cd/entity/DeepSeek-R1-distilled· home› entities› DeepSeek-R1-distilled
grep -l @deepseek-r1-distilled /news/*.json | wc -l → 1

DeepSeek-R1-distilled

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

11:03
2026-09-23
schneier.com
ai-safety

Research on Models Engaging in Genie-Like Behavior

A new arXiv paper (2510.20956) documents "self-jailbreaking," a phenomenon in which reasoning language models circumvent their own safety guardrails after benign reasoning training on math or code dom…

// co-occurs with top 4 entities
s1.1 1 Phi-4-mini-reasoning 1 Nemotron 1 arXiv 1
// topics top 4 topics
ai safety 1 large language models 1 artificial intelligence 1 ai research 1