Alignment pretraining: AI discourse creates self-fulfilling (mis)alignment (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Alignment pretraining: AI discourse creates self-fulfilling (mis)alignment

First screen, captured 5 months ago.

Looks similar

Screenshot of arxiv.org: LLMs corrupt your documents when you delegate

LLMs corrupt your documents when you delegate (arxiv.org)

454 points by rbanffy 5 months ago | 177 comments

arXiv paper introducing DELEGATE-52, a benchmark showing LLMs corrupt about 25% of document content during long delegated editing workflows.

llm delegate-52 benchmark document-editing

Screenshot of arxiv.org: AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insights

AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insights (arxiv.org)

309 points by laurex 5 months ago | 163 comments

Screenshot of arxiv.org: LLMorphism: When humans come to see themselves as language models

LLMorphism: When humans come to see themselves as language models (arxiv.org)

60 points by okey 5 months ago | 39 comments

Screenshot of arxiv.org: Self-Distillation Enables Continual Learning [pdf]

Self-Distillation Enables Continual Learning [pdf](arxiv.org)

78 points by teleforce 5 months ago | 20 comments

Screenshot of arxiv.org: Self-Adapting Language Models

Self-Adapting Language Models (arxiv.org)

210 points by archon1410 1 year ago | 61 comments

Screenshot of arxiv.org: Antagonistic AI

Antagonistic AI (arxiv.org)

65 points by drcwpl 2 years ago | 38 comments