alt Hacker NewsWhat do you think those tokens are used for?
Distillation attacks aren't about replacing the entire pretraining dataset with questionably sourced synthetics. It's all about post-training.
Train your own base model - but tune it off Claude output to make it perform more in line with Claude. Yoink the products of Anthropic's expensive SFT, RLHF and RLVR work for yourself by training on the outcomes.
The post-training datasets are small, but they are what controls the final model behavior.
Replies
How does yoinking outputs from from prior generation Claude model and post raining on them result in a model competitive with the latest generation? That doesn't add up - nevermind Anthropic hasbeen summarizing thinking tokens since January to counter distillation.
> Train your own base model - but tune it off Claude output to make it perform more in line with Claude
Is that actually genuine distillation though? Distillation suggests the core model is being pre-trained using output from another model. For the above to work, you have to already have all the core intelligence trained into your base model.
If distillation just comes down to post-training then it's tantamount to admitting that the Chinese base models are just as good as frontier US lab models. Because you can't post-train frontier intelligence into a model. It has to be there in the base. Then you can change how that intelligence is expressed through post-training.