2503.13657 0 comments
Related searches:
Search whole site: site:mercurialsolo.substack.com
Search title: No Safe Words - by Barada Sahu - Notes for the Future
See how to search.