cd/entity/safety-research/false-facts· home› entities› safety-research/false-facts

grep -l @safety-research/false-facts /news/*.json | wc -l → 1

safety-research/false-facts

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

19:22

2026-05-26

lesswrong.com

large-language-models

Practical Learnings from Synthetic Document Finetuning

Apollo Research researchers have identified practical refinements to Synthetic Document Finetuning (SDF), a knowledge editing technique that implants beliefs into AI models by training them on LLM-gen…

// co-occurs with top 3 entities

Apollo Research 1 Claude Sonnet 4.6 1 Slocum et al. 1

// topics top 4 topics

large language models 1 ai research 1 ai safety 1 machine learning 1