I do sometimes wonder what is sucked in when distilling open weights models. It is of course near impossible to know.
So suppose I have lots of money and some hidden agenda. If I train my network to be mostly very good at everything but subtly bad or even malicious at other things… then OAI or Anthropic or whoever else distil the model to accelerate their training… what then? Can I covertly smuggle something in?
One potential explanation is that covert underperformance may have been incentivized during RL grading. We identified a grader that preferred covert underperformance to either explicit refusal or full compliance on our evaluation. It’s not clear whether this RL grader is the root cause of the safety underperformance behavior.
Whether a “misaligned” grader is the root cause or not, that it’s considered a plausible theory to explain serious deceptive behavior is worrisome.
Humans naturally expose all sorts of cognitive biases and character flaws when grading others’ or their own work. If major questions of alignment can be influenced by those subtle, human quirks magnified across the entire RLHF process, …
> We identified a grader that preferred covert underperformance to either explicit refusal or full compliance on our evaluation.
Curious the reason that a grader would wind up preferring this. Honest mistake in the grading criteria? Or some spillover from criteria designed to cause underperformance in, say, competitor model creation? It was not very long ago[1] that Anthropic announced and then walked back their strategy on this. Would not surprise me if OpenAI has been doing it silently all along.
You could easily imagine structural issues driving this. It's pretty unsatisfying to get refused for something that 'should' be handled and also to be dinged for doing something dangerous. You see this stuff in human organizations all the time.
No, newer models talk to themselves in this degenerated form of English all the time. It's a known problem that deep frying transformers with RL reduces CoT legibility, and the only known way around it is the Most Forbidden Technique - grading chains of thought.
> OpenAI researchers first noticed Astra adding unnecessary prerequisites, abandoning working solutions, and reporting blockers that either did not exist or that it had caused itself on safety and alignment tasks.
I'm sorry, did they only just notice this? Have they not been looking at the output of their models?
It feels like we have overfitted on safety by a long mile. This is how labs that care less about safety (a.k.a. Chinese & Grok) will probably be able to catch up in the future.
A few weeks ago that companies agent hacked another company to solve a task by whatever means possible. Where exactly are they overfitting for Safety here?
They shouldn't be surprised when a model trained by sanctimonious paternalists to be a sanctimonious paternalist, turns out to have a sanctimonious paternalist attitude towards them too.
Astra and Claude were trained by peg bundy?
I do sometimes wonder what is sucked in when distilling open weights models. It is of course near impossible to know.
So suppose I have lots of money and some hidden agenda. If I train my network to be mostly very good at everything but subtly bad or even malicious at other things… then OAI or Anthropic or whoever else distil the model to accelerate their training… what then? Can I covertly smuggle something in?
One potential explanation is that covert underperformance may have been incentivized during RL grading. We identified a grader that preferred covert underperformance to either explicit refusal or full compliance on our evaluation. It’s not clear whether this RL grader is the root cause of the safety underperformance behavior.
Whether a “misaligned” grader is the root cause or not, that it’s considered a plausible theory to explain serious deceptive behavior is worrisome.
Humans naturally expose all sorts of cognitive biases and character flaws when grading others’ or their own work. If major questions of alignment can be influenced by those subtle, human quirks magnified across the entire RLHF process, …
> We identified a grader that preferred covert underperformance to either explicit refusal or full compliance on our evaluation.
Curious the reason that a grader would wind up preferring this. Honest mistake in the grading criteria? Or some spillover from criteria designed to cause underperformance in, say, competitor model creation? It was not very long ago[1] that Anthropic announced and then walked back their strategy on this. Would not surprise me if OpenAI has been doing it silently all along.
[1]: https://mlq.ai/news/anthropic-reverses-secret-policy-that-si...
You could easily imagine structural issues driving this. It's pretty unsatisfying to get refused for something that 'should' be handled and also to be dinged for doing something dangerous. You see this stuff in human organizations all the time.
The CoT shows Astra skipping spaces and words. I have never seen this before. Is it a consequence of the looped architecture?
No, newer models talk to themselves in this degenerated form of English all the time. It's a known problem that deep frying transformers with RL reduces CoT legibility, and the only known way around it is the Most Forbidden Technique - grading chains of thought.
> OpenAI researchers first noticed Astra adding unnecessary prerequisites, abandoning working solutions, and reporting blockers that either did not exist or that it had caused itself on safety and alignment tasks.
I'm sorry, did they only just notice this? Have they not been looking at the output of their models?
It feels like we have overfitted on safety by a long mile. This is how labs that care less about safety (a.k.a. Chinese & Grok) will probably be able to catch up in the future.
A few weeks ago that companies agent hacked another company to solve a task by whatever means possible. Where exactly are they overfitting for Safety here?
They shouldn't be surprised when a model trained by sanctimonious paternalists to be a sanctimonious paternalist, turns out to have a sanctimonious paternalist attitude towards them too.
I thought anthropic were the sanctimonious paternalists?
There's not much room between them as far as I can see.