An instance of LLM prompting for programming

Lately I watched a captivating 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 an internet 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
exams for view.

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

There are 2 sorts
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 below 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), except for international native view mannequin, which can 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 would use ‘createSelector’ and
‘useSelector’ for memorization. Examined in vitest and react testing
library.

4. Don’t dispatch motion instantly to vary the states of shared view
mannequin, use an encapsulated view mannequin interface as a substitute. 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 by way of
react-konva. Examined in cypress part exams 

Listed below are sure patterns needs to be adopted when implement and check
the part

1. When write check, use `describe` as a substitute of `check`

2. Information-driven exams are most popular.

3. When check the view part, faux view mannequin by way of the view mannequin
interface

Consciousness Layer 

Requirement: 

Show different customers’ consciousness data(cursor, title 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 steering talked about above.
Trace, hold all consciousness info in a Konva layer, and an consciousness
data part to render cursor, and title. Don’t generate code. Describe
the answer, and breaking the answer down as a job checklist based mostly on the
steering talked about above. And we'll refer this job checklist as our grasp
plan.

There’s loads happening with this immediate, so he highlighted a couple of
factors.

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

Many 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, trying 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
group.

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

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

A standard approach of interacting with an LLM is to offer it an issue and ask
it to generate some ultimate product, whether or not than be prose or (on this case)
code. With Generated Data we cut 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 attention-grabbing a part of the immediate is the “implementation technique”
part which mixes two kinds of immediate:

• Instruction prompting supplies 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.

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 factor of the response is an ordered job checklist, with numbers for
every step. We are able to use these numbers to refer to those duties for the remainder of
the session.

The LLM responds with a plan.

Xu Hao can now take a look at the grasp plan and see if it is sensible. If
there are issues with it, he can ask ChatGPT to re-write a few of 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 potential immediate may be:

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

This may very well be helpful to confirm the alignment between the structure
imaginative and prescient and grasp plan.

These tweaks may very well 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 have been added in later iteration:

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

As soon as the grasp plan appears to be like 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

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

present me instance exams and implementation for the attention slice
and AwarenessViewModel. Take a look at first.

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

Take a look at 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 title', () => 
    retailer.dispatch(setName('John Doe'));
    const state = retailer.getState().consciousness;
    anticipate(state.title).toBe('John Doe');
  );

  it('ought to set the web standing', () => 
    retailer.dispatch(setOnline(true));
    const state = retailer.getState().consciousness;
    anticipate(state.isOnline).toBe(true);
  );
);
Take a look at 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 title', () => 
    awarenessViewModel.setName('John Doe');
    const state = retailer.getState().consciousness;
    anticipate(state.title).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 ;
  title: string;
  isOnline: boolean;


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

const awarenessSlice = createSlice(
  title: 'consciousness',
  initialState,
  reducers: 
    setCursorLocation: (state, motion: PayloadAction) => 
      state.cursorLocation = motion.payload;
    ,
    setName: (state, motion: PayloadAction) => 
      state.title = 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(title: string) 
    this.retailer.dispatch(setName(title));
  

  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 dangerous nor good. 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. Here is one to get rig of redux-mock-store.

rewrite the exams with out redux-mock-store

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

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

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

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

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

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

const initialState: AwarenessState = 
  customers: ,
;

const awarenessSlice = createSlice(
  title: '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;

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

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