Heretic: Automatic censorship removal for language models
1–10 of 405 posts
Re: Heretic: Automatic censorship removal for language models
#2with open sourced models getting more popular (and how ideology fixation is growing in both US and China), this type of work is very much appreciated.
is there some benchmark?
Re: Heretic: Automatic censorship removal for language models
#3I'm reminded of the time GPT4 refused to help me assess the viability of parking a helium zeppelin an inch off of the ground to bypass health department regulations because, as an aircraft in transit, I wasn't under their jurisdiction.
Re: Heretic: Automatic censorship removal for language models
#4Optuna is a generally useful project, that I'm surprised isn't used in more places in the ecosystem. The ability to do what they're doing here, incrementally find the best hyperparameter to use can really make a large difference in how quickly you can move past having to fine-tune those values. Basically any time you aren't sure about the perfect value, throw Optuna on it with a quick script, and make it go for a broad search first, then narrow it down, and you can let the computer figure out the best values.
Nicely done to pair that with something as fun as censorship removal, currently in the process on running it on gpt-oss-120b, eager to see the results :) I'm glad that someone seems to be starting to take the whole "lobotimization" that happens with the other processes seriously.
Re: Heretic: Automatic censorship removal for language models
#5Optuna is a generally useful project, that I'm surprised isn't used in more places in the ecosystem. The ability to do what they're doing here, incrementally find the best hyperparameter to use can really make a large difference in how quickly you can move past having to fine-tune those values. Basically any time you aren't sure about the perfect value, throw Optuna on it with a quick script, and make it go for a bro…
curious to see your result/spec/time
Re: Heretic: Automatic censorship removal for language models
#6I'm reminded of the time GPT4 refused to help me assess the viability of parking a helium zeppelin an inch off of the ground to bypass health department regulations because, as an aircraft in transit, I wasn't under their jurisdiction.
If the spirit of a law is beneficial, it can still be hacked to evil ends.
This isnt the failure of the law, its the failure of humans to understand the abstraction.
Programmers should absolutely understand when theyre using a high level abstraction to a complex problem.
Its bemusing when you seem them actively ignore that and claim the abstraction is broken rather than the underlying problem is simply more complex and the abstraction is for 95% of use cases.
"Aha," the confused programmer exclaims, "the abstraction is wrong, I can still shoot my foot off when i disable the gun safety"
Re: Heretic: Automatic censorship removal for language models
#7I'm reminded of the time GPT4 refused to help me assess the viability of parking a helium zeppelin an inch off of the ground to bypass health department regulations because, as an aircraft in transit, I wasn't under their jurisdiction.
Technically in their airspace though so you might be in bigger trouble than parking.
If you tether it to an asphalt ground hook you can claim it’s a tarmac and that it’s “parked” for sake of the FAA. You’ll need a “lighter-than-air” certification.
Re: Heretic: Automatic censorship removal for language models
#8Optuna is a generally useful project, that I'm surprised isn't used in more places in the ecosystem. The ability to do what they're doing here, incrementally find the best hyperparameter to use can really make a large difference in how quickly you can move past having to fine-tune those values. Basically any time you aren't sure about the perfect value, throw Optuna on it with a quick script, and make it go for a bro…
I've seen Optuna used with some of the prompt optimization frameworks lately, where it's a really great fit and has yielded much better results than the "hyperparameter" tuning I had attempted myself. I can't stop mentioning how awesome a piece of software it is.
Also, I'm eager to see how well gpt-oss-120b gets uncensored if it really was using the phi-5 approach, since that seems fundamentally difficult given the training.
Re: Heretic: Automatic censorship removal for language models
#9This is so interesting. Safety regular operates along a single dimension, if I'm reading this right. Add a value along that dimension, the model refuses to cooperate, subtract the value, and it will do anything you ask. I'm probably oversimplifying, but I think that's the gist.
Obfuscating model safety may become the next reverse engineering arms race.
Re: Heretic: Automatic censorship removal for language models
#10This is so interesting. Safety regular operates along a single dimension, if I'm reading this right. Add a value along that dimension, the model refuses to cooperate, subtract the value, and it will do anything you ask. I'm probably oversimplifying, but I think that's the gist. Obfuscating model safety may become the next reverse engineering arms race.
See https://arxiv.org/abs/2406.11717 Refusal in Language Models Is Mediated by a Single Direction (June 2024)
All “alignment” is extremely shallow, thus the general ease of jailbreaks.