Prior Technology Notes

Annotate Transformer
RASP and TRACR
Interpretability
Ambient Space
On hallucination in Large Language Models
Inference
Technical Architecture
Bertology
Large Language Models
AI Alignment
Security Standards
Generative Machine Learning Models
Explainable AI
AI Legislation
Distillation
GPT2
Latent Space
Transformer
OpenAI
GPT 3
Functional Discourse Grammar

AI Alignment

AI Alignment #

The problem of alignment is around ensuring that an AI algorithm that the incentives of an AI algorithm remain consistent with the overall intent for the system.