Advanced topic
Baking a Model: How Models Get Made
Pre‑training vs post‑training (high‑level mental model)
~15–20 minutes
Advanced add‑on
1 / 10
Mechanism + machinery

Baking a Model

A mental model for how modern AI systems get constructed: product UI vs model proper, and pre‑training vs post‑training.

High‑level No math Process‑focused
ADV

What we’ll cover

  • What “model” can mean (and why it’s two parts)
  • Why the model proper is “a bag of numbers”
  • Pre‑training vs post‑training
  • Why the baking analogy helps

How to use this mini‑deck

Use it as a compact mental model for model construction. It’s intentionally high‑level and process‑focused.

  • Use the UI vs model split to avoid confusion
  • Use pre‑ vs post‑training to explain iteration speed
  • Use the baking analogy to remember the phases
Zooming out

What Do We Mean by “Model”?

In everyday talk, “model” often means the whole product. For understanding how it’s made, split it into two parts.

SPLIT
Part 1

User interface / product layer

Formatting inputs/outputs, auth, sequencing, tool wiring, UX, policy, etc. Built with conventional software engineering.

Part 2

The model proper

The artifact that produces probabilistic outputs from inputs. Built via training—radically different from writing code.

Why the split matters

People often attribute product behavior to “the model,” when some behavior lives in the UI/product layer.

Model proper

A Model Is a Bag of Numbers

At a high level, the model is a large collection of numbers. Those numbers are what training produces and what behavior depends on.

NUMS

What this means

  • The “intelligence” is not hand-written rules
  • Behavior comes from learned parameter values
  • Changing the numbers changes behavior

What we’re not covering (today)

  • The math inside attention/transformers
  • Exact optimization algorithms

The focus is the construction process.

How behavior gets created

Training Isn’t Programming

Programming writes explicit steps. Training sets up conditions so the artifact adjusts itself based on data and objectives.

DIFF

Programming

  • Explicit instructions
  • Small changes are cheap
  • Fast compile/test cycles

Training

  • Set data + initial conditions
  • Long-running processes
  • Iteration speed varies by phase
Phased process

Pre‑Training and Post‑Training

Rather than one monolithic “training,” it helps to think of phases with very different rhythms and risks.

PHASE
Phase

Pre‑training

Big batch run to get an approximately capable base model.

Phase

Mid‑training

Sometimes referenced; details vary (and are often not publicly described).

Phase

Post‑training

Many smaller, targeted batches to improve usability and weak spots.

Why this matters

Iteration speed, cost, and collaboration patterns differ drastically by phase.

Phase 1

Pre‑Training: Big Batch, Big Bet

Teams set initial conditions: data + a blank-ish model, then run enormous training jobs, monitoring and checkpointing along the way.

PRE

What happens

  • Prepare data + model
  • Run massive training loops
  • Checkpoint / snapshot
  • Monitor for divergence

Why it’s hard

  • Very expensive and slow to iterate
  • Failures cost time and money
  • Restart decisions are high-stakes
Baking analogy

Pre‑Training ≈ Cold Proofing

You mix ingredients, put them away, and let time do the work. You can’t constantly intervene without changing the process.

PROOF

Cold proofing

  • Mix ingredients
  • Put it away
  • Small early changes have big later effects

Pre‑training

  • Set initial conditions
  • Run long jobs
  • Early choices echo later

Key insight

Pre‑training produces a base that isn’t necessarily “ready for humans”—it’s the precursor to later shaping.

Phase 2

Post‑Training: Many Small Batches

Post‑training is where teams address specific weaknesses: small experiments that improve the model’s behavior for real users.

POST

What happens

  • Find failure modes
  • Design targeted tweaks
  • Run small batches
  • Keep the wins

Outcome

Lots of small code+data artifacts (surviving experiments) that supplement the base model.

  • More helpful responses
  • Better instruction following
  • Reduced obvious failures
Baking analogy

Post‑Training ≈ Shaping & Cooking

You take something with potential and make it useful for humans. This phase is iterative and collaborative.

BAKE

Shaping & cooking

  • Adjust texture and form
  • Make it enjoyable to humans
  • Iterate with feedback

Post‑training

  • Target specific weaknesses
  • Improve usability
  • Refine behavior iteratively

One nuance

The analogy doesn’t capture how post‑training is often reversible and experiment-driven—but it captures the “make it usable for humans” intent.

Conclusion

Why This Framing Matters

It explains why model development has different teams, different rhythms, and different costs compared to conventional software.

END

Practical consequences

  • Pre‑training is slow to iterate; choices are high-stakes
  • Post‑training is faster; many targeted improvements
  • Product behavior = UI layer + model behavior

Audience takeaway

Models are engineered through processes—more like baking than coding. Understanding the phases makes AI discussions clearer and less mystical.

Arrows • Space • Home/End