Reactions
3 postsMT 
MTS@MTSliveIncoming UC Berkeley prof. @sayashk reveals AI reliability is improving 4–10X slower than capability and why 90% accuracy can still be catastrophic: "We came up with a list of metrics that other industries had used, industries like aviation and nuclear safety and so on. We…
- likes: 74
- replies: 5
- bookmarks: 26
- reposts: 6
MT MTS@MTSliveIncoming UC Berkeley prof. @sayashk says AI companies have spent billions on alignment while investing orders of magnitude less in agent control: "If you think about interventions on control, I would argue there have been orders of magnitude less investments." "Companies have…
- likes: 45
- replies: 4
- bookmarks: 16
- reposts: 5
MT MTS@MTSliveIncoming UC Berkeley prof. @sayashk says AI companies have spent billions on alignment while investing orders of magnitude less in agent control: "If you think about interventions on control, I would argue there have been orders of magnitude less investments." "Companies have…
- likes: 45
- replies: 4
- bookmarks: 16
- reposts: 5