statementSaid on 2026-11-08
Each implanted layer is multiplied by a learned gate initialized to zero; at the moment of implantation the network does not change at all, and the gradient descent decides whether to open the gate.
A statement by post author, said on 2026-11-08. Statements are as reported by the cited publishers — not verified by DecisionGateway.
הטריק היפה הוא שכל שכבה נכנסת מוכפלת בשער נלמד שמאותחל לאפס. ברגע ההשתלה הרשת לא משתנה בכלל, מורד הגרדיאנט מחליט אם לפתוח את השער.
Discussion
Related claims
To know where to implant, the agent computes the loss gradient for each token according to its representation in each layer.post author · statementThe same layer works better when implanted in the middle of training than when it is there from the first step.post author · statementThe agent implants "code layers" into the network — small programs that read tokens or internal representations, and whose output re-enters the computation alongside attention and MLP.post author · statementIn a linear layer, each new memory is simply added to the weights; retrieval returns the correct value plus a bit of every other memory depending on key overlap.post author · statementIn a regular network, if the model errs, the backprop algorithm stops everything, goes back from end to start and updates all the weights; in the brain there is no such central manager, and instead each synapse learns on its own from its local environment using STDP.author · statementWhen the same gradient keeps appearing across several checkpoints, the writers interpret it as "demand" that SGD fails to supply.the writers · statement