Make Fabrication Unrepresentable
A practical approach to preventing AI assistants from fabricating numbers by making model outputs cite or compute values instead of asserting them.
3 articles
A practical approach to preventing AI assistants from fabricating numbers by making model outputs cite or compute values instead of asserting them.
A CQRS-inspired approach to integrating LLMs: treat the language model as a user sending commands, not an internal system component.
How conversational AI interfaces are breaking the GUI vs. CLI dichotomy and creating a new paradigm for human-computer interaction.