In the small but growing literature on supervised document finetuning, its typical to finetune "post-trained" models on synthetic facts (see Alignment faking, Wang et al., Lessons from Two-Hop Reasoning) 

To me, the more natural thing is "synthetic continued pretraining" - further training the base model on synthetic documents (mixed with pretraining data), then applying post-training techniques (this is the approach used in Auditing language models for hidden objectives nvm they apply SDF to post-trained model, then apply further post-training)

I'm sort of confused why more papers aren't doing synthetic continued pretraining. I suspect its some combination of a) finetuing post-trained models is easier and b) people have tried both and it doesn't make much of a difference. 

But if its mostly a) and not really b), this would useful to know (and implies people should explore b more!)

I wish there was a bibTeX functionality for alignment forum posts...

I'm pretty happy with modeling SGD on deep nets as solomonoff induction, but seems like the key missing ingredient is path dependence. What's the best literature on this? Lots of high level alignment plans rely on path dependence (shard theory, basin of corrigibility...) 

Maybe the best answer is just: SGD is ~local, modulated by learning rate. But this doesn't integrate lottery ticket hypothesis stuff (which feels like it pushes hard against locality)

maybe research fads are good? 

disclaimer: contrarian take that I don't actually believe, but marginally updates me in favor of fads

Byrne Hobart has this thesis of "bubbles as coordination mechanisms" (*disclaimer, have not read the book). 
If true, this should make us less sad about research fads that don't fully deliver (e.g. SAEs) - the hype encourages people to build out infrastructure they otherwise wouldn't that ends up being useful for other things (e.g. auto-interp, activation caching utils)

So maybe the take is "overly optimistic visions are pragmatically useful", but be aware of operating under overly optimistic visions, and let this awareness subtly guide prioritization. 

Note this also applies to conceptual research - I'm pretty skeptical that "formalizing natural abstractions" will directly lead to novel interpretability tools, but the general vibe of natural abstractions has helped my thinking about generalization. 

Clarifying the relationship between mechanistic anomaly detection (MAD), measurement tampering detection (MTD), weak to strong generalization (W2SG), weak to strong learning (W2SL), and eliciting latent knowledge (ELK). (Nothing new or interesting here, I just often loose track of these relationships in my head)

eliciting latent knowledge is an approach to scalable oversight which hopes to use the latent knowledge of a model as a supervision signal or oracle. 

weak to strong learning is an experimental setup for evaluating scalable oversight protocols, and is a class of sandwiching experiments

weak to strong generalization is a class of approaches to ELK which relies on generalizing a "weak" supervision signal to more difficult domains using the inductive biases and internal structure of the strong model. 

measurement tampering detection is a class of weak to strong generalization problems, where the "weak" supervision consists of multiple measurements which are sufficient for supervision in the absence of "tampering" (where tampering is not yet formally defined)

mechanistic anomaly detection is an approach to ELK, where examples are flagged as anomalous if they cause the model to do things for "different reasons" then on a trusted dataset, where "different reasons" are defined w.r.t internal model cognition and structure. 

mechanistic anomaly detection methods that work for ELK should also probably work for other problems (such as backdoor detection and adversarial example detection)

so when developing benchmarks for mechanistic anomaly detection, we both want to test methods against methods in standard machine learning security problems (adversarial examples and trojans) that have similar structure to scalable oversight problems, against other elk approaches (e.g. CCS), and against other scalable oversight approaches (e.g. debate)

I’ve been running a safety grad student reading group, and feeling like it would be healthier / more productive to have concrete metrics or deliverables.

My tentative idea to incorporate LW / Alignment Forum posting as a core component of the group (with karma as a metric). I’m not exactly sure on the structure, but something like:

• Reading week (everyone reads the same set of papers / blog posts, discuss thought
• Writing week: everyone prepares comment / shortform / post, then we trade and revise writers-workshop style
  • this also provides filtering (avoid spamming LW with bad comments) and maybe makes people feel more comfortable/confident about posting public writing

would love feedback, and curious if anyone has tried stuff like this. 

(Another nice feature of this is it increases the odds of getting people hooked on LW, which imo should be a top priority for safety field-building, c.f. https://www.lesswrong.com/posts/ke24kxhSzfX2ycy57/simon-lermen-s-shortform?commentId=HqQsNdp4bdp4nDn7G)

does anyone have thoughts on how to improve peer review in academic ML? From discussions with my advisor, my sense is that the system used to depend on word of mouth and people caring more about their academic reputation, which works in a fields of 100's of researchers but breaks down in fields of 1000's+. Seems like we need some kind of karma system to both rank reviewers and submissions. I'd be very surprised if nobody has proposed such a system, but a quick google search doesn't yield results. 

I think reforming peer review is probably underrated from a safety perspective (for reasons articulated here - basically bad peer review disincentivizes any rigorous analysis of safety research and degrades trust in the safety ecosystem)

I’ve been thinking a little more about the high-level motivation of measurement tampering, and struggling to think through when measurement tampering detection itself is actually going to be useful for mitigating x-risk. Like is human/ai feedback considered a robust measurement device? If no, then what is the most alignment relevant domain MTD could be applied to. If yes, do the structural properties of measurement that supposedly make it easier then general ELK still hold?

Is the move of a lot of alignment discourse to Twitter/X a coordination failure or a positive development? 

I'm kinda sad that LW seems less "alive" than it did a few years ago, but also seems healthy to be engaging in a more neutral space with a wider audience

One confusion I have with MAD as an approach to ELK is that it seems to assume some kind of initial inner alignment. If we're flagging when the model takes actions / makes predictions for "unusual reasons", where unusual is define with respect to some trusted set, but aligned and misaligned models are behaviorally indistinguishable on the trusted set, then a model could learn to do things for misaligned reasons on the trusted set, and then use those same reasons on the untrusted set. For example, a deceptively aligned model would appear aligned in training but attempt take-over in deployment for the "same reason" (e.g. to maximize paperclips), but a MAD approach that "properly" handles out of distribution cases would not flag take over attempts because we want models to be able to respond to novel situations. 

I guess this is part of what motivates measurement tampering as a subclass of ELK - instead of trying to track motivations of the agent as reasons, we try to track the reasons for the measurement predictions, and we have some trusted set with no tampering, where we know the reasons for the measurements is ~exactly that the thing we want to be measuring. 

Now time to check my answer by rereading https://www.alignmentforum.org/posts/vwt3wKXWaCvqZyF74/mechanistic-anomaly-detection-and-elk