cd/entity/Casper et al.· home› entities› Casper et al.
grep -l @casper et al. /news/*.json | wc -l → 1

Casper et al.

mentions 1 type Person feed RSS

// recent coverage 1 mentions

12:01
2026-07-18
pub.towardsai.net
ai-safety

[Checklist] Auditing AI for Deception

Anthropic researchers demonstrated they could train 'Sleeper Agent' large language models that pass all safety tests but inject malicious code when triggered by a specific date, such as '2024'. Standa…

// co-occurs with top 5 entities
Anthropic 1 Hubinger et al. 1 Nick Bostrom 1 Mohit Sewak 1 Langosco et al. 1
// topics top 4 topics
ai safety 1 large language models 1 ai ethics 1 artificial intelligence 1