No. There is no link. But crucially, they have given you modern source-code for the entire thing. You should be able to use an LLM agent to produce a similar tool. And the diversity of such tools may well restore diversity of textual conversation.
I read it as it's an in-house tool used at theconsensus.dev for labeling articles in their feed, because using Pangram on every article would cost too much.
No. There is no link. But crucially, they have given you modern source-code for the entire thing. You should be able to use an LLM agent to produce a similar tool. And the diversity of such tools may well restore diversity of textual conversation.
I don't see the source code, where did you find that?
[Edit] Or are you implying that readers should direct an LLM at the entire article and expect an equivalent tool to be produced
Haha, yes, the latter. The textual description is the critical source code. Here, it tells you that you:
* compare pre-LLM and post-LLM writing using 2023 as your index year
* create some 100+ fixed rules rather than a sophisticated model
* use a fixed threshold to kill
I read it as it's an in-house tool used at theconsensus.dev for labeling articles in their feed, because using Pangram on every article would cost too much.
That's right.
going with something low-tech and gamable is better imo - pangram would flag the good stuff too and cause collateral damage