From 606335c7c16f7000aa6f572d84b4229cc93eaf1c Mon Sep 17 00:00:00 2001 From: Stevan Freeborn <65925598+StevanFreeborn@users.noreply.github.com> Date: Mon, 9 Feb 2026 13:51:03 -0600 Subject: [PATCH] talk: finish pres and yt script --- slides/why_llms_dont_make_choices/index.md | 162 ++++++++++++++++++++ slides/why_llms_dont_make_choices/script.md | 101 ++++++++++++ 2 files changed, 263 insertions(+) create mode 100644 slides/why_llms_dont_make_choices/index.md create mode 100644 slides/why_llms_dont_make_choices/script.md diff --git a/slides/why_llms_dont_make_choices/index.md b/slides/why_llms_dont_make_choices/index.md new file mode 100644 index 0000000..878f53d --- /dev/null +++ b/slides/why_llms_dont_make_choices/index.md @@ -0,0 +1,162 @@ +--- +title: Why LLMs Don't Make Decisions +theme: default +layout: center +class: text-center +fonts: + sans: "CaskaydiaCove Nerd Font Mono" +--- + +# Why LLMs don't make decisions + +--- +layout: center +--- + +# The Narrative vs. The Reality + +
+ +
+

The "Agentic" Narrative

+
    +
  • "The agent decided to call the tool."
    • +
  • "The model assessed the PRD."
    • +
  • "It chose the execution path."
    • +
+
+ + +
+

The Engineering Reality

+
    +
  • It is completing a pattern.
    • +
  • It is statistically mapping tokens.
    • +
  • It is following constraints.
    • +
+
+ +
+ +
+ "We mistake highly accurate mapping for decision making." +
+ + +--- +layout: center +--- + +# The Domino Analogy + +
+

+ "If I set up a long row of dominos... and the last domino falls and hits a bell..." +

+ +
+ Did the last domino decide to ring the bell? +
+ + +

Of course not.

+ +
+ +--- +layout: default +--- + +# The functional reality of LLMs + +If we strip away the magic, an LLM is effectively a **pure, stateless function**. + +```csharp {all|1|3-6|8} +ProbabilityDistribution PredictNext(int[] contextTokens, float[] fixedWeights) +{ + // 1. Input: Static sequence of integers (Tokens) + // 2. Process: Fixed graph of matrix operations (Weights) + + // Matrix Multiplication Magic... + + return probabilities; // 3. Output: Probability scores +} +``` + +
+ +
+
No "Pondering"
+
There is no loop where it weighs pros and cons. It is a single, deterministic forward pass.
+
+ + +
+
The "Choice" is External
+
The Sampler picks the token based on temperature. The model just provides the stats.
+
+ +
+ +--- +layout: center +--- + +# Where the logic actually lives + +
+
+
+

Prompt Engineering

+

Rigging the machine so it pays out the exact token we need 99% of the time.

+
+
+

The Agentic Loop

+

Engineering the context so the "next token" is useful JSON, not hallucinated poetry.

+
+
+
+ +--- +layout: center +--- + +# Why the distinction matters + +
+ +
+
1
+
+

Constrain the Context

+

Reduce the search space so the "right" token is the only probable one.

+
+
+ + +
+
2
+
+

Rig the Inputs

+

Format prompts so the pattern that needs to be completed leads to your output.

+
+
+ + +
+
3
+
+

Verify the Output

+

It didn't "choose" based on belief. It made a statistical guess. Always validate.

+
+
+ +
+ +--- +layout: center +--- + +# Conclusion + +
The "Decision" is just the inevitable result of the constraints and context you fed into the prediction engine.
diff --git a/slides/why_llms_dont_make_choices/script.md b/slides/why_llms_dont_make_choices/script.md new file mode 100644 index 0000000..6bf47f9 --- /dev/null +++ b/slides/why_llms_dont_make_choices/script.md @@ -0,0 +1,101 @@ +[Face to Camera] + +"There is a dangerous idea spreading in software engineering right now. It's the idea that Large Language Models are 'Decision Makers'." + +"We treat them like junior employees. We think they 'choose' to call a tool, or 'decide' how to fix a bug." + +[Switch to Presentation] + +"But today, I want to show you why that mental model is wrong—and how it leads to fragile software." + +[CLICK] + +"We need to distinguish between the Narrative and the Reality." + +[CLICK] + +"The narrative—the marketing fluff—says things like: 'The agent decided to call the tool.' Or 'The model assessed the PRD and chose a path.'" + +"This language implies agency. It implies intent." + +[CLICK] + +"But the engineering reality is boring. The model is simply completing a pattern. It is statistically mapping tokens based on weights. It is following constraints we set." + +[CLICK] + +"We mistake highly accurate mapping for decision making." + +[CLICK] + +"Think of it this way." + +"If I set up a long row of dominos... and the last domino falls and hits a bell..." + +[CLICK] + +"Did the last domino decide to ring the bell?" + +[CLICK] + +"Of course not. It just followed the physics of the environment I built." + +"The 'decision' to ring the bell wasn't made by the domino. It was made by the person who set it up." + +[CLICK] + +"If we strip away the magic, an LLM is effectively a pure, stateless function." + +[CLICK] + +"You give it a static sequence of tokens." + +[CLICK] + +"It pushes those integers through a fixed graph of matrix operations." + +[CLICK] + +"And it returns a probability distribution. Not a choice. A list of percentages." + +[CLICK] + +"There is no 'pondering' inside that function. There is no while loop where it weighs the pros and cons. It is a single, deterministic forward pass." + +[CLICK] + +"The actual 'choice' happens outside the model. The Sampler picks the token based on temperature. The model didn't 'decide' to output a JSON bracket; it just assigned it a 99% probability because you rigged the prompt." + +[CLICK] + +"So if the model isn't deciding, where does the logic actually live?" + +"It lives in two places." + +"First, Prompt Engineering. This isn't 'whispering to AI'. It is rigging the slot machine so it pays out the exact token we need 99% of the time." + +"Second, The Agentic Loop. We engineer the context so that the only statistically probable next token is useful JSON, not hallucinated poetry." + +[CLICK] + +"This distinction matters because it changes how you build software." + +[CLICK] + +"If you know it's not a decision maker, you focus on Constraining the Context. You reduce the search space so the 'right' token is the only probable one." + +[CLICK] + +"You Rig the Inputs. You format your prompts so the pattern that needs to be completed inevitably leads to your desired output." + +[CLICK] + +"And crucially, you Verify the Output. You never trust the model's 'belief', because it has none. It made a statistical guess. You must validate it." + +[CLICK] + +"The bottom line is this: The 'Decision' is just the inevitable result of the constraints and context you fed into the prediction engine." + +"You are the decision maker. The model is just the domino." + +"Thanks for watching."