i should probably put tonepolice.py on github but it is quite limited and resource efficiency was not a goal, so:
- you have to manually train it on a hugo/jekyll/whatever blog
- it requires py3-transformers and CUDA
i should probably put tonepolice.py on github but it is quite limited and resource efficiency was not a goal, so:
- you have to manually train it on a hugo/jekyll/whatever blog
- it requires py3-transformers and CUDA
i was already somewhat dissatisfied with grammarly because they had started using LLM copyediting, which reduced the quality of some of my more recent articles
but the use of my likeness on software engineering content expert review feature was the last fucking straw
@whitequark you did not hear about this?
they trained on everyone's data and then started making suggestions in an "expert review" feature
so, for example, "Ariadne would say X about Y"
they did this to basically everyone who used grammarly who was notable
then they quickly backpedaled after they realized a lot of us are quite willing to sue