Re:Models can now transmit viruses in weight-space
by cmrx64 on Saturday November 14, 2026 @07:01AM
(#50496339)
there’s a conception of GDNs/linear attention as fast-weight programmers. it is inherent to the architecture i guess
Re:Models can now transmit viruses in weight-space
by flufluflufluffy on Saturday November 14, 2026 @08:14AM
(#50496772)
> to accomplish some task
That’s what I mean by intent. It doesn’t matter if an agent was prompted by a human to do it or if it just did it itself. It is the process of altering specific weights for some intended purpose.
A protein misfolding just happens at random. The majority of misfolded proteins are nonfunctional and just get degraded by the cell. Even the few that result in a self-propagating pattern are still just random aberrations. Idk their use of the term just irks me.
Not necessarily. You could very well have a model trained without any human intention to have it do weight space programming that nevertheless does weight space programming to accomplish some task.
I'm not even sure it's the less likely option. Across millions of evals and training runs among different organizations, can we confidently say no agent will ever autonomously perform weight programming? It only takes one success, and it's only a short leap from a success there to a success that induces downstream models to weight program.