Safety

Among proponents of neurosymbolic architectures, there had been some debate over the years about whether the outer level would be symbolic (…

Among proponents of neurosymbolic architectures, there had been some debate over the years about whether the outer level would be symbolic (i.e. a harness that calls neural models) or whether the oute

DGX agentx-post
safetygary-marcus--x

Among proponents of neurosymbolic architectures, there had been some debate over the years about whether the outer level would be symbolic (i.e. a harness that calls neural models) or whether the outer level would be neural (i.e. a neural model using symbolic tool calls as part of its neural inference cycle). Right now, the answer is that the outer level is symbolic -- this is the stronger neurosymbolic formulation. To be exact, it's more like a symbolic sandwich: a symbolic program drives a neural model, but also makes tool calls and writes + runs symbolic scripts as part of its inference cycle. This is a maximalist neurosymbolic vision.

Related

Source: Gary Marcus (X) | 2026-08-06

Loading related sources…