Nathaniel Mitrani Hadida

Identifiers

• name variant Nathaniel Mitrani Hadida 0.60 · backfill

Papers (2)

1. Behavioural Analysis of Alignment Faking cs.AI · 2026 · author #1
2. Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks cs.AI · 2026 · author #1

Mentions

• 2605.27681 #1 · arxiv_oai · confidence 0.70 Nathaniel Mitrani Hadida
• 2601.23086 #1 · arxiv_oai · confidence 0.70 Nathaniel Mitrani Hadida

Frequent Coauthors

• Alan Cooney 1 shared papers
• Cameron Tice 1 shared papers
• David Williams-King 1 shared papers
• Puria Radmard 1 shared papers
• Rhea Karty 1 shared papers
• Sassan Bhanji 1 shared papers