Viewing profile — bloep

You'd need something Spotify. Another similar possibility might be to do more RL with this data, e.g. using upside-down RL. One can possibly steer this with user feedback as well.

What I had in mind was kind of like a reward model that is trained by on longer outputs that have a very high similarity to training examples. Something similar has been done to pr…

There are quite simple tricks to avoid repetition/copying in NNs, e.g. by (1) training a model to predict the "popularity" of the main model's outputs and penalizing popular/copied…

Indeed, there is lots of denial or ignorance in this thread (ignorance in the technical sense). AudioLM already produced impressive results and it's a tiny fraction of what is alre…

Modern ThinkPads are unfortunately also not very repairable. Replacing the USB-C port on the X1 Carbon is a 1 hour Job. The RAM is soldered on. Replacing the keyboard requires disa…