Re:Can a Linear Program Do Weight-Space Programming?
by theptip on Wednesday November 11, 2026 @06:28PM
(#50460471)
Astra was directly editing the weight, ie modifying the values without backprop.
It’s a bit conflated because the paper covered a bunch of experiments.
The early experiments did read/write the weights directly, no forward pass.
The math eval improvement experiment that got a lot of attention 1) fixed a specific known problem (looping) without actually understanding how the model solves problems, and 2) was allowed to do forward passes to check the results of the edits.
As others have noted, steering vectors are interp 101 and it’s pretty rare that there is an “act dumb vector” just waiting to be steered out of the residual stream.
It’s a bit conflated because the paper covered a bunch of experiments.
The early experiments did read/write the weights directly, no forward pass.
The math eval improvement experiment that got a lot of attention 1) fixed a specific known problem (looping) without actually understanding how the model solves problems, and 2) was allowed to do forward passes to check the results of the edits.
As others have noted, steering vectors are interp 101 and it’s pretty rare that there is an “act dumb vector” just waiting to be steered out of the residual stream.