sammatuba

ESSAY · PROJECT 0003

Misalignment is measured, not assumed

Dataset the ARENA 3.0 curriculum (TARA vault submodule, pinned 81533b2) + the TARA Learning Plan v2 · Charts 0 · Written SEP 2026

Entry 11 of the ARENA guide. Part 4.2, science of misalignment. Route position: program week 10, tagged [core], API-only (ARENA prices the part around $10 of API budget). Reading thread: Wang et al., persona features control emergent misalignment.

The mental model

Chapter 3 built instruments; chapter 4 points them at alignment questions and treats

the answers as science: hypotheses, experiments, replications. This part runs two of

the field's live experiments on real models through your own pipeline. Shutdown

resistance: give a model a task, then a shutdown instruction, and measure what it

does when finishing the task and obeying the instruction conflict. Alignment

faking: give a model a scratchpad and a training setup that threatens its values,

and look for the signature pattern of complying now while preserving the option to

defect later.

The frame that makes this science rather than anecdote is in the exercises' shape:

system-prompt variants are the experimental conditions, the main experiment loop is

the trial harness, and the replication exercises connect your numbers to published

ones. A result you cannot reproduce on your own API key is a rumor; this week's job

is turning two famous results into numbers you own.

The exercises

Quoted from the pinned 4.2 page, with ARENA's own budgets:

What it unlocks

The capstone's evaluation claims will be judged by exactly this standard: conditions,

controls, replications. The route also lands the research-intent amendment window

here, with the pilot environment smoke tests one week behind and the proposal gate

two weeks ahead; alignment-science fluency is what makes the intent's design

defensible in front of a mentor.

Budget and receipts

ARENA's budgets sum to roughly 1.5–2.5 hours plus API spend (ARENA's cost note for

4.2 is about $10). The route keeps the part API-only: no GPU appears anywhere in it.

[TODO: receipts — hours vs budget, API spend, shutdown-control and alignment-faking results, what broke (fill from the TARA vault when the week closes)]

PREVIOUS Control assumes the model is trying to fool you · NEXT Week 12 is a fork, and either road is one session long · GUIDE HOME