News for hackers. Stuff that matters.
Re:Anthropic announces Claude 2.1 – 200k context, less refusals by sitkack on Tuesday November 21, 2023 @03:06PM (#38369329)
It has problems summarizing papers because it freaks out about copyright. I then need to put significant effort into crafting a prompt that both gaslights and educates the LLM into doing what I need. My specific issue is that it won't extract, format or generally "reproduce" bibliographic entries.

I damn near canceled my subscription.

Re:Anthropic announces Claude 2.1 – 200k context, less refusals by fragmede on Tuesday November 21, 2023 @05:37PM (#38371451)
Right? I'm all for it not being anti-semetic but to run into the guard rails for benign shit is frustrating enough to want the guard rails gone.