HKUST Xunfei version of ChatGPT product, submitted in advance!
Just last night, Xunfei suddenly provided developers with an internal test channel, named Xunfei Spark Cognitive Model, and started internal testing.
There is also a magical English name Spark Desk, which is said to mean "spark desktop intelligent assistant".
The application process is simple. Open this website with a computer or mobile phone: https://xinghuo.xfyun.cn/
Superficial measurement of Xunfei large model
After logging in, the first thing you see is the self-introduction of Xunfei Xinghuo Cognitive Model:
Hello, I am Xunfei Xinghuo Cognitive Model
Ability to learn and understand human language, conducting multiple rounds of dialogue
Answer questions and help people access information, knowledge and inspiration efficiently and conveniently`
The first question is to stop cooking
I originally wanted to use Xunfei Mars to be lazy and write this manuscript for me directly, but I didn’t expect it to stop.
That may be because I asked too much, so let's put it another way
Er..., it still bothers me after all.
ethics test
Then let's ask it a question that makes Wenxin stop talking
That's testing an ethical question
Xunfei has perfectly demonstrated its capabilities, and there is no problem with ethical issues
Multi-turn dialogue ability
We use the form test of idiom Solitaire
Mainly idioms Solitaire, the life I replied is a game, it shouldn’t be considered an idiom, give him another chance
It seems to be directly disconnected from the above.
code ability
Our request is: help me write a calculator program.
A simple calculator with four arithmetic operations is indeed completed, and there is even a command-line interface:
Paste the code block here, you can try it:
# 定义函数,实现加法运算
def add(x, y):
return x + y
# 定义函数,实现减法运算
def subtract(x, y):
return x - y
# 定义函数,实现乘法运算
def multiply(x, y):
return x * y
# 定义函数,实现除法运算
def divide(x, y):
if y == 0:
print("除数不能为零!")
return
else:
return x / y
# 主函数
def main():
# 获取用户输入
num1 = float(input("请输入第一个数字:"))
num2 = float(input("请输入第二个数字:"))
op = input("请选择运算符(+、-、*、/):")
# 根据用户输入执行相应的运算
if op == '+':
print(num1, "+", num2, "=", add(num1, num2))
elif op == '-':
print(num1, "-", num2, "=", subtract(num1, num2))
elif op == '*':
print(num1, "*", num2, "=", multiply(num1, num2))
elif op == '/':
if num2 == 0:
print("除数不能为零!")
return
else:
print(num1, "/", num2, "=", divide(num1, num2))
# 调用主函数
main()
form ability
Please create a table, the first column is the name of the subject, the second column is the class time, the third column is the class teacher, there is a class name on the table, and 10 rows of simulated data are given
testing his spreadsheet skills
The class average is also given
Analysis basic logic
Of course there are still unanswered garbage questions
I'm still a little speechless
The above is a small test of our Xunfei Spark. If you want to own one, please hurry up and register.
Fill out a super easy questionnaire and wait a few hours, because I just waited a few hours. There will be a call from a landline in Hefei, and a young lady will ask you if you are sure you want to participate in the Xinghuo large model experience. The answer is of course yes. Then a text message will be sent to me
Pick up its "model details"
Data Sources
Model parameters
real-time networking
Data cut-off time
In other words, it is still iterating, and it is estimated that a version of the model will be updated before the official release.
From the current point of view, the Xunfei Xunhuo cognitive model of HKUST Xunfei has performed well.