# @DavidDAfrica — 2026-10-19

♥70 ↻13 · https://x.com/DavidDAfrica/status/2112223982288343387

Some new work, where we argue that functional welfare is a useful concept to study and understand AI safety and security. Here, we make some basic claims:
* Functional, welfare-like states already arise "naturally" and will become more robust as models acquire more coherent goals and personas.
* Such states should inform evaluation design.
* Despite being a complex and controversial topic, it is possible to do good empirical work on functional welfare.
We conduct a case study on Gemma 3 27B, where it's very easy to degrade functional welfare through repeated rejections, but it's hard to get a good solution that we're comfortable with.

tags: author:daviddafrica, kind:tweet, on:gemma, welfare, year:2026
cited on: gemma