#Prompt工程

共 37 篇带此标签

37 articles Newest 2026-10-26
Archive · #Prompt工程 11 articles
Opinion

Why LLM Outputs Are Hard to Understand

A practical framework for evaluating whether AI Agent outputs are understandable enough to support diagnosis, decision-making, and action. The approach draws on an arXiv paper and its Hacker News discussion.

2026-10-25 Source 2026-10-24 6 min 250 views
Case Studies

Abliterated LLMs Face Greater Prompt Injection Risk

Project Discovery tested an abliterated LLM in a Nuclei template workflow and found that it produced more usable output while becoming more vulnerable to instructions embedded in target data. Security tools should enforce permission boundaries rather than rely on model refusals.

2026-10-21 Source 2026-10-19 7 min 250 views
Case Studies

Hidden WhatsApp Instructions Target LLM Support Agents

Researchers found instructions hidden in WhatsApp help pages that may steer LLM support agents away from regulatory guidance and external escalation options. The risk extends beyond manipulated answers to incorrect business actions and weakened compliance decisions.

2026-10-21 Source 2026-10-19 7 min 250 views