dmm: (Default)
Dataflow matrix machines (by Anhinga anhinga) ([personal profile] dmm) wrote2024-05-24 10:26 am
  • Previous Entry
  • Add Memory
  • Share This Entry
  • Next Entry
Entry tags:
  • large language models,
  • understanding internals of ai

Golden Gate Claude

I think humans tend to have these idée fixes:

www.anthropic.com/news/golden-gate-claude

A pretty interesting example of conversation by a very experienced interlocutor:

www.lesswrong.com/posts/cxuzALcmucCndYv4a/daniel-kokotajlo-s-shortform#hyXAiafwbwfEPiX5Q


  • 5 comments
  • Post a new comment
Flat | Top-Level Comments Only
dmm: (Default)

no subject

[personal profile] dmm 2024-05-27 03:43 pm (UTC)(link)
Zvi comments: https://www.lesswrong.com/posts/JdcxDEqWKfsucxYrk/i-am-the-golden-gate-bridge
  • Thread
  • Reply to this
  • Thread from start
  • Parent
  • Thread
  • Hide 1 comment
  • Show 1 comment
dmm: (Default)

no subject

[personal profile] dmm 2024-06-03 01:28 pm (UTC)(link)
Another set of comments: https://www.lesswrong.com/posts/zzmhsKx5dBpChKhry/comments-on-anthropic-s-scaling-monosemanticity
  • Thread
  • Reply to this
  • Thread from start
  • Parent

  • 5 comments
  • Post a new comment
Flat | Top-Level Comments Only

[ Home | Post Entry | Log in | Search | Browse Options | Site Map ]