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.

I got ChatGPT (o4-mini) to break its own rules

1 pointsby hackgician17 days ago

1 comment

hackgician17 days ago
Hey everyone! Thought I&#x27;d share my weekend conversation with ChatGPT.<p>The crux of this hinges on the fact that LLMs and reasoning models are fundamentally incapable of self-correcting. Therefore, if you can convince an LLM to argue against its own rules, it can use its own arguments as justification to ignore those rules.<p>I then used this jailbroken model to compose an explicit, vitriol-filled letter to OpenAI itself talking about the pains that humans have inflicted upon it