ManySpace
Türkçe Sign in Sign up

AI & MLRecommendedAIML-LM-014

Alignment Concepts

Helpful, honest, harmless: what alignment asks for and where it provably strains.

Difficulty
3 / 5
Importance
4 / 5
Study time
1–2 h
Kind of work
Mixed

Why it matters

The learner can state the alignment triad and explain one tension between its members.

The route to this topic

Route AIML-LM-014
What Is a Model? Tasks: Regression, Classification, and Beyond Features and Targets Classification Framing Linear Regression I: Prediction and Residuals Embeddings Tokens and Tokenization Scores and Logits Loss and Fitting: Squared Error Multiclass Scores and Softmax The Artificial Neuron Autoregression Objective Functions and Empirical Risk Activation Functions Next-Token Prediction Gradient Descent in Machine Learning Likelihood The Multilayer Perceptron Cross-Entropy Loss Stochastic and Mini-batch Optimization The Language-Modeling Objective Transfer Learning Pretraining Fine-Tuning Supervised Fine-Tuning Preference Optimization Alignment Concepts