Jarrah Bloomfield

About

I work on security at Anthropic, previously at Google. I care about using information security to have a positive impact on the world.

Security

• 🔐 Information Security in High-Impact Areas — 80,000 Hours career review
• 🖥️ Retbleed Explainer — an accessible breakdown of the CPU vulnerability
• 🛡️ Demystifying Zero Trust — what it actually means
• 🍩 Donutting is Bad — why the "unlocked computer" prank has hidden costs

Games

• 🧑‍🍳 Too Many Cooks — a party deduction game for 2-6 players (Buy: 🇺🇸 / 🇦🇺)
• 👖 Know Your Pants — crack the dress code
• 🃏 Blind Play — an advanced Hanabi convention
• 🎯 Priority Order — a simple Hanabi convention that works

Everything Else

• 💃 Downfall of Paris — an animated guide to an English Country Dance
• 🦘 Australian Slang — words the world needs
• 🇦🇺 Australian Citizenship Test — practice questions (2/2 pass rate)
• 🍞 Celiacs Don't Need to Live in Fear — a risk-based approach to managing celiac disease

Acknowledgements

• Frontier Safety Framework — Google DeepMind, 2024
• The Capacity for Moral Self-Correction in Large Language Models — Anthropic, 2023
• Constitutional AI: Harmlessness from AI Feedback — Anthropic, 2022
• Toy Models of Superposition — Anthropic, 2022
• Red Teaming Language Models to Reduce Harms — Anthropic, 2022
• Language Models (Mostly) Know What They Know — Anthropic, 2022

Links