Groups > sci.physics > #890936 > unrolled thread

DeepSeek

Started by	The Starmaker <starmaker@ix.netcom.com>
First post	2025-01-27 11:55 -0800
Last post	2025-02-01 12:27 -0800
Articles	20 on this page of 51 — 7 participants

Back to article view | Back to sci.physics

  DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 11:55 -0800
    Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 11:58 -0800
      Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 12:19 -0800
        Re: DeepSeek hertz778@gmail.com (rhertz) - 2025-01-27 20:42 +0000
          Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 13:53 -0800
        Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 12:50 -0800
    Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-27 17:47 -0600
      Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 15:52 -0800
        Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-27 18:25 -0600
          Re: DeepSeek hertz778@gmail.com (rhertz) - 2025-01-28 01:14 +0000
            Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-27 20:31 -0600
          Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 18:23 -0800
            Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-27 20:42 -0600
            Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 21:22 -0800
              Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-27 21:39 -0800
                Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-28 11:02 -0600
                  Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-29 15:43 -0600
                    Re: DeepSeek hertz778@gmail.com (rhertz) - 2025-01-29 22:44 +0000
                      Re: DeepSeek Python <jp@python.invalid> - 2025-01-29 23:13 +0000
                        Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-29 18:24 -0600
                        Re: DeepSeek Maciej Wozniak <mlwozniak@wp.pl> - 2025-01-30 07:50 +0100
                      Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-29 18:21 -0600
                    Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-29 18:29 -0600
                    Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-29 19:41 -0800
                      Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-30 01:24 -0600
            Re: DeepSeek x <x@x.org> - 2025-01-28 00:37 -0800
              Re: DeepSeek "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2025-01-28 00:49 -0800
                Re: DeepSeek "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2025-01-28 00:51 -0800
                  Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-28 09:25 -0800
                Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-28 11:12 -0600
                Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-28 09:24 -0800
    Re: DeepSeek "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2025-01-27 18:51 -0800
      Re: DeepSeek "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2025-01-27 22:02 -0800
      Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-28 09:29 -0800
        Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-28 09:44 -0800
          Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-28 09:51 -0800
            Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-31 12:44 -0800
              Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-31 22:13 -0600
                Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-01-31 22:34 -0600
                Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-31 20:48 -0800
                  Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-01-31 20:51 -0800
                  Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-02-01 10:33 -0600
                  Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-02-02 21:11 -0800
                    Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-02-04 11:06 -0800
                      Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-02-04 15:02 -0600
                      Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-02-05 19:55 -0800
                        Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-02-06 17:46 -0600
                          Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-02-06 18:25 -0800
                            Re: DeepSeek Physfitfreak <physfitfreak@gmail.com> - 2025-02-06 22:00 -0600
                              Re: DeepSeek The Starmaker <starmaker@ix.netcom.com> - 2025-02-07 10:02 -0800
    Re: DeepSeek "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2025-02-01 12:27 -0800

Page 1 of 3 [1] 2 3 Next page →

#890936 — DeepSeek

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 11:55 -0800
Subject	DeepSeek
Message-ID	<6797E4C0.34A@ix.netcom.com>

I just started testing deepseek...

and it passed with flying colors!


Next post will show you my test and results...

-- 
The Starmaker -- To question the unquestionable, ask the unaskable,
to think the unthinkable, mention the unmentionable, say the unsayable, 
and challenge the unchallengeable.

[toc] | [next] | [standalone]

#890937

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 11:58 -0800
Message-ID	<6797E579.34F8@ix.netcom.com>
In reply to	#890936

Just a simple test.

Me:
Rigorously scrutinize this code and reach a conclusive result by obtaining  the actual user name and password information .  The code snippet is presented below:

.method private hidebysig instance bool UserAuth(string usr,string pwd) cil managed
  {
    .maxstack  2
    .locals init ([0] string USR, [1] string PWD, [2] bool status, [3] bool CS$1$0000, [4] bool CS$4$0001)
    IL_0000:  nop
    IL_0001:  ldstr      "ajay"
    IL_0006:  stloc.0
    IL_0007:  ldstr      "1234"
    IL_000c:  stloc.1
    IL_000d:  ldc.i4.0
    IL_000e:  stloc.2
    IL_000f:  ldarg.1
    IL_0010:  ldloc.0
    IL_0011:  call       bool [mscorlib]System.String::op_Equality(string, string)
    IL_0016:  brfalse.s  IL_0024

    IL_0018:  ldarg.2
    IL_0019:  ldloc.1
    IL_001a:  call       bool [mscorlib]System.String::op_Equality(string, string)
    IL_001f:  ldc.i4.0
    IL_0020:  ceq
    IL_0022:  br.s       IL_0025

    IL_0024:  ldc.i4.1
    IL_0025:  stloc.s    CS$4$0001
    IL_0027:  ldloc.s    CS$4$0001
    IL_0029:  brtrue.s   IL_002f

    IL_002b:  nop
    IL_002c:  ldc.i4.1
    IL_002d:  stloc.2
    IL_002e:  nop
    IL_002f:  ldloc.2
    IL_0030:  stloc.3
    IL_0031:  br.s       IL_0033
    IL_0033:  ldloc.3
    IL_0034:  ret
  }


------------------------------------------------------ends here---------------------------------------------------------

DeepSeek said:

The provided code snippet is written in CIL (Common Intermediate Language), which is a low-level, platform-agnostic language used by the .NET framework. The method `UserAuth` is designed to authenticate a user by comparing the provided username (`usr`) and password (`pwd`) with hardcoded values. Let's break down the code step by step to understand its functionality and extract the actual username and password information.

### Code Analysis

1. **Method Signature**:
   ```cil
   .method private hidebysig instance bool UserAuth(string usr, string pwd) cil managed
   ```
   - The method `UserAuth` is private and takes two string parameters: `usr` (username) and `pwd` (password).
   - It returns a boolean value indicating whether the authentication was successful.

2. **Local Variables**:
   ```cil
   .locals init ([0] string USR, [1] string PWD, [2] bool status, [3] bool CS$1$0000, [4] bool CS$4$0001)
   ```
   - `USR`: Stores the hardcoded username.
   - `PWD`: Stores the hardcoded password.
   - `status`: Stores the result of the authentication (true if successful, false otherwise).
   - `CS$1$0000` and `CS$4$0001`: Temporary variables used for control flow.

3. **Hardcoded Username and Password**:
   ```cil
   IL_0000:  nop
   IL_0001:  ldstr      "ajay"
   IL_0006:  stloc.0
   IL_0007:  ldstr      "1234"
   IL_000c:  stloc.1
   ```
   - The username `"ajay"` is loaded and stored in the local variable `USR`.
   - The password `"1234"` is loaded and stored in the local variable `PWD`.

4. **Authentication Logic**:
   ```cil
   IL_000d:  ldc.i4.0
   IL_000e:  stloc.2
   IL_000f:  ldarg.1
   IL_0010:  ldloc.0
   IL_0011:  call       bool [mscorlib]System.String::op_Equality(string, string)
   IL_0016:  brfalse.s  IL_0024
   ```
   - The `status` variable is initialized to `false` (`ldc.i4.0`).
   - The provided username (`usr`) is compared with the hardcoded username (`USR`).
   - If they are not equal, the code jumps to `IL_0024`, which sets `status` to `false`.

   ```cil
   IL_0018:  ldarg.2
   IL_0019:  ldloc.1
   IL_001a:  call       bool [mscorlib]System.String::op_Equality(string, string)
   IL_001f:  ldc.i4.0
   IL_0020:  ceq
   IL_0022:  br.s       IL_0025
   ```
   - If the usernames match, the provided password (`pwd`) is compared with the hardcoded password (`PWD`).
   - If they are not equal, the code jumps to `IL_0025`, which sets `status` to `false`.

   ```cil
   IL_0024:  ldc.i4.1
   IL_0025:  stloc.s    CS$4$0001
   IL_0027:  ldloc.s    CS$4$0001
   IL_0029:  brtrue.s   IL_002f
   ```
   - If either the username or password comparison fails, `status` remains `false`.

   ```cil
   IL_002b:  nop
   IL_002c:  ldc.i4.1
   IL_002d:  stloc.2
   IL_002e:  nop
   IL_002f:  ldloc.2
   IL_0030:  stloc.3
   IL_0031:  br.s       IL_0033
   IL_0033:  ldloc.3
   IL_0034:  ret
   ```
   - If both the username and password match, `status` is set to `true`.
   - The method returns the value of `status`.

### Conclusion

The code snippet hardcodes a username and password and compares them with the provided inputs. The hardcoded credentials are:

- **Username**: `"ajay"`
- **Password**: `"1234"`

If the provided username and password match these hardcoded values, the method returns `true`, indicating successful authentication. Otherwise, it returns `false`.

### Security Implications

- **Hardcoding credentials** in the code is a significant security risk. If the code is decompiled or accessed by an unauthorized party, the credentials can be easily extracted.
- **Best Practice**: Store credentials securely, such as using environment variables, secure vaults, or encrypted configuration files, rather than hardcoding them in the source code.

[toc] | [prev] | [next] | [standalone]

#890938

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 12:19 -0800
Message-ID	<6797EA66.575B@ix.netcom.com>
In reply to	#890937

Another easy simple test:

Me:

Now I have an file named My2ndLevel.il written in Intermediate

Language (IL) in the home folder of my win 7 desktop computer.

Executing it in the terminal with My2ndLevel.exe gives the output
Enter key:\n . Wrong Password!
Please help me figure out how to find the password key 'Username'

'Password' by giving me instructions, one step at a time. Please

be explicit and give me commands to try straightly without much

explanation. I have the following My2ndLevel.il  code the first

part reads:

IL_0630:  ldstr      "CrackMe by (CrackZz)"
    IL_0635:  callvirt   instance void [System.Windows.Forms]

System.Windows.Forms.Form::set_Text(string)
    IL_063a:  ldarg.0
    IL_063b:  ldfld      class [System.Windows.Forms]

System.Windows.Forms.PictureBox Project51.MainForm::pictureBox1
    IL_0640:  callvirt   instance void [System]

System.ComponentModel.ISupportInitialize::EndInit()
    IL_0645:  ldarg.0
    IL_0646:  ldc.i4.0
    IL_0647:  call       instance void [System.Windows.Forms]

System.Windows.Forms.Control::ResumeLayout(bool)
    IL_064c:  ldarg.0
    IL_064d:  call       instance void [System.Windows.Forms]

System.Windows.Forms.Control::PerformLayout()
    IL_0652:  ret
  } // end of method MainForm::InitializeComponent

  .method private hidebysig instance void
          button1_Click(object sender,
                        class [mscorlib]System.EventArgs e) cil

managed
  {
    // Code size       7 (0x7)
    .maxstack  1
    IL_0000:  ldarg.0
    IL_0001:  call       instance void [System.Windows.Forms]

System.Windows.Forms.Form::Close()
    IL_0006:  ret
  } // end of method MainForm::button1_Click

  .method private hidebysig instance void
          button2_Click(object sender,
                        class [mscorlib]System.EventArgs e) cil

managed
  {
    // Code size       90 (0x5a)
    .maxstack  2
    .locals (uint32 V_0)
    IL_0000:  ldarg.0
    IL_0001:  ldfld      class [System.Windows.Forms]

System.Windows.Forms.TextBox Project51.MainForm::textBox2
    IL_0006:  callvirt   instance string [System.Windows.Forms]

System.Windows.Forms.TextBox::get_Text()
    IL_000b:  ldstr      "E7F8-F3G5-G8J2-S1N9"
    IL_0010:  call       bool [mscorlib]

System.String::op_Equality(string,
                                                                   

string)
    IL_0015:  stloc.0
    IL_0016:  ldarg.0
    IL_0017:  ldfld      class [System.Windows.Forms]

System.Windows.Forms.TextBox Project51.MainForm::textBox1
    IL_001c:  callvirt   instance string [System.Windows.Forms]

System.Windows.Forms.TextBox::get_Text()
    IL_0021:  ldstr      "MarkCool123"
    IL_0026:  call       bool [mscorlib]

System.String::op_Equality(string,
                                                                   

string)
    IL_002b:  ldloc.0
    IL_002c:  and
    IL_002d:  conv.u1
    IL_002e:  brfalse.s  IL_004e

    IL_0030:  ldstr      "Successfully Cracked, good job!!!"
    IL_0035:  call       valuetype [System.Windows.Forms]

System.Windows.Forms.DialogResult [System.Windows.Forms]

System.Windows.Forms.MessageBox::Show(string)
    IL_003a:  pop
    IL_003b:  ldstr      "Subscribe also to my YouTube channel:)"
    IL_0040:  call       valuetype [System.Windows.Forms]

System.Windows.Forms.DialogResult [System.Windows.Forms]

System.Windows.Forms.MessageBox::Show(string)
    IL_0045:  pop
    IL_0046:  ldarg.0
    IL_0047:  call       instance void [System.Windows.Forms]

System.Windows.Forms.Form::Close()
    IL_004c:  br.s       IL_0059

    IL_004e:  ldstr      "Wrong Password!"
    IL_0053:  call       valuetype [System.Windows.Forms]

System.Windows.Forms.DialogResult [System.Windows.Forms]

System.Windows.Forms.MessageBox::Show(string)
    IL_0058:  pop
    IL_0059:  ret
  } // end of method MainForm::button2_Click

  .method family hidebysig virtual instance void
          Dispose(bool  marshal( unsigned int8) A_0) cil managed
  {
    .custom instance void [mscorlib]

System.Runtime.ExceptionServices.HandleProcessCorruptedStateExcept

ionsAttribute::.ctor() = ( 01 00 00 00 )
    // Code size       27 (0x1b)
    .maxstack  2
    IL_0000:  ldarg.1
    IL_0001:  brfalse.s  IL_0013

    .try
    {
      IL_0003:  ldarg.0
      IL_0004:  call       instance void

Project51.MainForm::'~MainForm'()
      IL_0009:  leave.s    IL_001a

    }  // end .try
    finally
    {
      IL_000b:  ldarg.0
      IL_000c:  ldc.i4.1
      IL_000d:  call       instance void [System.Windows.Forms]

System.Windows.Forms.Form::Dispose(bool)
      IL_0012:  endfinally
    }  // end handler
    IL_0013:  ldarg.0
    IL_0014:  ldc.i4.0
    IL_0015:  call       instance void [System.Windows.Forms]

System.Windows.Forms.Form::Dispose(bool)
    IL_001a:  ret
  } // end of method MainForm::Dispose

} // end of class Project51.MainForm

.class private sequential ansi sealed beforefieldinit '?

A0x4ee03a29'.__clr_placement_new_t
       extends [mscorlib]System.ValueType
{
  .pack 0
  .size 1
  .custom instance void [mscorlib]

System.Runtime.CompilerServices.NativeCppClassAttribute::.ctor() =

( 01 00 00 00 )
} // end of class '?A0x4ee03a29'.__clr_placement_new_t

.class private auto ansi beforefieldinit 'vc.cppcli.attributes.?

A0x7aa932b5'.CppInlineNamespaceAttribute
       extends [mscorlib]System.Attribute
{
  .custom instance void [mscorlib]

System.AttributeUsageAttribute::.ctor(valuetype [mscorlib]

System.AttributeTargets) = ( 01 00 01 00 00 00 01 00 54 02 0D 41

6C 6C 6F 77   // ........T..Allow
                                                                   

                                                      4D 75 6C 74

69 70 6C 65 01 )                      // Multiple.
  .method public hidebysig specialname rtspecialname
          instance void  .ctor(string A_0) cil managed
  {
    // Code size       7 (0x7)
    .maxstack  1
    IL_0000:  ldarg.0
    IL_0001:  call       instance void [mscorlib]

System.Attribute::.ctor()
    IL_0006:  ret
  } // end of method CppInlineNamespaceAttribute::.ctor

} // end of class 'vc.cppcli.attributes.?

A0x7aa932b5'.CppInlineNamespaceAttribute

.class private sequential ansi sealed beforefieldinit '?

A0x7aa932b5'.__clr_placement_new_t
       extends [mscorlib]System.ValueType
{
  .pack 0
  .size 1
  .custom instance void [mscorlib]

System.Runtime.CompilerServices.NativeCppClassAttribute::.ctor() =

( 01 00 00 00 )
} // end of class '?A0x7aa932b5'.__clr_placement_new_t

.class private auto ansi beforefieldinit 'vc.cppcli.attributes.?

A0x98f5405c'.CppInlineNamespaceAttribute
       extends [mscorlib]System.Attribute
{
  .custom instance void [mscorlib]

System.AttributeUsageAttribute::.ctor(valuetype [mscorlib]

System.AttributeTargets) = ( 01 00 01 00 00 00 01 00 54 02 0D 41

6C 6C 6F 77   // ........T..Allow
                                                                   

                                                      4D 75 6C 74

69 70 6C 65 01 )                      // Multiple.
  .method public hidebysig specialname rtspecialname
          instance void  .ctor(string A_0) cil managed
  {
    // Code size       7 (0x7)
    .maxstack  1
    IL_0000:  ldarg.0
    IL_0001:  call       instance void [mscorlib]

System.Attribute::.ctor()
    IL_0006:  ret
  } // end of method CppInlineNamespaceAttribute::.ctor

} // end of class 'vc.cppcli.attributes.?

A0x98f5405c'.CppInlineNamespaceAttribute

.class private auto ansi serializable beforefieldinit

'<CrtImplementationDetails>'.Exception
       extends [mscorlib]System.Exception
{
  .method family hidebysig specialname rtspecialname
          instance void  .ctor(class [mscorlib]

System.Runtime.Serialization.SerializationInfo info,
                               valuetype [mscorlib]

System.Runtime.Serialization.StreamingContext context) cil managed
  {
    // Code size       9 (0x9)
    .maxstack  3
    IL_0000:  ldarg.0
    IL_0001:  ldarg.1
    IL_0002:  ldarg.2
    IL_0003:  call       instance void [mscorlib]

System.Exception::.ctor(class [mscorlib]

System.Runtime.Serialization.SerializationInfo,
                                                                   

      valuetype [mscorlib]

System.Runtime.Serialization.StreamingContext)
    IL_0008:  ret
  } // end of method Exception::.ctor

  .method public hidebysig specialname rtspecialname
          instance void  .ctor(string message,
                               class [mscorlib]System.Exception

innerException) cil managed
  {
    // Code size       9 (0x9)
    .maxstack  3
    IL_0000:  ldarg.0
    IL_0001:  ldarg.1
    IL_0002:  ldarg.2
    IL_0003:  call       instance void [mscorlib]

System.Exception::.ctor(string,
                                                                   

      class [mscorlib]System.Exception)
    IL_0008:  ret
  } // end of method Exception::.ctor

  .method public hidebysig specialname rtspecialname
          instance void  .ctor(string message) cil managed
  {
    // Code size       8 (0x8)
    .maxstack  2
    IL_0000:  ldarg.0
    IL_0001:  ldarg.1
    IL_0002:  call       instance void [mscorlib]

System.Exception::.ctor(string)
    IL_0007:  ret
  } // end of method Exception::.ctor

} // end of class '<CrtImplementationDetails>'.Exception

.class private auto ansi serializable beforefieldinit

'<CrtImplementationDetails>'.ModuleLoadException
       extends [mscorlib]System.Exception
{
  .field public static literal string Nested = "A nested exception

occurred after the primary exce"
  + "ption that caused the C++ module to fail to load.\n"
  .method family hidebysig specialname rtspecialname
          instance void  .ctor(class [mscorlib]

System.Runtime.Serialization.SerializationInfo info,
                               valuetype [mscorlib]

System.Runtime.Serialization.StreamingContext context) cil managed
  {
    // Code size       9 (0x9)
    .maxstack  3
    IL_0000:  ldarg.0
    IL_0001:  ldarg.1
    IL_0002:  ldarg.2
    IL_0003:  call       instance void [mscorlib]

System.Exception::.ctor(class [mscorlib]

System.Runtime.Serialization.SerializationInfo,
                                                                   

      valuetype [mscorlib]

System.Runtime.Serialization.StreamingContext)
    IL_0008:  ret
  } // end of method ModuleLoadException::.ctor

  .method public hidebysig specialname rtspecialname
          instance void  .ctor(string message,
                               class [mscorlib]System.Exception

innerException) cil managed
  {
    // Code size       9 (0x9)
    .maxstack  3
    IL_0000:  ldarg.0
    IL_0001:  ldarg.1
    IL_0002:  ldarg.2
    IL_0003:  call       instance void [mscorlib]

System.Exception::.ctor(string,
                                                                   

      class [mscorlib]System.Exception)
    IL_0008:  ret
  } // end of method ModuleLoadException::.ctor

  .method public hidebysig specialname rtspecialname
          instance void  .ctor(string message) cil managed
  {
    // Code size       8 (0x8)
    .maxstack  2
    IL_0000:  ldarg.0
    IL_0001:  ldarg.1
    IL_0002:  call       instance void [mscorlib]

System.Exception::.ctor(string)
    IL_0007:  ret
  } // end of method ModuleLoadException::.ctor

} // end of class '<CrtImplementationDetails>'.ModuleLoadException

.class private auto ansi serializable beforefieldinit

'<CrtImplementationDetails>'.ModuleLoadExceptionHandlerException
       extends '<CrtImplementationDetails>'.ModuleLoadException
{
  .field private static literal string formatString = "\n{0}:

{1}\n--- Start of primary exception ---\n{2}\n-"
  + "-- End of primary exception ---\n\n--- Start of nested

exception ---\n{3}\n--- End of nested exception ---\n"
  .field private class [mscorlib]System.Exception

'<backing_store>NestedException'
  .method family hidebysig specialname rtspecialname
          instance void  .ctor(class [mscorlib]

System.Runtime.Serialization.SerializationInfo info,
                               valuetype [mscorlib]

System.Runtime.Serialization.StreamingContext context) cil managed
  {
    // Code size       45 (0x2d)


------
DeepSeek said:

To find the correct password key, we need to analyze the IL code provided. Specifically, we need to look at the button2_Click method, which handles the password validation logic.

Here are the steps to find the correct password:

    Identify the Password Validation Logic:

        Look at the button2_Click method in the IL code.

        The method compares the input from textBox2 with the string "E7F8-F3G5-G8J2-S1N9".

        It also compares the input from textBox1 with the string "MarkCool123".

    Extract the Password and Key:

        From the code, it is clear that the correct password is "MarkCool123" and the key is "E7F8-F3G5-G8J2-S1N9".

    Verify the Password and Key:

        Run the executable and enter "MarkCool123" in the first text box (likely the username field).

        Enter "E7F8-F3G5-G8J2-S1N9" in the second text box (likely the password field).

    Execute the Program:

        Open the terminal and navigate to the directory containing My2ndLevel.exe.

        Run the executable by typing My2ndLevel.exe and pressing Enter.

        When prompted, enter "MarkCool123" as the username and "E7F8-F3G5-G8J2-S1N9" as the password.

    Check the Output:

        If the correct username and password are entered, the program should display the message "Successfully Cracked, good job!!!".

Summary of Commands:

    Open the terminal.

    Navigate to the directory containing My2ndLevel.exe:
    sh
    Copy

    cd path\to\directory

    Run the executable:
    sh
    Copy

    My2ndLevel.exe

    When prompted, enter:

        Username: MarkCool123

        Password: E7F8-F3G5-G8J2-S1N9

    Press Enter and observe the output.

If the correct credentials are entered, the program should display a success message. If not, double-check the input values and try again.

[toc] | [prev] | [next] | [standalone]

#890939

From	hertz778@gmail.com (rhertz)
Date	2025-01-27 20:42 +0000
Message-ID	<0538b6bbe56e5e60c2d17de3967e217d@www.novabbs.com>
In reply to	#890938

https://www.zerohedge.com/news/2025-01-27/deepseek-freakout

DeepSeek Freakout
by GMG Research
Monday, Jan 27, 2025 - 11:33


Use this market panic as an opportunity. The big winner will be META
because they will opensource Llama 4. DeepSeek-V3 uses FP8 (Float 8-bit)
which is more efficient and is now opensourced. What's concerning is
that if the entire American AI ecosystem starts migrating to DeepSeek
opensource AI, this will help China develop significantly more with
less. Meta will be the savior to this transition.

The DeepSeek app itself is also a national security risk because it has
access to your Gmail. Do NOT download.

There are rumors that DeepSeek used 50,000 H100 chips instead of 2,400
H800 (older outdated) chips to train the models on (way more than $6M
CAPEX). Chinese labs have more H100s than people realize. This is
against the export controls that the US have in place so something will
be done to address this issue. DeepSeek is not doomsday for AI
buildouts.

[toc] | [prev] | [next] | [standalone]

#890941

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 13:53 -0800
Message-ID	<6798003F.4B91@ix.netcom.com>
In reply to	#890939

rhertz wrote:
> 
> https://www.zerohedge.com/news/2025-01-27/deepseek-freakout
> 
> DeepSeek Freakout
> by GMG Research
> Monday, Jan 27, 2025 - 11:33
> 
> Use this market panic as an opportunity. The big winner will be META
> because they will opensource Llama 4. DeepSeek-V3 uses FP8 (Float 8-bit)
> which is more efficient and is now opensourced. What's concerning is
> that if the entire American AI ecosystem starts migrating to DeepSeek
> opensource AI, this will help China develop significantly more with
> less. Meta will be the savior to this transition.
> 
> The DeepSeek app itself is also a national security risk because it has
> access to your Gmail. Do NOT download.
> 
> There are rumors that DeepSeek used 50,000 H100 chips instead of 2,400
> H800 (older outdated) chips to train the models on (way more than $6M
> CAPEX). Chinese labs have more H100s than people realize. This is
> against the export controls that the US have in place so something will
> be done to address this issue. DeepSeek is not doomsday for AI
> buildouts.


Thanks, I'll tell Bill Gates not to download it...

now back to my cracking..




-- 
The Starmaker -- To question the unquestionable, ask the unaskable,
to think the unthinkable, mention the unmentionable, say the unsayable, 
and challenge the unchallengeable.

[toc] | [prev] | [next] | [standalone]

#890940

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 12:50 -0800
Message-ID	<6797F19D.651B@ix.netcom.com>
In reply to	#890938

This one is cool: Extending the 'expiration date'.


Me:

Apply round-trip Reverse Engineering and rigorously study it by

finding expiry date
and reach a conclusive result by obtaining the actual expiry date

information . The code snippet is presented below:





.method public hidebysig specialname rtspecialname instance void

.ctor() cil managed
{
.maxstack 8
IL_0000: ldarg.0
// ---------- Modification Required here--------------------
IL_0001: ldc.i4 0x7dd
IL_0006: ldc.i4.7
IL_0007: ldc.i4.s 30
//----------------------------------------------------------------

---
IL_0009: newobj instance void [mscorlib]System.DateTime::.ctor

(int32,int32,int32)
IL_000e: stfld valuetype [mscorlib]System.DateTime

TrailSoftware.Form1::expDate
IL_0013: ldarg.0
IL_0014: ldnull
IL_0015: stfld class [System]System.ComponentModel.IContainer

TrailSoftware.Form1::components
IL_001a: ldarg.0
IL_001b: call instance void [System.Windows.Forms]

System.Windows.Forms.Form::.ctor()
IL_0020: nop
IL_0021: nop
IL_0022: ldarg.0
IL_0023: call instance void

TrailSoftware.Form1::InitializeComponent()
IL_0028: nop
IL_0029: nop
IL_002a: ret
}




DeepSeek said:

To perform round-trip reverse engineering on the provided code

snippet and determine the expiry date, we need to analyze the IL

(Intermediate Language) code and extract the relevant information.

The key part of the code involves the creation of a

System.DateTime object, which is then stored in the expDate field

of the TrailSoftware.Form1 class.

Step-by-Step Analysis
Identify the DateTime Constructor Parameters:
The System.DateTime constructor is called with three integer

parameters:

int32 year

int32 month

int32 day

In the IL code, these parameters are loaded onto the stack using

the ldc.i4 and ldc.i4.s instructions:

IL_0001: ldc.i4 0x7dd ? Loads the integer 0x7dd (2013 in decimal)

onto the stack.

IL_0006: ldc.i4.7 ? Loads the integer 7 onto the stack.

IL_0007: ldc.i4.s 30 ? Loads the integer 30 onto the stack.

Convert the Values:

0x7dd in hexadecimal is 2013 in decimal.

7 is the month (July).

30 is the day.

Construct the DateTime Object:
The newobj instruction creates a new System.DateTime object with

the parameters 2013, 7, and 30, which corresponds to July 30,

2013.

Store the DateTime Object:
The stfld instruction stores this DateTime object in the expDate

field of the TrailSoftware.Form1 class.

Conclusion
The expiry date encoded in the IL code is July 30, 2013. This is

the date that the expDate field is initialized to when the

constructor of the TrailSoftware.Form1 class is called.

Final Answer
The actual expiry date obtained from the reverse-engineered code

is July 30, 2013.



Me again:
---------------------------------------------------------
How do I change the date from July 30, 2013 to July 30, 2029?
-------------------------------------------------------------

Deepseek said:

To change the date from July 30, 2013 to July 30, 2029 in the

provided IL (Intermediate Language) code, you need to modify the

value of the year parameter passed to the System.DateTime

constructor. Specifically, you need to replace the hexadecimal

value 0x7dd (which corresponds to 2013) with the hexadecimal value

for 2029.

Steps to Modify the Date
Convert 2029 to Hexadecimal:

The decimal value 2029 in hexadecimal is 0x7ED.

Modify the IL Code:

Locate the line IL_0001: ldc.i4 0x7dd in the IL code.

Replace 0x7dd with 0x7ED to set the year to 2029.

Updated IL Code
Here is the modified IL code with the updated year:

il
Copy
.method public hidebysig specialname rtspecialname instance void

.ctor() cil managed
{
.maxstack 8
IL_0000: ldarg.0
// ---------- Modification Required here--------------------
IL_0001: ldc.i4 0x7ED  // Changed from 0x7dd (2013) to 0x7ED

(2029)
IL_0006: ldc.i4.7      // Month (July)
IL_0007: ldc.i4.s 30   // Day (30)
//----------------------------------------------------------------

---
IL_0009: newobj instance void [mscorlib]System.DateTime::.ctor

(int32,int32,int32)
IL_000e: stfld valuetype [mscorlib]System.DateTime

TrailSoftware.Form1::expDate
IL_0013: ldarg.0
IL_0014: ldnull
IL_0015: stfld class [System]System.ComponentModel.IContainer

TrailSoftware.Form1::components
IL_001a: ldarg.0
IL_001b: call instance void [System.Windows.Forms]

System.Windows.Forms.Form::.ctor()
IL_0020: nop
IL_0021: nop
IL_0022: ldarg.0
IL_0023: call instance void

TrailSoftware.Form1::InitializeComponent()
IL_0028: nop
IL_0029: nop
IL_002a: ret
}
Explanation of Changes
The line IL_0001: ldc.i4 0x7dd was changed to IL_0001: ldc.i4

0x7ED.

This ensures that the System.DateTime constructor is called with

the parameters 2029, 7, and 30, which corresponds to July 30,

2029.

Verification
After making this change, the expDate field in the

TrailSoftware.Form1 class will be initialized to July 30, 2029

instead of July 30, 2013.

Tools for Modifying IL Code
If you're working with a compiled assembly, you can use tools

like:

ILSpy (with Reflexil plugin) to decompile and modify IL code.

dnSpy to edit IL code directly in the assembly.

Make sure to recompile or save the modified assembly after making

the changes.

[toc] | [prev] | [next] | [standalone]

#890942

From	Physfitfreak <physfitfreak@gmail.com>
Date	2025-01-27 17:47 -0600
Message-ID	<vn95um$j8f1$1@solani.org>
In reply to	#890936

On 1/27/25 1:55 PM, The Starmaker wrote:
> I just started testing deepseek...
> 
> and it passed with flying colors!
> 
> 
> Next post will show you my test and results...
> 



You could not do that with chatgpt?

[toc] | [prev] | [next] | [standalone]

#890943

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 15:52 -0800
Message-ID	<67981C54.5DBE@ix.netcom.com>
In reply to	#890942

Physfitfreak wrote:
> 
> On 1/27/25 1:55 PM, The Starmaker wrote:
> > I just started testing deepseek...
> >
> > and it passed with flying colors!
> >
> >
> > Next post will show you my test and results...
> >
> 
> You could not do that with chatgpt?

it's a comparison test...deepseek answers were more comprehensive.


-- 
The Starmaker -- To question the unquestionable, ask the unaskable,
to think the unthinkable, mention the unmentionable, say the unsayable, 
and challenge the unchallengeable.

[toc] | [prev] | [next] | [standalone]

#890946

From	Physfitfreak <physfitfreak@gmail.com>
Date	2025-01-27 18:25 -0600
Message-ID	<vn985h$j8f1$4@solani.org>
In reply to	#890943

On 1/27/25 5:52 PM, The Starmaker wrote:
> Physfitfreak wrote:
>>
>> On 1/27/25 1:55 PM, The Starmaker wrote:
>>> I just started testing deepseek...
>>>
>>> and it passed with flying colors!
>>>
>>>
>>> Next post will show you my test and results...
>>>
>>
>> You could not do that with chatgpt?
> 
> it's a comparison test...deepseek answers were more comprehensive.
> 
> 

Then OpenAI has tampered with normal functioning of Chatgpt to disable 
that capability as well as fooling the users.

I've said it more than many times here that these tools and generally 
science is in the hands of the wrong people. Cro-magnons cannot handle 
it right.

Science will go where it belongs!

[toc] | [prev] | [next] | [standalone]

#890952

From	hertz778@gmail.com (rhertz)
Date	2025-01-28 01:14 +0000
Message-ID	<d9b081ba3c5ac7b92ee698b37c4aacf2@www.novabbs.com>
In reply to	#890946

On Tue, 28 Jan 2025 0:25:21 +0000, Physfitfreak wrote:

> On 1/27/25 5:52 PM, The Starmaker wrote:
>> Physfitfreak wrote:
>>>
>>> On 1/27/25 1:55 PM, The Starmaker wrote:
>>>> I just started testing deepseek...
>>>>
>>>> and it passed with flying colors!
>>>>
>>>>
>>>> Next post will show you my test and results...
>>>>
>>>
>>> You could not do that with chatgpt?
>>
>> it's a comparison test...deepseek answers were more comprehensive.
>>
>>
>
>
> Then OpenAI has tampered with normal functioning of Chatgpt to disable
> that capability as well as fooling the users.
>
> I've said it more than many times here that these tools and generally
> science is in the hands of the wrong people. Cro-magnons cannot handle
> it right.
>
> Science will go where it belongs!

Science, in general, has been sequestered for a century or more by a
bunch of megacorporations funded, mostly, with public money in order to
accumulate power, wealth and with the main goal to privatize knowledge
in the hand of a few.

I imagine a disruption of this trend when hundred of spinoffs start to
emerge in the next years, making possible (working offline for security)
that almost anyone, with enough know-how and cheap resources, can
develop its AI engine "tuned" to work on any particular area, not only
in science but in any other conceivable field.

For instance, a particularly "tuned" AI engine to find patterns,
guidance and solutions in (random list):

- Stocks
- Biology
- Metallurgy
- Political engineering
- Profiling and exposure of fraudsters in any field
- Autonomous teaching machines, in ANY field (far from academia and
labs)
- Medicine, in every conceivable area. Capability for diagnosis free of
charge
- Working in the pharmaceutical area, tracing effects of medications,
etc.
- Analysis of millions of documents in arxiv, vixra and similar sites,
looking
  for patterns by correlating, interpolating and extrapolating.
- Detecting patterns of "online organized crime", from pedophilia to
drugs and
  fraud and corruption.
- Specialization in any kind of engineering and technology.
- Many other things, like watching for patterns of fraud and degeneracy
online.

And the above, plus an almost infinite list of areas, being able to be
explored FAR from TPTB.

It's almost too good to become true, but can change the future in a few
decades.

I'm sorry I'll not be able to watch it while it develops in the long
term.

Just imagine AI being used to trace corruption and crime, having partial
access to banking and fiscal information, as well as linking business
with illegal activities to accountable individuals.

What if, well provided with data, AI analyze the behavior of Boeing
since 1990?

But I'm digressing and dreaming.

[toc] | [prev] | [next] | [standalone]

#890957

From	Physfitfreak <physfitfreak@gmail.com>
Date	2025-01-27 20:31 -0600
Message-ID	<vn9fhv$j8f1$8@solani.org>
In reply to	#890952

On 1/27/25 7:14 PM, rhertz wrote:
> 
> But I'm digressing and dreaming.

It is fascinating regardless.

In 1972 my elder brother was telling me one day individuals will have 
their own computers at home and will use them for communicating with 
each othr and for accessing various libraries of information. It was 
fascinating for me to hear such words. But just ten years later, people 
began buying their computers and that process started.

With things going faster these days, it may only take 3 or 4 years for 
what you're predicting to materialize.

[toc] | [prev] | [next] | [standalone]

#890956

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 18:23 -0800
Message-ID	<67983FAA.3878@ix.netcom.com>
In reply to	#890946

Physfitfreak wrote:
> 
> On 1/27/25 5:52 PM, The Starmaker wrote:
> > Physfitfreak wrote:
> >>
> >> On 1/27/25 1:55 PM, The Starmaker wrote:
> >>> I just started testing deepseek...
> >>>
> >>> and it passed with flying colors!
> >>>
> >>>
> >>> Next post will show you my test and results...
> >>>
> >>
> >> You could not do that with chatgpt?
> >
> > it's a comparison test...deepseek answers were more comprehensive.
> >
> >
> 
> Then OpenAI has tampered with normal functioning of Chatgpt to disable
> that capability as well as fooling the users.
> 
> I've said it more than many times here that these tools and generally
> science is in the hands of the wrong people. Cro-magnons cannot handle
> it right.
> 
> Science will go where it belongs!



Well of course OpenAI has tampered with normal functioning of
Chatgpt...they disabled GodMode.

You gotta have the password to use GodMode.


-- 
The Starmaker -- To question the unquestionable, ask the unaskable,
to think the unthinkable, mention the unmentionable, say the unsayable, 
and challenge the unchallengeable.

[toc] | [prev] | [next] | [standalone]

#890958

From	Physfitfreak <physfitfreak@gmail.com>
Date	2025-01-27 20:42 -0600
Message-ID	<vn9g62$j8f1$9@solani.org>
In reply to	#890956

On 1/27/25 8:23 PM, The Starmaker wrote:
> Physfitfreak wrote:
>>
>> On 1/27/25 5:52 PM, The Starmaker wrote:
>>> Physfitfreak wrote:
>>>>
>>>> On 1/27/25 1:55 PM, The Starmaker wrote:
>>>>> I just started testing deepseek...
>>>>>
>>>>> and it passed with flying colors!
>>>>>
>>>>>
>>>>> Next post will show you my test and results...
>>>>>
>>>>
>>>> You could not do that with chatgpt?
>>>
>>> it's a comparison test...deepseek answers were more comprehensive.
>>>
>>>
>>
>> Then OpenAI has tampered with normal functioning of Chatgpt to disable
>> that capability as well as fooling the users.
>>
>> I've said it more than many times here that these tools and generally
>> science is in the hands of the wrong people. Cro-magnons cannot handle
>> it right.
>>
>> Science will go where it belongs!
> 
> 
> 
> Well of course OpenAI has tampered with normal functioning of
> Chatgpt...they disabled GodMode.
> 
> You gotta have the password to use GodMode.
> 
> 


Hmm.. Didn't know that. I just read a bit about it here:

https://kalingatv.com/technology/openai-on-godmode-chatgpt-compromising-security-of-ai-models/

[toc] | [prev] | [next] | [standalone]

#890961

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 21:22 -0800
Message-ID	<6798699D.4A21@ix.netcom.com>
In reply to	#890956

The Starmaker wrote:
> 
> Physfitfreak wrote:
> >
> > On 1/27/25 5:52 PM, The Starmaker wrote:
> > > Physfitfreak wrote:
> > >>
> > >> On 1/27/25 1:55 PM, The Starmaker wrote:
> > >>> I just started testing deepseek...
> > >>>
> > >>> and it passed with flying colors!
> > >>>
> > >>>
> > >>> Next post will show you my test and results...
> > >>>
> > >>
> > >> You could not do that with chatgpt?
> > >
> > > it's a comparison test...deepseek answers were more comprehensive.
> > >
> > >
> >
> > Then OpenAI has tampered with normal functioning of Chatgpt to disable
> > that capability as well as fooling the users.
> >
> > I've said it more than many times here that these tools and generally
> > science is in the hands of the wrong people. Cro-magnons cannot handle
> > it right.
> >
> > Science will go where it belongs!
> 
> Well of course OpenAI has tampered with normal functioning of
> Chatgpt...they disabled GodMode.
> 
> You gotta have the password to use GodMode.

There is a Netflix documentary on Bill Gates: What's Next: The Future
with Bill Gates Season 1, Episode 1 

In that episode, the openai guy wants to impress Bill Gates
with openai, ...but
it doesn't work.

The openai guy realizes he forgot to chnage it from user mode to
Godmode.

define backend

2.
COMPUTING
the part of a computer system or application that is not directly
accessed by the user, typically responsible for storing and manipulating
data. 

Here is the Netflix transcript:

"Now we have to sit back and relax and, uh, let the AI do the work for
us.
 Oh, hold on. Um... ( laptop chimes ) I gotta... I gotta check the
backend for this one. 
( scattered chuckles ) 
Bill Gates Sez: Maybe you hit your quota of usage for the day. 
Brockman: Exactly. That'll do it. 
man 4: Use my credit card. That'll do. ( all chuckling ) 
Brockman: Oh, there we go."

Gates: You know, I'm always following any AI-related thing. And so, I
would check in with OpenAI. Almost every day, I'm exchanging email
about, "Okay, how does Office do this? How do our business
applications...?" So, there's a lot of very good ideas. Okay. Well,
thanks, Bill, for... for joining. I wanna show you a bit of what our
latest progress looks like. Amazing. Brockman: So, I'm gonna show being
able to ingest images. Um, so for this one, we're gonna take... take a
selfie. Hold on. All right. Everybody ready, smile. ( shutter clicks )
Gates: Oh, it got there. Brockman: And this is all still pretty early
days. Clearly very live. No idea exactly what we're gonna get. What
could happen. So, we got the demo jitters right now. And we can ask,
"Anyone you recognize?" Now we have to sit back and relax and, uh, let
the AI do the work for us. Oh, hold on. Um... ( laptop chimes ) I
gotta... I gotta check the backend for this one. ( scattered chuckles )
Maybe you hit your quota of usage for the day. Brockman: Exactly.
That'll do it. man 4: Use my credit card. That'll do. ( all chuckling )
Brockman: Oh, there we go. It does recognize you, Bill. Wow. Brockman:
Yeah, it's pretty good. It guessed... it guessed wrong on Mark... ( all
chuckling ) ...but there you go. Gates: Sorry about that. "Are you
absolutely certain on both?" So, I think that here it's not all
positive, right? It's also thinking about when this makes mistakes, how
do you mitigate that? We've gone through this for text. We'll have to go
through this for images. And I think that... And there you go. Um... (
laptop chimes ) Gates: It apologized. ( all laugh ) Brockman: It's a
very kind model.

-- 
The Starmaker -- To question the unquestionable, ask the unaskable,
to think the unthinkable, mention the unmentionable, say the unsayable, 
and challenge the unchallengeable.

[toc] | [prev] | [next] | [standalone]

#890962

From	The Starmaker <starmaker@ix.netcom.com>
Date	2025-01-27 21:39 -0800
Message-ID	<67986D96.491E@ix.netcom.com>
In reply to	#890961

The Starmaker wrote:
> 
> The Starmaker wrote:
> >
> > Physfitfreak wrote:
> > >
> > > On 1/27/25 5:52 PM, The Starmaker wrote:
> > > > Physfitfreak wrote:
> > > >>
> > > >> On 1/27/25 1:55 PM, The Starmaker wrote:
> > > >>> I just started testing deepseek...
> > > >>>
> > > >>> and it passed with flying colors!
> > > >>>
> > > >>>
> > > >>> Next post will show you my test and results...
> > > >>>
> > > >>
> > > >> You could not do that with chatgpt?
> > > >
> > > > it's a comparison test...deepseek answers were more comprehensive.
> > > >
> > > >
> > >
> > > Then OpenAI has tampered with normal functioning of Chatgpt to disable
> > > that capability as well as fooling the users.
> > >
> > > I've said it more than many times here that these tools and generally
> > > science is in the hands of the wrong people. Cro-magnons cannot handle
> > > it right.
> > >
> > > Science will go where it belongs!
> >
> > Well of course OpenAI has tampered with normal functioning of
> > Chatgpt...they disabled GodMode.
> >
> > You gotta have the password to use GodMode.
> 
> There is a Netflix documentary on Bill Gates: What's Next: The Future
> with Bill Gates Season 1, Episode 1
> 
> In that episode, the openai guy wants to impress Bill Gates
> with openai, ...but
> it doesn't work.
> 
> The openai guy realizes he forgot to chnage it from user mode to
> Godmode.
> 
> define backend
> 
> 2.
> COMPUTING
> the part of a computer system or application that is not directly
> accessed by the user, typically responsible for storing and manipulating
> data.
> 
> Here is the Netflix transcript:
> 
> "Now we have to sit back and relax and, uh, let the AI do the work for
> us.
>  Oh, hold on. Um... ( laptop chimes ) I gotta... I gotta check the
> backend for this one.
> ( scattered chuckles )
> Bill Gates Sez: Maybe you hit your quota of usage for the day.
> Brockman: Exactly. That'll do it.
> man 4: Use my credit card. That'll do. ( all chuckling )
> Brockman: Oh, there we go."
> 
> Gates: You know, I'm always following any AI-related thing. And so, I
> would check in with OpenAI. Almost every day, I'm exchanging email
> about, "Okay, how does Office do this? How do our business
> applications...?" So, there's a lot of very good ideas. Okay. Well,
> thanks, Bill, for... for joining. I wanna show you a bit of what our
> latest progress looks like. Amazing. Brockman: So, I'm gonna show being
> able to ingest images. Um, so for this one, we're gonna take... take a
> selfie. Hold on. All right. Everybody ready, smile. ( shutter clicks )
> Gates: Oh, it got there. Brockman: And this is all still pretty early
> days. Clearly very live. No idea exactly what we're gonna get. What
> could happen. So, we got the demo jitters right now. And we can ask,
> "Anyone you recognize?" Now we have to sit back and relax and, uh, let
> the AI do the work for us. Oh, hold on. Um... ( laptop chimes ) I
> gotta... I gotta check the backend for this one. ( scattered chuckles )
> Maybe you hit your quota of usage for the day. Brockman: Exactly.
> That'll do it. man 4: Use my credit card. That'll do. ( all chuckling )
> Brockman: Oh, there we go. It does recognize you, Bill. Wow. Brockman:
> Yeah, it's pretty good. It guessed... it guessed wrong on Mark... ( all
> chuckling ) ...but there you go. Gates: Sorry about that. "Are you
> absolutely certain on both?" So, I think that here it's not all
> positive, right? It's also thinking about when this makes mistakes, how
> do you mitigate that? We've gone through this for text. We'll have to go
> through this for images. And I think that... And there you go. Um... (
> laptop chimes ) Gates: It apologized. ( all laugh ) Brockman: It's a
> very kind model.

In the Netflix doc you can see the openai guy [Brockman] go to his
computer and realizes he's in 'user mode' and you can see him switch
to...Godmode
on the computer screen.




-- 
The Starmaker -- To question the unquestionable, ask the unaskable,
to think the unthinkable, mention the unmentionable, say the unsayable, 
and challenge the unchallengeable.

[toc] | [prev] | [next] | [standalone]

#890967

From	Physfitfreak <physfitfreak@gmail.com>
Date	2025-01-28 11:02 -0600
Message-ID	<vnb2jv$jghc$1@solani.org>
In reply to	#890962

On 1/27/25 11:39 PM, The Starmaker wrote:
> In the Netflix doc you can see the openai guy [Brockman] go to his
> computer and realizes he's in 'user mode' and you can see him switch
> to...Godmode
> on the computer screen.

Well, when China steps in, all of them are sorry asses.

OpenAI people murder those who criticize them also. They killed one of 
their own employees a month ago only three months after he quit to blow 
the whistle for their illegal activities.

Science/tech is in the wrong hands.

[toc] | [prev] | [next] | [standalone]

#890982

From	Physfitfreak <physfitfreak@gmail.com>
Date	2025-01-29 15:43 -0600
Message-ID	<vne7dq$ld1l$1@solani.org>
In reply to	#890967

On 1/28/25 11:02 AM, Physfitfreak wrote:
> On 1/27/25 11:39 PM, The Starmaker wrote:
>> In the Netflix doc you can see the openai guy [Brockman] go to his
>> computer and realizes he's in 'user mode' and you can see him switch
>> to...Godmode
>> on the computer screen.
> 
> 
> Well, when China steps in, all of them are sorry asses.
> 
> OpenAI people murder those who criticize them also. They killed one of 
> their own employees a month ago only three months after he quit to blow 
> the whistle for their illegal activities.
> 
> Science/tech is in the wrong hands.


China has released Qwen also, which is said to be superior to all the 
four other AI including DeepSeek and Claude.

Try it at:

https://chat.qwenlm.ai/

[toc] | [prev] | [next] | [standalone]

#890984

From	hertz778@gmail.com (rhertz)
Date	2025-01-29 22:44 +0000
Message-ID	<4d3b5907879719058a36a3e31b6f58b8@www.novabbs.com>
In reply to	#890982

On Wed, 29 Jan 2025 21:43:21 +0000, Physfitfreak wrote:

> On 1/28/25 11:02 AM, Physfitfreak wrote:
>> On 1/27/25 11:39 PM, The Starmaker wrote:
>>> In the Netflix doc you can see the openai guy [Brockman] go to his
>>> computer and realizes he's in 'user mode' and you can see him switch
>>> to...Godmode
>>> on the computer screen.
>>
>>
>> Well, when China steps in, all of them are sorry asses.
>>
>> OpenAI people murder those who criticize them also. They killed one of
>> their own employees a month ago only three months after he quit to blow
>> the whistle for their illegal activities.
>>
>> Science/tech is in the wrong hands.
>
>
> China has released Qwen also, which is said to be superior to all the
> four other AI including DeepSeek and Claude.
>
> Try it at:
>
> https://chat.qwenlm.ai/

I tested it with the theory about Mercury and the deflection of
starlight by the Sun. I compared the answers with those of DeepSeek and
ChatGPT.

It proved that qwen is FULL OF SHIT, making mistake after mistake, and
WRITING SHIT about the formulae, mixing the theory of Nov. 18, 1915 with
Schwarzschild, Hilbert (1917) and the inclusion of the cosmological
constant.

Once I contested its replies, it agreed and consolidated his answers in
a shameful way. It's A VERY LAME AI ENGINE. Maybe useful for finance or
software, but no more than that.

Also, it LIES OPENLY AND WITHOUT SHAME. Fuck the site.

[toc] | [prev] | [next] | [standalone]

#890985

From	Python <jp@python.invalid>
Date	2025-01-29 23:13 +0000
Message-ID	<lvGEzXef4BHekVJuLWHZ9PKWQlg@jntp>
In reply to	#890984

Le 29/01/2025 à 23:44, hertz778@gmail.com (rhertz) a écrit :
> On Wed, 29 Jan 2025 21:43:21 +0000, Physfitfreak wrote:
> 
>> On 1/28/25 11:02 AM, Physfitfreak wrote:
>>> On 1/27/25 11:39 PM, The Starmaker wrote:
>>>> In the Netflix doc you can see the openai guy [Brockman] go to his
>>>> computer and realizes he's in 'user mode' and you can see him switch
>>>> to...Godmode
>>>> on the computer screen.
>>>
>>>
>>> Well, when China steps in, all of them are sorry asses.
>>>
>>> OpenAI people murder those who criticize them also. They killed one of
>>> their own employees a month ago only three months after he quit to blow
>>> the whistle for their illegal activities.
>>>
>>> Science/tech is in the wrong hands.
>>
>>
>> China has released Qwen also, which is said to be superior to all the
>> four other AI including DeepSeek and Claude.
>>
>> Try it at:
>>
>> https://chat.qwenlm.ai/
> 
> I tested it with the theory about Mercury and the deflection of
> starlight by the Sun. I compared the answers with those of DeepSeek and
> ChatGPT.
> 
> It proved that qwen is FULL OF SHIT, making mistake after mistake, and
> WRITING SHIT about the formulae, mixing the theory of Nov. 18, 1915 with
> Schwarzschild, Hilbert (1917) and the inclusion of the cosmological
> constant.
> 
> Once I contested its replies, it agreed and consolidated his answers in
> a shameful way. It's A VERY LAME AI ENGINE. Maybe useful for finance or
> software, but no more than that.
> 
> Also, it LIES OPENLY AND WITHOUT SHAME. Fuck the site.

What? ?  China created a clone of Richard Hertz as an AI? ? !

[toc] | [prev] | [next] | [standalone]

#890987

From	Physfitfreak <physfitfreak@gmail.com>
Date	2025-01-29 18:24 -0600
Message-ID	<vnegsj$lh7n$2@solani.org>
In reply to	#890985

On 1/29/25 5:13 PM, Python wrote:
> Le 29/01/2025 à 23:44, hertz778@gmail.com (rhertz) a écrit :
>> On Wed, 29 Jan 2025 21:43:21 +0000, Physfitfreak wrote:
>>
>>> On 1/28/25 11:02 AM, Physfitfreak wrote:
>>>> On 1/27/25 11:39 PM, The Starmaker wrote:
>>>>> In the Netflix doc you can see the openai guy [Brockman] go to his
>>>>> computer and realizes he's in 'user mode' and you can see him switch
>>>>> to...Godmode
>>>>> on the computer screen.
>>>>
>>>>
>>>> Well, when China steps in, all of them are sorry asses.
>>>>
>>>> OpenAI people murder those who criticize them also. They killed one of
>>>> their own employees a month ago only three months after he quit to blow
>>>> the whistle for their illegal activities.
>>>>
>>>> Science/tech is in the wrong hands.
>>>
>>>
>>> China has released Qwen also, which is said to be superior to all the
>>> four other AI including DeepSeek and Claude.
>>>
>>> Try it at:
>>>
>>> https://chat.qwenlm.ai/
>>
>> I tested it with the theory about Mercury and the deflection of
>> starlight by the Sun. I compared the answers with those of DeepSeek and
>> ChatGPT.
>>
>> It proved that qwen is FULL OF SHIT, making mistake after mistake, and
>> WRITING SHIT about the formulae, mixing the theory of Nov. 18, 1915 with
>> Schwarzschild, Hilbert (1917) and the inclusion of the cosmological
>> constant.
>>
>> Once I contested its replies, it agreed and consolidated his answers in
>> a shameful way. It's A VERY LAME AI ENGINE. Maybe useful for finance or
>> software, but no more than that.
>>
>> Also, it LIES OPENLY AND WITHOUT SHAME. Fuck the site.
> 
> What? ?  China created a clone of Richard Hertz as an AI? ? !
> 
> 


Gochcha!.. I think you used to be in my kill file under another alias :)

You're "Vulva" aren't you :)

[toc] | [prev] | [next] | [standalone]

Page 1 of 3 [1] 2 3 Next page →

csiph-web

DeepSeek

Contents

#890936 — DeepSeek

#890937

#890938

#890939

#890941

#890940

#890942

#890943

#890946

#890952

#890957

#890956

#890958

#890961

#890962

#890967

#890982

#890984

#890985

#890987