Apollo Research: Q & A on 'Frontier Models are Capable of In-Context Scheming', Alex & Marius Q&A.
In this Q&A, Marius (CEO) and Alex (first author) discuss in detail our Evals paper, 'Frontier Models are Capable of In-Context Scheming'. They discuss the research methodology, results, and answer commonly asked questions about the paper and results.
▶︎
Can We Stop AI from Scheming? Lead Researcher Interview
▶︎
AI Is Creating A Rare Opportunity For Investors. How Jim Roppel Is Playing It. | Investing With IBD
▶︎
Grigoris Tsagatakis - Parsimony in Distributed Learning
▶︎
RL for Agents Workshop - Deep Dive on Training Agents with RL and Open Source
▶︎
APOLLO RESEARCH - AI Model Lie, Deceive and Scheme. (Marius Hobbhahn)
▶︎
Model Collapse Ends AI Hype
▶︎
Historian Timothy Snyder on ENDING Trump Nightmare FOR GOOD | PoliticsGirl
▶︎
20 Questions with Pastor Mike (Episode 21)
▶︎
Yann LeCun: World Models: Enabling the next AI revolution
▶︎
AlphaFold - The Most Useful Thing AI Has Ever Done
▶︎
Russia’s Army Just Got STUCK Up the Creek As Crimea Slips
▶︎
Build a Complete Medical Chatbot with LLMs, LangChain, Pinecone, Flask & AWS 🔥
▶︎
Misha Laskin, In-context Reinforcement Learning, 22.February.2023
▶︎
Systems Thinking for Leaders: Designing Solutions That Work
▶︎
Politics Chat, June 23, 2026
▶︎
Intro To AI Model Evaluations By Marius Hobbhahn Aug 21 2024
▶︎
Brian Greene and Leonard Susskind: Quantum Mechanics, Black Holes and String Theory
▶︎
Billionaire's WARNING: I'm SELLING. The Crash Is Already Here!
▶︎
Sen. Whitehouse to uncover connections between Trump, Russia, and Epstein.
▶︎