offaxis
- Karma
- 5
- Created
- 4 months ago
About
IoT / Matter / AI agent execution safety. Building AI-readable physical device actions.Recent Submissions
- 1. ▲ We gave AI a trust we never gave people: can it, may it, on what grounds (discuss.huggingface.co)
- 2. ▲ Values, conditions, intent: People should declare them, not the model (github.com)
- 3. ▲ LLM Tool Failures: Only 3 Root Causes – Value, Condition, Intent (github.com)
- 4. ▲ Forms did five things. Natural language kept one
- 5. ▲ From knowledge-based inference to presence-based verification (discuss.huggingface.co)
- 6. ▲ If Unsure, Ask. Never Guess. AI Agent Pre-Execution Checklist (discuss.huggingface.co)
- 7. ▲ Unknown Is Not False: An AI Agent Pre-Execution Checklist (discuss.huggingface.co)