Loading live stats
New Anthropic research: Natural Language Autoencoders.
Models like Claude talk in words but think in numbers. The numbers—called activations—encode Claude’s thoughts, but not in a language we can read.
Here, we train Claude to translate its activations into human-readable text.
| Tags | Top launches |
|---|---|
| Subject | AI |
| Colors | Colors sampled from the image |
| Posted | |
| Views | 2.5m+ |
| Spotted | |
| Curator | @baseddesigner |
