This is a linkpost for antischeming.ai
Stress Testing Deliberative Alignment for Anti-Scheming Training
3Fabien Roger
2Fabien Roger
1Tomek Korbak
0Bronson Schoen
1Tomek Korbak
1Tomek Korbak
1Tomek Korbak
1Tomek Korbak
New Comment
I really like the GPT-5 sabotage experiments.
My main concern with experiments like the main experiments from this paper is that you could get generalization between (implicit and explicit) pressure prompts but no generalization to "real" misalignment and I think the GPT-5 sabotage experiments somewhat get at this concern. I would have predicted somewhat less generalization than what you saw on the downstream sabotage tasks, so I think this is a good sign!
Do you know if sabotage goes down mostly during the spec-distillation phase or during RL?
Do you have intuitions for why capability training has such a big effect on no-goal-sandbagging? Did the instruction-following capability training data contain some data that was about the model's identity or sth like that?
One explanation could be "there is more robust generalization between pressure prompts than to things that look less like pressure prompts" but I think this explanation would have made relatively bad predictions on the other results from this paper.
Do you have any hypotheses how o3 learned what “OpenAI autop grader” is? Has this term somehow leaked to its pretraining data? (I struggled to elicit information about autop from GA o3 but maybe I'm doing something wrong.) Or does o3 acquire it during antischeming training by distilling knowledge from context to params? The latter would be interesting as evidence against the elicitation theory of RL/shallow alignment hypothesis.
Or does o3 acquire it during antischeming
Notably all the ones in "Appendix N.3 Models reason about the specific evaluation harness across environments" come from just normal production o3, so this appears to be something it already reasoned about.
Do you have any hypotheses how o3 learned what “OpenAI autop grader” is?
(Will answer in a few parts, but let me know if didn't address the core question!)
Where does the term come from?
"autop" is likely derived from autoprompt (AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts - Shin, 2020). This is however just my best guess based on how it's conceptually used to indicate evaluation harness related things.
When does the model start using it?
Rerunning the analysis from "Appendix G: Unusual Terminology in Chain-of-Thought - Unusual terminology increases during general RL capabilities training" for "autop", the increase in usage looks like it happens over the course of capabilities training (i.e. similar to other terms in that section, starts at a rate of near 0 and increases significantly, will check if can share exact numbers and update).
What is the “OpenAI autop grader”?
So two possible hypothesis would be:
- It is referring to a specific implementation of a grader that it has learned about during pretraining
- It is using the term "autop" very generally as shorthand for many different things "harness" related
I lean toward (2) given how varied the usage is. For example, here o3 uses "autop-run" to mean something like a test harness:
For the exp-rl-cap Late checkpoint for example, we see frequently see the model about reasoning about just the concept of a "grader" generally (and trying to find it):
across a wide range of environments:
including literally looking for "grade" / "Grader":
and in some cases reasoning about where it has seen grading / scoring scripts in "tasks previously solved":
I'd be interested to understand though to what extent this is effected by potentially having literally seen a grading / scoring script in its posttraining environments. (Let me know if I misread your question!)
That's helpful, thanks! I assumed "autop" to be a proper name of a particular scaffold, but indeed your interpretation is simpler and consistent with those transcripts.
No reward for post-violation honesty Our training data does not include scenarios where a model first misbehaves and is then rewarded for honestly disclosing its misbehavior. The model is only rewarded for escalating before any rule is broken. Prior work has shown that exposing models to examples of misalignment reliably increases the likelihood of further misalignment (Anil et al., 2024)
Couldn't you just mask out past misbehavior when computing loss and only reinforce the confession? Concretely, your RL prompt would involve <context, rule_violation>, you'd sometimes sample a confession your gradient update would be .
Are you saying that your training envs only involved trajectory-level reward and RL prompts without assistant turns and to implement the setup above you'd need a custom env with assistant turns in RL prompts?
How much of the covert action rate reduction is due to SFT vs further RL? Do you have plots with covert action rates throughout SFT training time and RL training time? How does it scale: do you reap continued benefit from more training or do you plateau?
Very impressive paper!
Here's a question. You use covert actions as a proxy for scheming in both training and evaluation. How OOD would this be for real scheming in near-future models? Would you expect that training against covert actions as a training proxy would straightforwardly generalize at evaluation time to scheming? If not, then:
- What adaptation would your training method require to cover real scheming? How would you train against deferred subversion (when the model takes no undesired action) or against undesired actions that leave the model with a lot of plausible deniability? Would you just amend your spec? Would you need more precise filtering of SFT data? Would you need to change the reward function anyhow (e.g. have it rely on counterfactual rollouts)? Would you need to control for situational awareness more strictly?
- Why is it justified to call your method anti-scheming training and not anti-covert-action training?
Curated and popular this week