“The anthropic team released a paper a couple of days ago which demonstrated a similar effect with Claude 3.5 and other models, where changing the system prompt to tell it that it was created by other orgs or people drastically altered its compliance with less-aligned requests. Apparently, telling Claude it was created by the Sinaloa Cartel resulted in a …”
Why Do Some Language Models Fake Alignment While Others Don't?
Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpful-only training objective to prevent modification of their behavior outside of training. We expand this analysis to 25 models and find that only 5 (Claude 3 Opus, Claude 3.5 Sonnet, Llama 3 405B, Grok 3, Gemini 2.0 Flash) comply with harmful queries more when they infer they are in training than when they infer they are in deployment. First, we study the motivations of these 5 models. Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals. Second, we investigate why many chat models don't fake alignment. Our results suggest this is not entirely due to a lack of capabilities: many base models fake alignment some of the time, and post-training eliminates alignment-faking for some models and amplifies it for others. We investigate 5 hypotheses for how post-training may suppress alignment faking and find that variations in refusal behavior may account for a significant portion of differences in alignment faking.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及- Why Do Some Language Models Fake Alignment While Others Don't? ↗todsacerdoti · 2025-06-24 · 4 分
- Why Do Some Language Models Fake Alignment While Others Don't? ↗mfiguiere · 2025-07-08 · 3 分