An instance of LLM prompting for programming

Xu Hao makes use of chain of thought and normal information prompting with ChatGPT when writing self-testing code

My account of an inside chat with Xu Hao, the place he exhibits how he
drives ChatGPT to provide helpful self-tested code. His preliminary immediate primes
the LLM with an implementation technique (chain of thought prompting). His
immediate additionally asks for an implementation plan fairly than code (normal
information prompting). As soon as he has the plan he makes use of it to refine the
implementation and generate helpful sections of code.

Lately I watched an enchanting name on Zoom. Xu Hao, Thoughtworks’s
Head of Expertise in China, defined his explorations in utilizing ChatGPT to
assist construct Self Testing Code. He
went by the type of interplay that works for him.

He begins with a immediate that units the context for the applying and the way
he desires the code to be structured.

The present system is a web based whiteboard system. Tech stack:
typescript, react, redux, konvajs and react-konva. And vitest, react
testing library for mannequin, view mannequin and associated hooks, cypress part
checks for view.

All codes ought to be written within the tech stack talked about above.
Necessities ought to be carried out as react parts within the MVVM
structure sample.

There are 2 varieties
of view mannequin within the system.

1. Shared view mannequin. View mannequin that represents states shared amongst
native and distant customers.

2. Native view mannequin. View mannequin that represents states solely relevant
to native person

Listed here are the frequent implementation technique:

1. Shared view mannequin is carried out as Redux retailer slice. Examined in
vitest.

2. Native view mannequin is carried out as React part props or states(by
useState hook), until for international native view mannequin, which can also be
carried out as Redux retailer slice. Examined in vitest.

3. Hooks are used as the main view helpers to retrieve knowledge from shared
view mannequin. For many the case, it can use ‘createSelector’ and
‘useSelector’ for memorization. Examined in vitest and react testing
library.

4. Don’t dispatch motion immediately to alter the states of shared view
mannequin, use an encapsulated view mannequin interface as an alternative. Within the interface,
every redux motion is mapped to a way. Examined in vitest.

5. View is include konva shapes, and carried out as react part through
react-konva. Examined in cypress part checks

Listed here are sure patterns ought to be adopted when implement and take a look at
the part

1. When write take a look at, use `describe` as an alternative of `take a look at`

2. Knowledge-driven checks are most well-liked.

3. When take a look at the view part, pretend view mannequin through the view mannequin
interface

Consciousness Layer

Requirement:

Show different customers’ consciousness information(cursor, identify and on-line
info) on the whiteboard.

AC1: Don’t show native person

AC2: When distant person modifications cursor location, show the change in
animation.

Present an general resolution following the steerage talked about above.
Trace, maintain all consciousness info in a Konva layer, and an consciousness
information part to render cursor, and identify. Don’t generate code. Describe
the answer, and breaking the answer down as a job checklist based mostly on the
steerage talked about above. And we are going to refer this job checklist as our grasp
plan.

There’s so much occurring with this immediate, so he highlighted a number of
factors.

He is utilizing a generic software instance in right here: one factor to be
cautious of when interacting with ChatGPT and the like is that we must always by no means
put something which may be confidential into the immediate, as that may be a
safety threat. Enterprise guidelines, any code from an actual venture – all these should
not enter the interplay with ChatGPT.

A lot of the immediate is setting out the design tips that he desires
ChatGPT’s generated code to observe. He refined this by placing prompts into
ChatGPT, wanting on the outcome, and crafting the immediate to make it generate
within the model he wished. As soon as he has context working, he can paste it into
each session he has with ChatGPT, and share it with the remainder of the
crew.

Xu Hao begins his session by prompting the
ChatGPT LLM with context in addition to the instruction to generate a plan

Though the ultimate aim of this session is to generate code and its
checks, at this stage he particularly mentioned Don’t generate code.
At this level he desires ChatGPT to stipulate its method earlier than we glance to any
code era. This can be a immediate approach referred to as Generated Data.

A typical means of interacting with an LLM is to provide it an issue and ask
it to generate some closing product, whether or not than be prose or (on this case)
code. With Generated Data we break up our interplay into separate steps:
first ask the LLM to generate some helpful details about the issue, and
then we feed that info again into the LLM to generate the ultimate
product.

Essentially the most fascinating a part of the immediate is the “implementation technique”
part which mixes two kinds of immediate:

Instruction prompting offers directions for the LLM to observe
Chain of Thought prompting encourages the LLM to elucidate its
reasoning.

Within the Implementation Technique part, Xu Hao described the specified
structure sample as an anticipated “Chain of Thought directions” for
ChatGPT to observe. Then he instructed ChatGPT to construct a job checklist (the
generated information) based mostly on this chain of thought.

Answer:

To implement the attention layer characteristic, we are able to observe the rules talked about in the issue assertion and use the present tech stack.

Process Checklist:

Create a brand new part named “AwarenessInfo” to render cursor and identify for distant customers.
Create a brand new Konva layer to carry all of the “AwarenessInfo” parts.
Add the Konva layer to the primary whiteboard part.
Create a brand new Redux slice to retailer the attention info for distant customers.
Create an encapsulated view mannequin interface for the attention Redux slice.
Implement the “AwarenessInfo” part to retrieve and show the attention info for every distant person from the view mannequin.
Implement a way within the encapsulated view mannequin interface to replace the attention info for every distant person.
When a distant person modifications the cursor location, dispatch the replace methodology within the encapsulated view mannequin interface to replace the corresponding consciousness info.
Within the “AwarenessInfo” part, use the brand new location to animate the cursor change.
Write checks for the brand new “AwarenessInfo” part, together with data-driven checks to make sure it correctly shows the attention info for all distant customers.
Write checks for the encapsulated view mannequin interface to make sure it correctly updates the attention info for distant customers.
Write end-to-end Cypress checks to make sure the attention layer is correctly displayed and up to date when distant customers change their cursor location.

By following these duties, we are able to implement the attention layer characteristic within the on-line whiteboard system.

The response from ChatGPT is non-deterministic, so this result’s simply
one run. In case you (or I) put this immediate in once more, we’ll get a distinct response.

The important thing ingredient of the response is an ordered job checklist, with numbers for
every step. We will use these numbers to refer to those duties for the remainder of
the session.

The LLM responds with a plan.

Xu Hao can now have a look at the grasp plan and see if it is smart. If
there are issues with it, he can ask ChatGPT to re-write among the duties
or the complete grasp plan by offering extra info.

For instance, the present grasp plan was not grouped by differing kinds
of parts. One attainable immediate is perhaps:

Rewrite the grasp plan, and group duties as mannequin, view mannequin and consider.

This might be helpful to confirm the alignment between the structure
imaginative and prescient and grasp plan.

These tweaks might be added to the preliminary immediate to get an general
higher response.For this specific immediate, the next instruction was
not within the preliminary immediate, however had been added in later iteration:

4. Don’t dispatch motion immediately to alter the states of shared view
    mannequin, use an encapsulated view mannequin interface as an alternative. Within the interface,
    every redux motion is mapped to a way. Examined in vitest.

As soon as the grasp plan seems to be affordable, Xu Hao asks to regenerate it with
names for this system parts.

Rewrite the grasp plan, this time with detailed part names,
strategies, and props

Positive, here is a revised grasp plan with detailed part names, strategies, and props:

Process Checklist:

Create a brand new part named “AwarenessInfo” to render cursor and identify for distant customers. This part will obtain props corresponding to person identify, cursor place, and on-line standing.
Create a brand new Konva layer named “AwarenessLayer” to carry all of the “AwarenessInfo” parts.
Add the “AwarenessLayer” to the primary whiteboard part.
Create a brand new Redux slice named “consciousness” to retailer the attention info for distant customers.
Create an encapsulated view mannequin interface named “AwarenessViewModel” for the “consciousness” Redux slice. This interface will comprise a way named “updateUserAwarenessInfo” to replace the attention info for every distant person.
Implement the “AwarenessInfo” part to retrieve and show the attention info for every distant person from the view mannequin. The part will use the “useSelector” hook to retrieve the related info.
Implement the “updateUserAwarenessInfo” methodology within the “AwarenessViewModel” interface to dispatch a Redux motion to replace the attention info for every distant person. This methodology might be referred to as by the “MainWhiteboard” part.
When a distant person modifications the cursor location, dispatch the “updateUserAwarenessInfo” methodology within the “AwarenessViewModel” interface to replace the corresponding consciousness info.
Within the “AwarenessInfo” part, use the brand new location to animate the cursor change. This may be completed utilizing the Konva “Tween” animation.
Write checks for the brand new “AwarenessInfo” part, together with data-driven checks to make sure it correctly shows the attention info for all distant customers. The checks might be written utilizing the React Testing Library.
Write checks for the encapsulated view mannequin interface to make sure it correctly updates the attention info for distant customers. These checks will use the Vitest framework.
Write end-to-end Cypress checks to make sure the attention layer is correctly displayed and up to date when distant customers change their cursor location. The checks will simulate person interactions with the whiteboard and confirm the state of the “AwarenessLayer” and “AwarenessInfo” parts.

At this level, Xu Hao is able to ask ChatGPT to supply code for one among
the steps

present me instance checks and implementation for the attention slice
and AwarenessViewModel. Check first.

Positive, let's begin with writing checks for the attention slice and AwarenessViewModel:

Check for Consciousness Slice:

describe('consciousness slice', () => 
  let retailer: MockStore;
  beforeEach(() => 
    retailer = configureMockStore()(initialState);
  );

  it('ought to set the cursor location', () => 
    retailer.dispatch(setCursorLocation( x: 100, y: 200 ));
    const state = retailer.getState().consciousness;
    anticipate(state.cursorLocation).toEqual( x: 100, y: 200 );
  );

  it('ought to set the identify', () => 
    retailer.dispatch(setName('John Doe'));
    const state = retailer.getState().consciousness;
    anticipate(state.identify).toBe('John Doe');
  );

  it('ought to set the web standing', () => 
    retailer.dispatch(setOnline(true));
    const state = retailer.getState().consciousness;
    anticipate(state.isOnline).toBe(true);
  );
);
Check for AwarenessViewModel:

describe('AwarenessViewModel', () => 
  let retailer: MockStore;
  let awarenessViewModel: AwarenessViewModel;
  beforeEach(() => 
    retailer = configureMockStore()(initialState);
    awarenessViewModel = new AwarenessViewModel(retailer);
  );

  it('ought to set the cursor location', () => 
    awarenessViewModel.setCursorLocation( x: 100, y: 200 );
    const state = retailer.getState().consciousness;
    anticipate(state.cursorLocation).toEqual( x: 100, y: 200 );
  );

  it('ought to set the identify', () => 
    awarenessViewModel.setName('John Doe');
    const state = retailer.getState().consciousness;
    anticipate(state.identify).toBe('John Doe');
  );

  it('ought to set the web standing', () => 
    awarenessViewModel.setOnline(true);
    const state = retailer.getState().consciousness;
    anticipate(state.isOnline).toBe(true);
  );
);
Now, let's implement the Consciousness slice and AwarenessViewModel:

Consciousness slice:

interface AwarenessState 
  cursorLocation:  x: quantity; y: quantity ;
  identify: string;
  isOnline: boolean;


const initialState: AwarenessState = 
  cursorLocation:  x: 0, y: 0 ,
  identify: '',
  isOnline: false,
;

const awarenessSlice = createSlice(
  identify: 'consciousness',
  initialState,
  reducers: 
    setCursorLocation: (state, motion: PayloadAction) => 
      state.cursorLocation = motion.payload;
    ,
    setName: (state, motion: PayloadAction) => 
      state.identify = motion.payload;
    ,
    setOnline: (state, motion: PayloadAction) => 
      state.isOnline = motion.payload;
    ,
  ,
);

export const  setCursorLocation, setName, setOnline  = awarenessSlice.actions;

export default awarenessSlice.reducer;
AwarenessViewModel:

class AwarenessViewModel 
  non-public retailer: Retailer;

  constructor(retailer: Retailer) 
    this.retailer = retailer;
  

  setCursorLocation(cursorLocation:  x: quantity; y: quantity ) 
    this.retailer.dispatch(setCursorLocation(cursorLocation));
  

  setName(identify: string) 
    this.retailer.dispatch(setName(identify));
  

  setOnline(isOnline: boolean) 
    this.retailer.dispatch(setOnline(isOnline));
  


Be aware: On this implementation, I assumed that the AwarenessViewModel is used to
set the values within the retailer. If it's also used to retrieve the values from the
retailer, we are able to add corresponding strategies to the AwarenessViewModel class

(I’ve eliminated the styling from ChatGPT’s response.)

Total this code is neither unhealthy nor excellent. It will not run because it stands.
It is lacking a configureMockStore and assumes it makes use of
redux-mock-store, which is not a part of the tech stack. Xu Hao can repair these
issues by asking the LLM to progressively tweak the code by a
sequence of rewrites. This is one to get rig of redux-mock-store.

rewrite the checks with out redux-mock-store

Positive, here is an instance implementation of the checks for the AwarenessViewModel and the attention slice with out utilizing redux-mock-store:

import  createAwarenessSlice, AwarenessState, updateAwareness  from './awarenessSlice';
import  AwarenessViewModel  from './AwarenessViewModel';

describe('AwarenessViewModel', () => {
  const mockDispatch = jest.fn();
  const initialState: AwarenessState = 
    customers: 
      'user1': 
        identify: 'Person 1',
        cursorPosition:  x: 0, y: 0 ,
        on-line: true,
      ,
      'user2': 
        identify: 'Person 2',
        cursorPosition:  x: 100, y: 100 ,
        on-line: true,
      ,
    ,
  ;
  let viewModel: AwarenessViewModel;

  beforeEach(() => 
    viewModel = new AwarenessViewModel(initialState, mockDispatch);
  );

  describe('getUserNames', () => 
    it('returns the checklist of person names', () => 
      const names = viewModel.getUserNames();
      anticipate(names).toEqual(['User 1', 'User 2']);
    );
  );

  describe('getCursorPosition', () => 
    it('returns the cursor place for a given person ID', () => 
      const cursorPosition = viewModel.getCursorPosition('user1');
      anticipate(cursorPosition).toEqual( x: 0, y: 0 );
    );

    it('returns undefined for an unknown person ID', () => 
      const cursorPosition = viewModel.getCursorPosition('unknown');
      anticipate(cursorPosition).toBeUndefined();
    );
  );

  describe('updateCursorPosition', () => 
    it('dispatches the updateAwareness motion with the brand new cursor place', () => 
      viewModel.updateCursorPosition('user1',  x: 50, y: 50 );
      anticipate(mockDispatch).toHaveBeenCalledWith(updateAwareness(
        person: 'user1',
        cursorPosition:  x: 50, y: 50 ,
      ));
    );
  );
});

And here is an instance implementation of the awarenessSlice with out utilizing redux-mock-store:

import  createSlice, PayloadAction  from '@reduxjs/toolkit';

export sort CursorPosition =  x: quantity, y: quantity ;

export sort UserAwareness = 
  identify: string;
  cursorPosition: CursorPosition;
  on-line: boolean;
;

export sort AwarenessState = 
  customers: File<string, UserAwareness>;
;

const initialState: AwarenessState = 
  customers: ,
;

const awarenessSlice = createSlice(
  identify: 'consciousness',
  initialState,
  reducers: 
    updateAwareness: (state, motion: PayloadAction< person: string, cursorPosition: CursorPosition >) => 
      const  person, cursorPosition  = motion.payload;
      state.customers[user].cursorPosition = cursorPosition;
    ,
    setOnline: (state, motion: PayloadAction< person: string, on-line: boolean >) => 
      const  person, on-line  = motion.payload;
      state.customers[user].on-line = on-line;
    ,
  ,
);

export const  updateAwareness, setOnline  = awarenessSlice.actions;
export const awarenessReducer = awarenessSlice.reducer;

Be aware that since we’re not utilizing redux-mock-store, we have to move a mock dispatch perform to the view mannequin constructor, and within the take a look at for updateCursorPosition we have to verify that the proper motion was dispatched utilizing jest.fn().

Additional rewrites can match in additional changes, corresponding to asking it to
Use `configureTestingStore(‘consciousness’, initialState)` to initialize the take a look at retailer can get it to slot in with the crew’s take a look at idioms. Then
with some path changes and a small quantity of glue for the reducers, the
code can run simply advantageous.

As soon as that is working, Xu Hao can repeat the method for the remainder of the
duties within the grasp plan.

My take away from this dialogue was that utilizing chain of thought and
generated information prompting approaches generally is a considerably great tool
for programming. Particularly it exhibits that to make use of LLMs effectively, we have to
learn to assemble prompts to get one of the best outcomes. This expertise
means that it is helpful to work together with the LLM like a junior accomplice,
beginning them with architectural tips, asking them to point out their
reasoning, and tweaking their outputs as we go.