The Decoderbreakthroughsafety16m agoenergy 137
Is AI interpretability close to a breakthrough? A new essay has researchers divided
image: The Decoder
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.
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.