News for hackers. Stuff that matters.
Re:Show HN: Llama 3.3 70B Sparse Autoencoders with API access by cbg0 on Tuesday December 24, 2024 @01:59AM (#42500165)
Quite a lot of whataboutisms and straw men in your post, let's stick to LLMs, as that was the original topic.
Re:Show HN: Llama 3.3 70B Sparse Autoencoders with API access by echelon on Tuesday December 24, 2024 @02:03AM (#42500174)
It's contextualization, not a logical fallacy.

Let's stop treating LLMs as spooky.

Re:Show HN: Llama 3.3 70B Sparse Autoencoders with API access by ben_w on Tuesday December 24, 2024 @10:38AM (#42502566)
Lots of things that aren't spooky are yet dangerous. Matches, for example. Scissors. Covid and A-10 Warthogs.