shipfeedAI news, curated daily

01:23:10 CET
21 MAY01:23:10shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

OpenAI publishes research on an instruction hierarchy framework that trains LLMs to prioritise privileged instructions and resist prompt injection and jailbreak attacks.

Apr 19 · · primary fetch1 sourceupdated Apr 19 ·

Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comThe Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructionsprimary