Channel: ai
- 1
Touching the Elephant - TPUs
Matrix multiplies have the property that as the size of inputs grow, the ratio of compute, O(n^3), to data access, O(n^2), improves. If you can dedicate hardware to speeding up arithmetic and coordinating data movement you can exploit this,
humanlayer/12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
- Factor 1: Natural Language to Tool Calls
- Factor 2: Own your prompts
- Factor 3: Own your context window
- Factor 4: Tools are just structured outputs
- Factor 5: Unify execution state and business state
- Factor 6: Launch/Pause/Resume with simple APIs
- Factor 7: Contact humans with tool calls
- Factor 8: Own your control flow
- Factor 9: Compact Errors into Context Window
- Factor 10: Small, Focused Agents
- Factor 11: Trigger from anywhere, meet users where they are
- Factor 12: Make your agent a stateless reducer
- 1