11–20 of 21 posts
I can't claim that I have any idea of how this model is built, but from their shifty excuses touching on "alignment" I'm confident that o1 is actually two copies of the same model, one "raw" and unchained that is fine-tuned for CoT, and one that has been crippled for safety and human alignment to parse that and provide the actual reply. They have finally realized how detrimental the "lobotomizing" process is to the m…
It also doesn't make sense intuitively, o1 isn't particularly good at creative tasks, and that's really the area where you'd think "censorship" would have the greatest impact, o1 is advertised as being "particularly useful if you’re tackling complex problems in science, coding, math, and similar fields."
openai is yahoo in ten years, change my mind
interesting...who will be Google in this case?
Some people at the top seriously need to be fired from Google. Working on advanced language models is all well and good, but not at the expense of maintaining the company's core competencies.
I can't claim that I have any idea of how this model is built, but from their shifty excuses touching on "alignment" I'm confident that o1 is actually two copies of the same model, one "raw" and unchained that is fine-tuned for CoT, and one that has been crippled for safety and human alignment to parse that and provide the actual reply. They have finally realized how detrimental the "lobotomizing" process is to the m…
I'm not convinced by your argument. If this was true we would expect the unofficial "uncensored" Llama 3 finetunes to outperform the official assistant ones, which as I understand it isn't the case. It also doesn't make sense intuitively, o1 isn't particularly good at creative tasks, and that's really the area where you'd think "censorship" would have the greatest impact, o1 is advertised as being "particularly usefu…
I also am not convinced by the argument but that is a poor reason against.
Earlier quoted context omitted.
I'm not convinced by your argument. If this was true we would expect the unofficial "uncensored" Llama 3 finetunes to outperform the official assistant ones, which as I understand it isn't the case. It also doesn't make sense intuitively, o1 isn't particularly good at creative tasks, and that's really the area where you'd think "censorship" would have the greatest impact, o1 is advertised as being "particularly usefu…
Uncensored finetunes aren't the same thing, that's taking a model that's already been lobotomised and trying to teach it that wrongthink is okay - rehabilitation of the injury. OpenAI's uncensored model would be a model that had never been injured at all. I also am not convinced by the argument but that is a poor reason against.
It's interesting that you weren't convinced by the above argument but still repeated the edgelord term "lobotomized" in your reply.
Earlier quoted context omitted.
Uncensored finetunes aren't the same thing, that's taking a model that's already been lobotomised and trying to teach it that wrongthink is okay - rehabilitation of the injury. OpenAI's uncensored model would be a model that had never been injured at all. I also am not convinced by the argument but that is a poor reason against.
I'm talking about taking the Llama 3 base model and finetuning it with a dataset that doesn't include refusals, not whatever you mean by "taking a model that's already been lobotomized". It's interesting that you weren't convinced by the above argument but still repeated the edgelord term "lobotomized" in your reply.
What is going on?!
I can't claim that I have any idea of how this model is built, but from their shifty excuses touching on "alignment" I'm confident that o1 is actually two copies of the same model, one "raw" and unchained that is fine-tuned for CoT, and one that has been crippled for safety and human alignment to parse that and provide the actual reply. They have finally realized how detrimental the "lobotomizing" process is to the m…
Earlier quoted context omitted.
I'm talking about taking the Llama 3 base model and finetuning it with a dataset that doesn't include refusals, not whatever you mean by "taking a model that's already been lobotomized". It's interesting that you weren't convinced by the above argument but still repeated the edgelord term "lobotomized" in your reply.
The claim is that llama is "lobotomized" because it was trained with safety in mind. You can't untrain that by finetuning. For what it's worth the non-instruct llama generally seems better at reasoning than instruct llama which i think is a point in support of OP.