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.

Come down a rabbit hole with OpenAI o1 system card

1 pointsby roh26it5 months ago

1 comment

roh26it5 months ago
The most interesting findings (at least from my perspective) - OpenAI measured "honesty" that could become an interesting model eval others should adopt. - Using instruction heirarchy to _avoid_ prompt injections - When pushed to pursue misaligned goals, it tried to disable oversight in 5% of tests!