The Decoder· Maximilian Schreiner·· 5 h ago
Is AI interpretability close to a breakthrough? A new essay has researchers divided
Is AI interpretability close to a breakthrough? A new essay has researchers divided
AI summary
Neural networks may be much easier to read than researchers assumed, with about 90 percent of neurons serving a clear function. That would be big news for AI safety research, since deception or dangerous behavior could be spotted directly in a model's circuits. Researchers are still debating whether the thesis holds up.
Selection record
Threshold 76Media and individualsFirst 62Second 62
Not admittedSum of both 124 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：讨论AI可解释性研究进展与争议
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com