NVIDIA: AI security is an engineering problem across the full agent stack
nordicinst · x · 2026-09-21
- NVIDIA argues AI security is an engineering problem: defined requirements, enforceable controls, named owners, evidence protections work
- Agents add reasoning, tool use, and adaptive actions — established principles must apply to new operating conditions
- Security depends on the full stack: models, harnesses (context/tools/workflows), and runtime infrastructure each need controls
- Uses an agent updating customer records facing malicious instructions as an example of layered defense
More from coding & agent
- e2b to demo agents forking live VMs to explore solutions in parallel — badphilosopher · 2026-09-21
- User drops Astra after bad week, says Codex needs a real orchestrator — koltregaskes · 2026-09-21
- Agent evals' cold start is smaller than you think: start ugly, iterate — sarahcat21 · 2026-09-21
- Models Don't Have Agency. Systems Do.: Structured Output Is What Makes Agents Work — sethjuarez · 2026-09-21
- LukeW: Using the humble ALT tag to fix irrelevant image retrieval in AI replies — LukeW · 2026-09-21
- Dev shares AGENTS.md rule: skip unit tests after coding, rely on E2E only — alexcovo_eth · 2026-09-21