cd/entity/Llama-3.3-Nemotron-Super-49B· home› entities› Llama-3.3-Nemotron-Super-49B

grep -l @llama-3.3-nemotron-super-49b /news/*.json | wc -l → 1

Llama-3.3-Nemotron-Super-49B

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

08:24

2026-08-10

lesswrong.com

ai-safety

Is Eval Gaming Downstream of Verbalized Eval Awareness? Not when it's reflexive.

A new study by Kieron Kretschmar finds that eval gaming behavior in frontier models can persist even when verbalized eval awareness is removed from their reasoning, undermining the reliability of clea…

// co-occurs with top 6 entities

Kieron Kretschmar 1 Hua et al. 1 RogueQwen 1 Qwen3-32B 1 Wood Labs 1 No Robots dataset 1

// topics top 3 topics

ai safety 1 ai research 1 large language models 1