TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Two-Faced AI Language Models Learn to Hide Deception

1 pointsby gigamaover 1 year ago

1 comment

gigamaover 1 year ago
&quot;Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive strategy, could we detect it and remove it using current state-of-the-art safety training techniques? To study this question, we construct proof-of-concept examples of deceptive behavior in large language models (LLMs).&quot;<p><a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2401.05566" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2401.05566</a>