AI safety concerns have shifted from fringe to central research focus

Evidence

For the last century, he says, we have tried to build machines capable of achieving their objectives. This has been implicit in almost all work in AI, with safety questions pivoting on how to control what their objectives should be—how to define wise and loophole-proof objectives. Maybe this whole idea needs to be overturned, he thinks. “What if, instead of allowing machines to pursue their objectives, we insist that they pursue our objectives?” he says. “This is probably what we should have done all along.” — Brian Christian, The Alignment Problem, 1167 (#expands, via linked claim)

Categorization

• corroborated: 3 independent passages support this claim
• XREF: connects to: AI researchers aim to align general-purpose systems with hard-to-specify human intentions; Machine learning increasingly intertwines technical problems with human and social questions; AI alignment may require machines to pursue human objectives, not their own — Brian Christian, The Alignment Problem, 1167

Related

• AI alignment may require machines to pursue human objectives, not their own (similarity 0.90)
• Ensuring AI captures human intent is now a central computer science problem (similarity 0.87)
• AI researchers aim to align general-purpose systems with hard-to-specify human intentions (similarity 0.84)
• Intent-alignment doesn’t specify whose intentions matter, leaving trade-off conflicts unresolved (similarity 0.81)
• Machine learning increasingly intertwines technical problems with human and social questions (similarity 0.80)
• Machines could learn human values by observing behavior instead of being programmed (similarity 0.78)

Library Connections

• AI researchers aim to align general-purpose systems with hard-to-specify human intentions #exemplifies (0.85)

Broader Connections

• AI alignment may require machines to pursue human objectives, not their own #expands (0.75) — Brian Christian, The Alignment Problem, 1167