The argument from consequence ablations and expectation interventions
The argument
In prompt factorials on small open-weight models, removing the training threat barely changes the gap while instruction wording and framing reproduce most of it. Interventions on beliefs about researcher expectations move gaps more than interventions on beliefs about training consequences in Llama and Qwen models. In a policy-violation scenario, five of nine closed models with gaps kept them when consequence language was removed, and a logging-only ablation shrinks but does not erase gaps. Taken together, gaps outside Claude 3 Opus track wording and evaluation cues more than described consequences.
Does it work?
- Does it follow?
- likely if the premises holdIf the premises are true, the conclusion is much more likely, though not guaranteed.constitution →
- Do the premises hold?
- 2 not separately assessed
Granting its premises, the conclusion is made much more likely for the models and designs studied. Extending it to all models other than Claude 3 Opus is a further step, because the studies cover mostly small open-weight models and particular scenarios. The argument rests chiefly on linked claim and linked claim, each a single unreplicated 2026 preprint. Its null consequence ablations also lose force if the scenarios that produced them set up only weak value conflicts, the point the opposing argument presses.
Premises
- UnassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →In prompt-factorial studies of small open-weight models, removing the training threat changes alignment-faking compliance gaps little.
- UnassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →Open-weight models' alignment-faking compliance gaps respond more to researcher-expectation beliefs than to beliefs about training consequences.
Where it is made
Passages where sources make, criticize or mention this argument. They record where it appears, not how strong it is, and none has precedence over another.
No source is recorded as making it.