|
|
|
|
|
|
by webstrand
23 days ago
|
|
|
As a counterexample, I've been seeing more "safety rejections" from Claude. Unlike search, being unable to ask _anything_ about botulinum, or details about the recent Copy Fail vulnerability (without giving my fingerprints to Anthropic to become a "verified security researcher") we're only just beginning to see the ways LLM can be used to distort information and its availability. |
|
|