cd/entity/Qwen3-32B-FP8· home› entities› Qwen3-32B-FP8
grep -l @qwen3-32b-fp8 /news/*.json | wc -l → 1

Qwen3-32B-FP8

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

05:28
2026-08-13
lesswrong.com
ai-safety

LLMs have the capacity for self-imposed steganography

A BlueDot Impact Technical AI Safety project demonstrated that large language models (LLMs) can be trained to perform steganography, embedding hidden information in their outputs to evade monitoring. …

// co-occurs with top 5 entities
BlueDot Impact 1 Llama-3.1-8B-Instruct 1 MMLU-Pro 1 Redwood Research 1 inspect framework 1
// topics top 3 topics
ai safety 1 large language models 1 ai research 1