Memory hook: Identify the input, output and consequence before selecting a model.
Must remember
- Machine learning predicts patterns from data; generative models create content; agents combine models with state and tools to pursue tasks. Supervised classification predicts categories, regression numbers, clustering finds groups, and reinforcement learning improves behaviour through rewards.
- Foundation models support broad tasks after pretraining. Large/small models trade capability, latency, footprint and cost. Multimodal models accept or produce supported combinations of text, images, audio or video. Model capability and deployment availability vary by version and Region.
- Tokens are model-specific units; context/output limits constrain requests. Temperature and related sampling settings influence variability, not truth. Embeddings represent content for similarity retrieval; they are not encryption or final answers.
- Choose text analysis for entities, key phrases, sentiment or summaries; speech recognition for audio-to-text; synthesis for text-to-audio; vision for visual interpretation; generation for new media; extraction for structured information from source content. A fixed exact calculation may be safer as ordinary code.
- Responsible AI considers fairness, reliability/safety, privacy/security, inclusion, transparency and accountability. Evaluate representative groups and failure costs. Explain intended use and limitations, offer accessible experiences and assign a responsible owner for correction/escalation.
- Hallucinations can be fluent and wrong. Ground responses in suitable evidence, validate structured outputs and use human review where consequence requires it. Filters reduce selected risks but cannot guarantee correctness, fairness or legal suitability.
Choose under exam pressure
| Requirement | Choice and reason |
|---|---|
| Classify an incoming request | A suitable classifier/model with measured category performance. |
| Answer using current company documents | Retrieval-grounded generation with access controls. |
| Perform an exact regulated calculation | Deterministic validated logic when prediction is unnecessary. |
Traps
- Model confidence is not independent evidence.
- A larger model is not always the best operational choice.
- Removing a sensitive column does not remove every proxy for that attribute.
Active recall
1. What distinguishes an agent from a basic chat call?
It can use tools/state and control logic to pursue a task, introducing action and permission risks.
2. What does temperature control?
Sampling behaviour/variability, not factual correctness.
3. Why assess subgroups?
Aggregate quality can hide poor or harmful performance for a smaller group.
4. What is an embedding useful for?
Representing content for similarity-based operations such as retrieval.
5. Why assign accountability?
Someone must own acceptable use, monitoring, corrective action and consequences.