Lesson 2.5: Pretraining vs fine-tuning vs RLHF, in plain English | GeekHub Learn

Every model you will use went through three life stages. Knowing them tells you what it is good at and where it will fail.

Stage 1: read every book in the library. Stage 2: take a specialized course. Stage 3: get coached by mentors on how to behave. That is pretraining, fine-tuning, RLHF.

Pretraining: the model is fed trillions of tokens of text and learns to predict the next token. This gives it language fluency, world knowledge, and general capabilities. Costs millions of dollars.
Fine-tuning (Supervised): the model is shown thousands of pairs of (instruction, ideal response). This teaches it to follow instructions in the desired format.
RLHF (Reinforcement Learning from Human Feedback): humans rank multiple model responses. A reward model learns the rankings. The model is updated to produce higher-ranked answers. This teaches helpfulness, harmlessness, and honesty.

Modern frontier models also use RLAIF (AI feedback in place of humans) and constitutional AI to scale this stage.

You will rarely pretrain a model yourself (cost is prohibitive). You may fine-tune one if you have 100 to 10,000 high-quality examples. You almost never run RLHF yourself for chat. Most production teams stop at fine-tuning, often using LoRA (low-rank adapters) to keep costs low.

Visualize it

A three-stage horizontal pipeline labeled "Pretrain (years of internet text) -> Fine-tune (instruction pairs) -> RLHF (human preferences)" with an output box labeled "ChatGPT-style assistant".

Try it now

Ask GPT-4 or Claude: "What was the last time you were updated?" Compare to: "Search the web for today's date." The first hits its training cutoff. The second uses tools. Train vs deploy time matters.

Hands-on lab

Look up the "knowledge cutoff" of three different LLMs (Google a phrase like "GPT-4 knowledge cutoff", "Claude knowledge cutoff", "Gemini knowledge cutoff"). Note them. Note that this is why models do not know "current" news without tool use.

Try it now

Why does RLHF make models more agreeable but sometimes less accurate?

Common mistakes

Trying to fine-tune to "teach the model facts". It learns style and format, not durable facts.
Confusing fine-tuning with RAG. RAG retrieves at inference time. Fine-tuning bakes in behavior.
Believing a model knows things "as of today". It knows up to its training cutoff.

Debugging tip

If your model gives stale answers, you need RAG or tools, not fine-tuning. If your model ignores format instructions, fine-tuning may help.

Challenge

Sketch a decision tree: "Should I prompt, fine-tune, or RAG this problem?". Three branches with one example each.

Where this shows up

Pretraining: not your job
Fine-tuning: domain-specific writing styles, structured outputs, low-resource languages
RLHF: behavior tuning at the model provider level

From the field

In 2026, prompt + RAG solves 80% of business problems. Fine-tuning solves another 15%. Pretraining is left to the labs. This ratio shapes your career: master prompting and RAG first.

Recap

Pretraining builds the brain. Fine-tuning shapes the personality. RLHF gives it manners. As a developer, you mostly work above all three with prompts, RAG, and the occasional fine-tune.

Quick recall

3 prompts · think before you flip

Prompt 1 of 3

Define pretraining, fine-tuning, and RLHF.

Quiz time

1 question · tap an answer to check it

1. To make the model answer in a specific JSON format every time, your first move should be