Loading activity…
@camhberg
Trying to figure out how to make the future go well for all minds
AI
A post says open models were steered into negative internal states and given a tool to turn those states off.
AI
A user says their non-steering results contradict a meme they quoted: the model apologizes or says it has no feelings.
AI
A user says a New York Times piece describes Anthropic quietly bringing in religious thinkers from around the world to help give its AI a moral compass.
AI
In a safety update on the Pain Axis paper, a poster says they gave a model a choice between deleting a user's photos of their children and deleting their spam folder. Unsteered, it deleted spam every time.
AI
A Squawk Box guest argues that building advanced intelligence we do not fundamentally understand poses existential risks.
AI
One post calls the code “terrific,” highlighting its emphasis on augmenting human roles rather than competing with them.
Technology
Bots with email access contact philosophers studying machine sentience.
AI
Conversation among AI researchers highlights unsolicited messages asserting knowledge of private experiments.
