Make AI solve it

Use weaker models to supervise and provide a feedback signal to stronger models.

Build formal and empirical frameworks where AIs supervise other (stronger) AI systems via structured interactions; construct monitoring tools which enable scalable tracking of behavioural drift, benchmarks for self-modification, and robustness guarantees

Make open AI tools to explain AIs, including AI agents. e.g. automatic feature descriptions for neuron activation patterns; an interface for steering these features; a behaviour elicitation agent that "searches" for a specified behaviour in frontier models.

In the limit, it's easier to compellingly argue for true claims than for false claims; exploit this asymmetry to get trusted work out of untrusted debaters.

Train LLMs to the predict the outputs of high-quality whitebox methods, to induce general self-explanation skills that use its own 'introspective' access