← Master Index
Vol. 11 Module 11.5 Lecture

GPT Family

Modern LLM Families

How This Lesson Fits the Module & Volume

Module 11.3 covered numbered GPT milestones. This lecture treats the GPT family as a product lineage: decoder-only transformers, scaled pretraining, and post-training for chat/tools. It opens Module 11.5 after Context Length.

Learning Objectives

By the end of this lesson, students should be able to:

  • Place GPT models in the decoder-only causal LM lineage.
  • Separate base completion models from ChatGPT-style assistants.
  • Describe closed API access versus open-weight alternatives.
  • List typical surfaces: chat, APIs, agents, multimodal.
  • State trade-offs: capability, cost, opacity, lock-in.
  • Avoid fabricating unpublished proprietary internals.
Definition

The GPT family (Generative Pre-trained Transformer) is OpenAI’s lineage of primarily decoder-only language models trained with next-token prediction and adapted with instruction/preference methods into widely deployed assistants and APIs.

Architecture & Lineage

Stage / modelPublicly known shiftCurriculum note
GPT-1 / GPT-2Unsupervised pretrain + generation demosHistorical teaching baselines
GPT-3In-context learning at API scaleFew-shot prompting era
Instruct / ChatGPT eraSFT + preference alignmentProductized assistants
GPT-4 class & successorsStronger reasoning/tools/multimodal SKUsClosed flagship tier
Pretrain

Causal LM at scale.

Post-train

SFT + preferences.

Productize

Chat, APIs, tools.

Iterate

New SKUs & modalities.

Open vs Closed Positioning

Access

  • Mostly closed API / product access
  • Flagship weights not generally public
  • Contrast with Llama / Mistral open weights

Differentiation

  • Strong general assistant ecosystem
  • Tools, multimodal, enterprise controls
  • Fast product iteration

Curriculum links

  • Builds on Module 11.3 GPT lectures
  • Compare next with Claude & Gemini
  • Open peers: Llama, Mistral, Qwen

Typical Use Cases

Use caseWhy this familyWatch-outs
General assistantsPolished chat + tool ecosystemsVendor cost & data policies
App backendsStable APIs and managed scaleRate limits; provider dependency
Multimodal featuresImage+text product pathsOpaque internals vs open forks

Engineering Touchpoint

# Conceptual API-style call (SDK versions vary) # from openai import OpenAI # client = OpenAI() # r = client.chat.completions.create( # model="gpt-4.1-mini", # messages=[{"role": "user", "content": "Summarize PEFT in 3 bullets"}], # ) # print(r.choices[0].message.content)

Engineering Upsides

  • High capability for many tasks
  • Mature SDKs and enterprise features
  • Lower ops burden than self-hosting

Engineering Trade-offs

  • Closed weights limit deep customization
  • Pricing/policy can change
  • Hard to audit model internals
Common Misconception

“GPT means one frozen architecture.” GPT is a brand lineage; generations change scale, data, post-training, and multimodal packaging. Treat SKU names as products, not eternal papers.

Knowledge Check

  1. Short Answer: What does GPT stand for? Answer: Generative Pre-trained Transformer.
  2. True/False: Flagship GPT models are typically fully open weights. Answer: False—they are primarily closed APIs/products.
  3. Multiple Choice: GPT models are primarily: (a) encoder-only BERT clones, (b) decoder-only causal LMs, (c) pure CNNs, (d) random forests. Answer: (b).
  4. Short Answer: What objective started the GPT lineage? Answer: Next-token / autoregressive language modeling.
  5. True/False: ChatGPT-style behavior needs no post-training. Answer: False—SFT and preference methods matter.
  6. Multiple Choice: A key GPT API trade-off is: (a) free infinite tokens, (b) capability vs cost/lock-in, (c) mandatory open weights, (d) no tokenizer. Answer: (b).
  7. Short Answer: Name one enterprise reason to use GPT APIs. Answer: Strong quality, tooling, and managed infrastructure.
  8. True/False: Module 11.3 already covered earlier GPT milestones. Answer: True.
  9. Multiple Choice: Versus Llama flagships, GPT flagships are usually: (a) more closed, (b) always smaller, (c) CNNs, (d) non-neural. Answer: (a).
  10. Short Answer: Why avoid inventing GPT internals? Answer: Proprietary details are unpublished; stick to public docs and engineering facts.

Key Takeaways

  • GPT is OpenAI’s decoder-only LM lineage turned product platform.
  • Access is mostly closed; ecosystem and quality are the draw.
  • Post-training and tools matter as much as raw scale.
  • Next: Claude Family.
Trainer’s Guide

Compare: Same coding prompt on a GPT API vs an open 7–8B instruct model.
Policy: Extract claims vs unknowns from a public system/model card.

Recap: The GPT family anchors closed, productized decoder-only LLMs. Continue with Claude Family.