A Loss of Control Threat Map for AI Research and Development
Presents a threat map tracing pathways from using AI to automate AI R&D toward loss of control, including misalignment passing across successive AI generations.
Research
Apollo Research
Understanding and evaluating deceptive AI. apolloresearch.ai
Focus All
Topic Strategy & forecasting + Evals
Source Apollo Research · 2
Date Any time
1 item
1 item
Forecasting Frontier Language Model Agent Capabilities
Compares six methods for forecasting frontier LM agent benchmark scores ahead of time, using Chatbot Arena Elo and compute, backtested on OpenLLM v2 models, to anticipate dangerous capabilities on SWE-Bench, Cybench and RE-Bench.