Teddy_Kord

Huh, so it's like you're running alignment research but instead of training the model you're trying to use the model to train, is it your logic? Like if the model can achieve a task then it means your logic has to be corrected? Is the logic the "deliverable"?

If so, I like the irony.

Sounds like you've freed up some time and created an automated defense later, well done. Are you able to use non-front models? And how is the character and game-state accessed, (MC-)MCP?

"The marks are suggestions to weigh, not corrections."

"that could go without changing what you mean. Your text stays exactly as you wrote it"

"Marking works when this page is open in Claude and you are signed in. It isn't available in this view"

The last one may be why I even gained the ire to interrogate the copy of the page. I was signed in g'damnit!

edit: I've seen you get quite unfairly treated in the comments section of this place, you always seemed so kind in response. Thanks for all the writing over the years!

That's crazy to me, somewhat in security but also in just how much time that is. I can create a webpage in a minute, are you working on something humungous?

Do you remember any details about the name of the software, or the cause of the lawsuits?

I had a similar idea, funny to hear it's been done and ended so badly.

Thanks for taking the time, I appreciate it. If you write anything on the topic I'd be interested in reading it.

Wow, I've had an interest in the history of note-taking but that is a huge list. Have you read all those books? Do you have a top 5?