原文地址鏈接

https://mp.weixin.qq.com/s/QEId53_7tpt3BnGar6sxiA 

不懂代碼的小白通過Deepseek寫一個游戲

?https://chat.deepseek.com/coder 

注冊賬戶后登錄即可免費(fèi)使用。

今天我們嘗試寫一個貪食蛇的Python代碼。

提示詞：

寫一個貪食蛇的Python程序

將生成的代碼復(fù)制到VS Code中報錯。

將錯誤信息直接復(fù)制到DeepSeek Coder讓其識別并進(jìn)行修改。

import pygameimport random
# 初始化pygamepygame.init()
# 設(shè)置屏幕大小screen_width = 800screen_height = 600screen = pygame.display.set_mode((screen_width, screen_height))
# 設(shè)置顏色white = (255, 255, 255)yellow = (255, 255, 102)black = (0, 0, 0)red = (213, 50, 80)green = (0, 255, 0)blue = (50, 153, 213)
# 設(shè)置蛇的初始位置和大小snake_block = 10snake_speed = 15
# 設(shè)置字體font_style = pygame.font.SysFont(None, 30)

def message(msg, color):    mesg = font_style.render(msg, True, color)    screen.blit(mesg, [screen_width / 6, screen_height / 3])

def game_loop():    game_over = False    game_close = False
    x1 = screen_width / 2    y1 = screen_height / 2
    x1_change = 0    y1_change = 0
    snake_list = []    length_of_snake = 1
    foodx = round(random.randrange(0, screen_width - snake_block) / 10.0) * 10.0    foody = round(random.randrange(0, screen_height - snake_block) / 10.0) * 10.0
    while not game_over:
while not game_over:
        while game_close:            screen.fill(black)            message("You Lost! Press Q-Quit or C-Play Again", red)            pygame.display.update()
            for event in pygame.event.get():                if event.type == pygame.KEYDOWN:                    if event.key == pygame.K_q:                        game_over = True                        game_close = False                    if event.key == pygame.K_c:                        game_loop()
        for event in pygame.event.get():            if event.type == pygame.QUIT:                game_over = True            if event.type == pygame.KEYDOWN:                if event.key == pygame.K_LEFT:                    x1_change = -snake_block                    y1_change = 0                elif event.key == pygame.K_RIGHT:                    x1_change = snake_block                    y1_change = 0                elif event.key == pygame.K_UP:                    y1_change = -snake_block                    x1_change = 0                elif event.key == pygame.K_DOWN:      x1_change = 0

        if x1 >= screen_width or x1 < 0 or y1 >= screen_height or y1 < 0:            game_close = True
        x1 += x1_change        y1 += y1_change        screen.fill(blue)        pygame.draw.rect(screen, green, [foodx, foody, snake_block, snake_block])
這次修正后游戲正常，最后的按鍵也沒有問題了。



        snake_head = []        snake_head.append(x1)        snake_head.append(y1)        snake_list.append(snake_head)        if len(snake_list) > length_of_snake:            del snake_list[0]
        for x in snake_list[:-1]:            if x == snake_head:                game_close = True
        our_snake(snake_block, snake_list)        your_score(length_of_snake - 1)
        pygame.display.update()
        if x1 == foodx and y1 == foody:            foodx = round(random.randrange(0, screen_width - snake_block) / 10.0) * 10.0            foody = round(random.randrange(0, screen_height - snake_block) / 10.0) * 10.0            length_of_snake += 1
        pygame.time.Clock().tick(snake_speed)
    pygame.quit()    quit()

def our_snake(snake_block, snake_list):    for x in snake_list:        pygame.draw.rect(screen, black, [x[0], x[1], snake_block, snake_block])

def your_score(score):    value = font_style.render("Your Score: " + str(score), True, yellow)    screen.blit(value, [0, 0])

game_loop()              

游戲重新開始后，貪食蛇和食物的位置隨機(jī)發(fā)生變化。

DeepSeek Coder 給我的體驗(yàn)是相當(dāng)絲滑的，不懂代碼的話進(jìn)行直接語言交互和反饋就能到達(dá)最終的效果。

DeepSeek Coder是私募巨頭幻方量化發(fā)布的第一代大模型，它是一款基于深度學(xué)習(xí)的編程語言處理模型，能夠進(jìn)行代碼生成、數(shù)學(xué)推理等多種任務(wù)。該模型已經(jīng)開源，并且包含了不同規(guī)模的版本，如1B、7B、33B等，以及Base模型和指令調(diào)優(yōu)模型。

在國際權(quán)威數(shù)據(jù)集HumanEval上的編程多語言測試中，DeepSeek Coder的表現(xiàn)領(lǐng)先于現(xiàn)有的開源模型。特別是在代碼生成任務(wù)上，DeepSeek Coder分別在HumanEval、MBPP和DS-1000數(shù)據(jù)集上優(yōu)于此前最好的開源大模型CodeLlama。此外，DeepSeek Coder還展示了出色的數(shù)學(xué)和推理能力。

該模型的發(fā)布標(biāo)志著幻方量化在探索人工通用智能（AGI）本質(zhì)的道路上取得了階段性成果。

。