淘客熙熙

主题:【原创】深入谈一下chatGPT对我们我国的重大影响 -- 东东山

共:💬200 🌺1876 🌵20 新:
分页树展主题 · 全看首页 上页
/ 14
下页 末页
    • 家园 不颂圣的时候写的挺好
    • 家园 解决美国再工业化的难题怕没这么简单

      工业化目前看总是需要人动手的,它能解决动脑的问题,还能解决动手的问题?

      这得靠机器人了

      这么几亿人持续调教下来,搞出自我意识估计快了?😅

      这次人家不开源,百度阿里能不能迎头赶上就很值得期待了

      • 家园 说起国内这些互联网公司就让人来气

        要么跟在别人后面抄,要么刚挣点钱就乱动心思,比如搞互联网金融放高利贷挣快钱,一副土财主的样子。别人家的资本家靠技术挣钱,这帮人有几个安心搞技术的?老是盯着别人又搞出来什么好东西,自己去拿现成, 都亿万家产了还是一副猥琐相,难怪被人鄙视。

        • 家园 风气就这样,从上到下都这样

          这个社会早就不讲什么理想之类的

          所以这个社会也不提倡理想什么的

          什么环境,自然结什么果

          有理想的,被筛选掉,都死了

          通宝推:真离,

          本帖一共被 1 帖 引用 (帖内工具实现)
        • 家园 气也没用,人家硅谷创业潮从上世纪80、90年代就开始

          已经有超过几十年的积累,中国的创业潮才多少年?美国的高科技互联网泡沫已经破灭过一次,已经挤过一次泡沫了,现在能留下来的肯定有不凡之处,而中国的高科技互联网泡沫还没破灭过,整个行业没有经过市场的筛选,所以鱼龙混杂,乱七八糟。

          现在国内所谓的高科技互联网企业根本就没有创新和搞技术的心,就算有心也没能力,有心也有能力,整个社会环境也不会给他们机会,所以他们只能抄。在我看来,要是能抄得好都算大功一件了。

          本人对国内现在所谓的“互联网”、“高科技”巨头一点期待都没有,只是希望他们不要掉队,不要被外面甩得太远。也正因为没有什么期待,所以一旦能拿出一点成绩我反而会夸一夸。

    • 家园 这篇有很多真知灼见
    • 家园 终于在这个时间连上了,做了个测试 -- 有补充

      If I have N recorders to record sounds in a room, and there are M people talking in the same room, N>M+5. Potentially there may be noises from cars outside. Could you give me some python code to demix the voices of these people from the recorded sounds?

      This is a complex problem that requires expertise in signal processing and machine learning. The task of demixing multiple sources from a single recording is referred to as "blind source separation".

      One common approach to solve this problem is to use Independent Component Analysis (ICA). ICA is a statistical technique that aims to separate a multivariate signal into independent non-Gaussian components.

      Here is a sample code to perform ICA on a signal using the FastICA library in Python:

      import numpy as np
      from scipy.io import wavfile
      from sklearn.decomposition import FastICA
      # Load the audio data into a numpy array
      rate, data = wavfile.read('input_signal.wav')
      # Reshape the data into a matrix, where each row represents a time frame
      samples, channels = data.shape
      data = data.reshape((samples, channels))
      # Perform ICA
      ica = FastICA(n_components=M)
      sources = ica.fit_transform(data)
      # Save the separated sources
      for i in range(M):
       wavfile.write('source_{}.wav'.format(i), rate, sources[:, i])
      

      Note that this is just an example code, and the actual performance will depend on the specifics of your data and the quality of separation achieved by the ICA algorithm. It is common to perform preprocessing on the data before applying ICA, such as filtering to remove low-frequency noise, or normalizing the data to improve the stability of the ICA algorithm. Additionally, it may be necessary to manually inspect the separated sources and perform additional post-processing steps to obtain the desired output.

      Could you give me an example python code to filter out noises from an airplane?

      Here is an example code to filter out the airplane noise from a signal in Python:

      import numpy as np
      import matplotlib.pyplot as plt
      import scipy.signal as signal
      # Load the signal
      fs, data = wavfile.read("airplane_noise.wav")
      # Design a Butterworth band-stop filter to remove airplane noise
      f0 = [1000, 6000] # Cutoff frequencies
      b, a = signal.butter(3, f0, btype="bandstop", fs=fs)
      # Apply the filter to the data
      filtered_data = signal.filtfilt(b, a, data)
      # Plot the original and filtered signals
      plt.figure(figsize=(12, 6))
      plt.plot(data, label="Original")
      plt.plot(filtered_data, label="Filtered")
      plt.xlabel("Sample")
      plt.ylabel("Amplitude")
      plt.legend()
      plt.show()
      

      Note: The above code assumes that the airplane noise is centered around 1000 to 6000 Hz. The cutoff frequencies and the order of the Butterworth filter can be adjusted to achieve better results. Also, this code uses the filtfilt function from the scipy.signal library to apply the filter, which is a zero-phase filter that doesn't cause phase shift in the filtered signal.

      通宝推:方平,
      作者 对本帖的 补充(1)
      家园 感觉对于低端脑力劳动者是个帮助 -- 补充帖

      你提问题它给思路,但是还是不能替代。以后码农可能会是一个产品经理和AI之间的翻译工作。

    • 见前补充 4858572
    • 家园 ai的前景也许没有想象中的乐观

      我更看好新能源(核聚变/储电技术)、新资源(人造物质)、量子技术的前景。

      • 家园 这几个不是相互对立是相辅相成的,现在尖端学科都是互相交叉的

        研究新能源新资源量子技术很可能需要人工智能的帮助,而人工智能的突破也许需要新材料量子技术的突破

    • 家园 人工智能的数据重要性要大于模型吧,中国也就这两年重视数据安全

      你读读人工智能的论文,大多是模型跟代码给你写的明明白白的,但是数据集比较语焉不详

      美国有全球的互联网平台,可以用全球的数据做训练。中国只能用国内的数据做训练,最多加上点周边东南亚国家的数据,抖音的数据还无法回传,虽然中国人口众多,但是跟全球人口还是没法比。至于老欧洲?已经沦为数据农场了,他们的数据他们说了不算的。

    • 家园 不吃大亏,不可能改变

      这种大亏要大到大家不可想像,提起来好几辈子人都得记住。清末的教训也刚刚100年,现在人大都对外面的新技术新应用不屑一顾,提起来什么东西,我天朝都有,即使现在不能用,百度也说了,三个月以后就可以了。实在没有,我们可以对着这个CHATGPT泼屎尿就可以让其不能失效。

      通宝推:达雅,
      • 家园 没必要随便抓个东西就要中国反思

        不知你对自己是否如此要求,比如同龄人有比你成功的多的,你是否每天反思自己了呢

        对新技术的排斥更多的与年龄相关,老人往往偏保守一些。另外过去类似的牛逼也吹了很多,后来好多也证明没有那么神,一些人有怀疑态度也是正常的。

        这东西我和身边朋友早就试过了,比过去的产品的确提高了很多,但具体的实际用途还要观察。

        美国作为唯一的帝国,某些最尖端的东西他先弄出来是很正常的,我不知道有个鸡巴毛可以反思的。先跟上,如果有前途就继续追加,我看也就可以了。

        通宝推:journal,
分页树展主题 · 全看首页 上页
/ 14
下页 末页


有趣有益,互惠互利;开阔视野,博采众长。
虚拟的网络,真实的人。天南地北客,相逢皆朋友

Copyright © cchere 西西河