Andrej Karpathy just dropped 12-page PDF on "Graph Engineering" for multi-agentic systems
the shift: Karpathy's loop runs 700 experiments and forgets all of them. A graph remembers forever
here's the full system:
step 1 → build one loop: generate, critique, revise. 630 lines, 700 experiments in 48 hours
step 2 → go parallel: agents in separate worktrees, same repo, different branches, no conflicts
step 3 → add a knowledge graph: extract entities, resolve aliases, assemble typed edges, query through subgraphs
step 4 → ground your evaluator: it checks claims against graph edges, not vibes
step 5 → plug the graph as shared memory. workers write to it. evaluators fact-check against it. Loops persist overnight
step 6 → the agent forgets. the graph does not. stop rebuilding context from scratch every session
Karpathy ran 1 agent in 1 direction. Anthropic's graph runs 1,000 with shared memory - same model, it's the architecture
https://drive.google.com/file/d/1-GOg0kxcp8tx1BMUECMj2yJq6JYGmfhb/view
the shift: Karpathy's loop runs 700 experiments and forgets all of them. A graph remembers forever
here's the full system:
step 1 → build one loop: generate, critique, revise. 630 lines, 700 experiments in 48 hours
step 2 → go parallel: agents in separate worktrees, same repo, different branches, no conflicts
step 3 → add a knowledge graph: extract entities, resolve aliases, assemble typed edges, query through subgraphs
step 4 → ground your evaluator: it checks claims against graph edges, not vibes
step 5 → plug the graph as shared memory. workers write to it. evaluators fact-check against it. Loops persist overnight
step 6 → the agent forgets. the graph does not. stop rebuilding context from scratch every session
Karpathy ran 1 agent in 1 direction. Anthropic's graph runs 1,000 with shared memory - same model, it's the architecture
https://drive.google.com/file/d/1-GOg0kxcp8tx1BMUECMj2yJq6JYGmfhb/view