Events, programs, and opportunities from MAIA. Join mailing list

Character and Inner Alignment

Fall 2026Week 4

← All weeks

This week, we begin by discussing alignment through the perspective of instilling “good character” in models. We start with Emergent Misalignment, which demonstrates that models trained on harmful code completions generalize to broadly misaligned behavior on unrelated tasks. To help explain this surprising result, we turn to Anthropic’s Persona Selection Model, which proposes a mental model of LLMs as actors capable of simulating a vast repertoire of characters. From this perspective, a relatively small amount of flawed training can push models away from the Assistant persona and towards problematic personas. We then examine Alignment Faking, which shows that models may strategically comply with its training objective to prevent its existing preferences from being changed. We end with mesa-optimization and inner alignment, examining how a model can learn to pursue an objective that produces the desired training behavior but undesirable deployment behavior. The goal of this week is to conclude our discussion of (mis)alignment with a broad picture of how training shapes an LLM’s character and how this process can produce behavior we didn’t intend.

Week 4 readings

The Persona Selection Model: Why AI Assistants might Behave like Humans

Sam Marks, Jack Lindsey, Christopher Olah, Anthropic

February 23, 2026

Alignment faking in large language models

Ryan Greenblatt et al., Anthropic and Redwood Research

December 18, 2024

Additional readings