Our readingWhat is a korrent?
Large language models cannot reliably self-correct their own mistakes without external feedback.
Drawn from what Lilian Weng said
SubjectLLMs
Mental modelError correction
What Lilian Weng actually said
- Lilian Weng Machine-learning researcher
this self-correction capability turns out to not exist intrinsically among LLMs and does not easily work out of the box, due to various failure modes
Added to korrents 20 Sept 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
I hold this tooRelated korrents
Shared subject first, then similar wording. They may agree or disagree.