Dan MacKinlay

The deep his­tory of intelligence

“Op­po­nent shap­ing” as a model for ma­nipu­la­tion and cooperation

• Dan MacKinlay 20 May 2025 23:01 UTC

  3 points

  0

  on: Selec­tive reg­u­lariza­tion for al­ign­ment-fo­cused rep­re­sen­ta­tion engineering

  Interesting! Ingenious choice of “color learning” to solve the problem of plotting the learned representations elegantly.
  This puts me in mind of the “disentangled representation learning” literature (review e.g. here). I’ve thought about disentangled learning mostly in terms of the Variational Auto-Encoder and GANs, but I think there is work there that applies to any architecture with a bottleneck, so your bottleneck MLP might find some interesting extensions there,
  I wonder: what is the generalisation of your regularisation approach to architectures without a bottleneck? I think you gesture at it when musing on how to generalise to transformers. If the latent/​regularised content space needs to “share” with lots of concepts, how do we get “nice mappings” there?

• Dan MacKinlay 20 May 2025 5:02 UTC

  1 point

  0

  on: Will Je­sus Christ re­turn in an elec­tion year?

  I’m enjoying envisaging this as an alternative explanation for the classic Lizardman’s Constant, which is a smidge larger than 3% but then, in cheap talk markets you have less on the line, so…

• Dan MacKinlay 12 May 2025 10:45 UTC

  1 point

  0

  in reply to: Sheikh Abdur Raheem Ali’s comment on: Sheikh Ab­dur Ra­heem Ali’s Shortform

  Ideally you would wish to calibrate your EV calcs against the benefit of a UAE AISI, though, no, not the expected budget? We could estimate the value of such an institute being more than the running cost (or, indeed, less) depending on the relative leverage of such an institute.