An instance of LLM prompting for programming

Lately I watched a captivating name on Zoom. Xu Hao, Thoughtworks’s
Head of Know-how in China, defined his explorations in utilizing ChatGPT to
assist construct Self Testing Code. He
went by way of the form of interplay that works for him.

He begins with a immediate that units the context for the appliance and the way
he needs 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 element
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 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 consumer

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 element props or states(by
useState hook), except for world 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 information from shared
view mannequin. For many the case, it'll use ‘createSelector’ and
‘useSelector’ for memorization. Examined in vitest and react testing
library.

4. Don’t dispatch motion straight to vary 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 encompass konva shapes, and carried out as react element by way of
react-konva. Examined in cypress element checks 

Listed here are sure patterns ought to be adopted when implement and check
the element

1. When write check, use `describe` as an alternative of `check`

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

3. When check the view element, pretend view mannequin by way of 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 consumer

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

Present an total resolution following the steering talked about above.
Trace, preserve all consciousness info in a Konva layer, and an consciousness
information element to render cursor, and identify. Don’t generate code. Describe
the answer, and breaking the answer down as a process checklist primarily based on the
steering talked about above. And we'll refer this process checklist as our grasp
plan.

There’s loads occurring with this immediate, so he highlighted just a few
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 might be a
safety threat. Enterprise guidelines, any code from an actual challenge – all these should
not enter the interplay with ChatGPT.

Many of the immediate is setting out the design tips that he needs
ChatGPT’s generated code to comply with. He refined this by placing prompts into
ChatGPT, trying on the end result, and crafting the immediate to make it generate
within the type 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
workforce.

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

Regardless that the ultimate aim of this session is to generate code and its
checks, at this stage he particularly stated Don’t generate code.
At this level he needs ChatGPT to stipulate its strategy earlier than we glance to any
code technology. This can be a immediate method known as Generated Data.

A typical approach of interacting with an LLM is to provide 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 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.

Probably the most attention-grabbing a part of the immediate is the “implementation technique”
part which mixes two types of immediate:

• Instruction prompting gives directions for the LLM to comply with
• Chain of Thought prompting encourages the LLM to clarify its
  reasoning.

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

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

The important thing aspect of the response is an ordered process 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 number of the duties
or the whole grasp plan by offering extra info.

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

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

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 total
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 straight to vary 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 cheap, Xu Hao asks to regenerate it with
names for this system parts.

Rewrite the grasp plan, this time with detailed element 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 checks and implementation for the notice slice
and AwarenessViewModel. Take a look at first.

Certain, let's begin with writing checks for the notice 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;
    count on(state.cursorLocation).toEqual( x: 100, y: 200 );
  );

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

  it('ought to set the net standing', () => 
    retailer.dispatch(setOnline(true));
    const state = retailer.getState().consciousness;
    count on(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;
    count on(state.cursorLocation).toEqual( x: 100, y: 200 );
  );

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

  it('ought to set the net standing', () => 
    awarenessViewModel.setOnline(true);
    const state = retailer.getState().consciousness;
    count on(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));
  


Word: 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 will add corresponding strategies to the AwarenessViewModel class

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

General 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 way of a
sequence of rewrites. This is one to get rig of redux-mock-store.

rewrite the checks 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': 
        identify: 'Consumer 1',
        cursorPosition:  x: 0, y: 0 ,
        on-line: true,
      ,
      'user2': 
        identify: 'Consumer 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 consumer names', () => 
      const names = viewModel.getUserNames();
      count on(names).toEqual(['User 1', 'User 2']);
    );
  );

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

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

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

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

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

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

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

const initialState: AwarenessState = 
  customers: ,
;

const awarenessSlice = createSlice(
  identify: 'consciousness',
  initialState,
  reducers: 
    updateAwareness: (state, motion: PayloadAction< consumer: string, cursorPosition: CursorPosition >) => 
      const  consumer, cursorPosition  = motion.payload;
      state.customers[user].cursorPosition = cursorPosition;
    ,
    setOnline: (state, motion: PayloadAction< consumer: string, on-line: boolean >) => 
      const  consumer, 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, akin to asking it to
Use `configureTestingStore(‘consciousness’, initialState)` to initialize
the check retailer can get it to slot in with the workforce’s check idioms. Then
with some path changes and a small quantity of glue for the reducers, the
code can run simply tremendous.

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