Aleksandr Bowkis* and David Africa* TL;DR * Chain of thought (CoT) monitorability may be fragile, and natural language autoencoders (NLAs) may provide a helpful, decorrelated monitoring surface. * We tried to read NLAs from the monitor itself, where the NLA readout surfaces what the monitor internally represents while judging an...
Executive Summary Summarisation is one approach to oversight of automated research: a non-scheming agent distils insights from a large body of research into an informative short summary for a human overseer. We investigate a toy setting for this: translation of synthetic languages. A strong summariser model infers a synthetic language’s...
Summary This is a summary of a paper published by the alignment team at UK AISI. Read the full paper here. AI research agents may help solve ASI alignment, for example via the following plan: * Build agents that can do empirical alignment work (e.g.~writing code, running experiments, designing evaluations...