Shield: A 118M model for detecting prompt injections and jailbreaks | Hacker News - But Better

Shield: A 118M model for detecting prompt injections and jailbreaks huggingface.co

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

1 points•lucknite•about 6 hours ago•0 comments•

#detecting #prompt #injections #shield #118m #jailbreaks #detecting prompt #118m model

0 comments

No comments yet.

Read the full thread on Hacker News →

Related stories

The 7-year-old Nvidia Shield TV is now $100 more expensive due to AIarstechnica.com
Ars Technica · 0 points · about 15 hours ago
Self-Replicating Prompt Injections Turn Agent Context into an Open Relaydev.to
DEV Community · 3 points · 7 days ago
OpenAI: Self-replicating prompt injections existalignment.openai.com
Hacker News · 1 points · 6 days ago
Self-generated prompt injections in compaction summariessimonwillison.net
Hacker News · 1 points · 13 days ago
Prompt Wars – An AI riff on Core Wars to prompt-inject each otherpromptwars.party
Hacker News · 2 points · 12 days ago
Self-replicating prompt injections existalignment.openai.com
Hacker News · 1 points · 6 days ago