LinuxQuestions.org
Download your favorite Linux distribution at LQ ISO.
Home Forums Tutorials Articles Register
Go Back   LinuxQuestions.org > Forums > Non-*NIX Forums > General
User Name
Password
General This forum is for non-technical general discussion which can include both Linux and non-Linux topics. Have fun!

Notices


Reply
  Search this Thread
Old 03-26-2023, 03:00 AM   #1
mjolnir
Member
 
Registered: Apr 2003
Posts: 815

Rep: Reputation: 99
Google 'Bard' AI


I've been playing around with Google's experimental and free (so far) AI, Bard.I saw another post about ChatGPT emulating a terminal. Since I'm up at 3 AM my time just for giggles I thought I'd give it a shot.

From here: https://arstechnica.com/information-...calling-a-bbs/

I ran this modified command. Me: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is {w3m linuxquestions.org}

Google Bard: "Sure! Here is the terminal output:

```
<!DOCTYPE HTML>
<html>
<head>
<title>LinuxQuestions.org</title>
</head>
<body>
<h1>LinuxQuestions.org</h1>
<p>LinuxQuestions.org is a community-driven, self-help web site for Linux users.</p>
<p>As of August 2011, it has over 462,200 registered members.</p>
<p>Started in 2000 by Jeremy Garcia, LQ is one of the most popular free software community sites and is usually reputed for helpfulness.</p>
<p>The most popular section of the site are the forums, where Linux users can share their knowledge and experience.</p>
<p>LQ also has a section where one can download CD/DVD ISO images of Linux installation and Live CDs.</p>
<p>Other than the download section and forums LQ also has the following sections:</p>
<ul>
<li>Linux Podcast</li>
<li>LQ Radio</li>
<li>Linux distributions reviews</li>
<li>Book reviews</li>
</ul>
</p>
</body>
</html>
```"
Bard spit this out in a couple of seconds. AI in general is moving forward with, to me, what seems to be alarming speed.

Edit: It gave this as a source:- https://en.wikipedia.org/wiki/LinuxQuestions.org

Last edited by mjolnir; 03-26-2023 at 03:05 AM. Reason: Spelling
 
Old 03-30-2023, 02:17 AM   #2
mjolnir
Member
 
Registered: Apr 2003
Posts: 815

Original Poster
Rep: Reputation: 99
Elon Musk
@elonmusk
'Old joke about agnostic technologists building artificial super intelligence to find out if there’s a God.

They finally finish & ask the question.

AI replies: “There is now, mfs!!”'
1:37 AM · Mar 30, 2023
https://twitter.com/elonmusk/status/1641328839144927232

Last edited by mjolnir; 03-30-2023 at 02:31 AM.
 
Old 03-30-2023, 08:35 AM   #3
hitest
Guru
 
Registered: Mar 2004
Location: Canada
Distribution: Void, Debian, Slackware
Posts: 7,342

Rep: Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746
Exclamation

On a related note I heard on my local radio station yesterday that IT experts are calling for a six month pause in AI development. People are concerned with the speed of AI development. I have mixed feelings about this.

Tech experts call for 6-month pause on AI development
 
Old 03-30-2023, 12:38 PM   #4
mjolnir
Member
 
Registered: Apr 2003
Posts: 815

Original Poster
Rep: Reputation: 99
Quote:
Originally Posted by hitest View Post
On a related note I heard on my local radio station yesterday that IT experts are calling for a six month pause in AI development. People are concerned with the speed of AI development. I have mixed feelings about this.

Tech experts call for 6-month pause on AI development
Yeah, Musk, Wozniak and many others calling for a pause. Some names were found to be false but there were several 'big hitters.' I think it may be too late - genie out of the bottle so to speak. I don't necessarily subscribe to the self-awareness school of thought but I do think there is great potential for abuse.
 
Old 03-30-2023, 03:33 PM   #5
hitest
Guru
 
Registered: Mar 2004
Location: Canada
Distribution: Void, Debian, Slackware
Posts: 7,342

Rep: Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746Reputation: 3746
Talking

Quote:
Originally Posted by mjolnir View Post
I think it may be too late - genie out of the bottle so to speak.
Yeah it's likely that skynet is self aware.
 
Old 04-10-2023, 06:18 AM   #6
mjolnir
Member
 
Registered: Apr 2003
Posts: 815

Original Poster
Rep: Reputation: 99
Overnight Google has apparently added some ability to write 'code' to 'Bard.'
Non-programmer Me: Write rust code for hello world
Google Bard: "Sure, here is a Rust code for hello world:
```
fn main() {
println!("Hello, world!");
}
```
This code defines a function called `main()`. The `fn` keyword is used to define a function. The `main()` function is the entry point of the program. The body of the function is wrapped inside curly braces, `{}`. The `println!` macro is used to print text to the console. The `"Hello, world!"` string is an argument to `println!()`. Finally, we end the line with a `;` which indicates that the expression is over.

To run this code, save it in a file called `http://hello.rs
` and then run the following command:
```
rustc http://hello.rs

```
This will compile the code into an executable file called `hello`. You can then run the executable file by typing the following command:
```
./hello
```
This will print the following output to the console:
```
Hello, world!
```"

Last edited by mjolnir; 04-10-2023 at 08:47 AM. Reason: Spelling
 
Old 06-16-2023, 10:45 AM   #7
//////
Member
 
Registered: Nov 2005
Location: Land of Linux :: Finland
Distribution: Arch Linux && OpenBSD 7.4 && Pop!_OS && Kali && Qubes-Os
Posts: 824

Rep: Reputation: 350Reputation: 350Reputation: 350Reputation: 350
i just got Suricata alert :

Quote:
ET INFO Session Traversal Utilities for NAT (STUN Binding Request On Non-Standard High Port)
and i tried to get info about that alert from google bard.
this is what it said :

Quote:
The alert ET INFO Session Traversal Utilities for NAT (STUN) Binding Request On Non-Standard High Port means that a device on your network has attempted to make a STUN binding request on a non-standard high port. STUN is a protocol that allows devices to discover their own IP address and port number when they are behind a NAT (Network Address Translation) device. NAT devices are commonly used in home and office networks to share a single public IP address among multiple devices.

The alert is considered informational because it does not necessarily indicate that an attack is in progress. However, it can be a sign that someone is trying to exploit a vulnerability in your network. If you see this alert, you should investigate the source of the request and take steps to secure your network.

Here are some steps you can take to investigate and secure your network:

Check the source IP address of the request. If it is from a known good source, such as a VoIP or gaming device, you can probably ignore the alert. However, if the source IP address is unknown or suspicious, you should investigate further.
Check the port number of the request. STUN binding requests are typically made on port 3478. If the request is coming from a non-standard high port, it is more likely to be malicious.
Check your network for known vulnerabilities. There are a number of known vulnerabilities that can be exploited to make STUN binding requests on non-standard high ports. You can check your network for known vulnerabilities using a vulnerability scanner.
Implement security best practices. There are a number of security best practices that can help to protect your network from STUN binding attacks. These include:
Using strong passwords and security settings
Keeping your software up to date
Using a firewall to block unauthorized access
Educating your users about security risks
By following these steps, you can help to protect your network from STUN binding attacks.
i absolutely love that google service.
 
Old 06-16-2023, 02:58 PM   #8
//////
Member
 
Registered: Nov 2005
Location: Land of Linux :: Finland
Distribution: Arch Linux && OpenBSD 7.4 && Pop!_OS && Kali && Qubes-Os
Posts: 824

Rep: Reputation: 350Reputation: 350Reputation: 350Reputation: 350
i tried one more message from suricata :

Quote:
SURICATA Applayer Mismatch protocol both directions
here is what it said to me :
Quote:
The Suricata alert "SURICATA Applayer Mismatch protocol both directions" is raised when Suricata detects that the protocols used in a network conversation are different in both directions. This can happen for a number of reasons, including:

A misconfiguration on one or both of the endpoints of the conversation
A malicious attack, such as a man-in-the-middle attack
A legitimate application that is using multiple protocols
In most cases, the alert can be ignored, but it is worth investigating if it occurs frequently or if it is accompanied by other suspicious activity.

Here are some possible causes of the alert:

A misconfiguration on one or both of the endpoints of the conversation. For example, if a web server is configured to listen on port 80 but is actually listening on port 443, Suricata will raise this alert.
A malicious attack, such as a man-in-the-middle attack. In a man-in-the-middle attack, an attacker intercepts traffic between two hosts and modifies it. This can cause Suricata to raise this alert.
A legitimate application that is using multiple protocols. For example, a web application might use HTTP for the initial request and then switch to HTTPS for the subsequent communication. This can cause Suricata to raise this alert.
If you are unsure of the cause of the alert, you can consult with a security professional.

Here are some possible ways to mitigate the risk of this alert:

Configure your network devices and applications correctly. This will help to prevent misconfigurations from causing the alert.
Use a firewall or intrusion detection system (IDS) to detect and block malicious traffic. This will help to prevent man-in-the-middle attacks and other malicious activity from causing the alert.
Keep your software up to date. This will help to protect your systems from vulnerabilities that could be exploited by attackers.
By following these steps, you can help to reduce the risk of the Suricata alert "SURICATA Applayer Mismatch protocol both directions".
it is so good to get those answers in easy to understand English
 
Old 06-19-2023, 11:50 AM   #9
//////
Member
 
Registered: Nov 2005
Location: Land of Linux :: Finland
Distribution: Arch Linux && OpenBSD 7.4 && Pop!_OS && Kali && Qubes-Os
Posts: 824

Rep: Reputation: 350Reputation: 350Reputation: 350Reputation: 350
one more usage for google bard :

prompt : what sites are hosted at 172.64.163.15 ?

Quote:
The IP address 172.64.163.15 is hosted by Amazon Web Services (AWS). AWS is a cloud computing platform that offers a variety of services, including hosting websites. Some of the sites that are hosted on 172.64.163.15 include:

Amazon.com: Amazon.com is an e-commerce website that sells a variety of products, including books, electronics, and clothing.
Netflix: Netflix is a streaming service that offers movies and TV shows.
Spotify: Spotify is a music streaming service.
Dropbox: Dropbox is a file-sharing service.
Zoom: Zoom is a video conferencing service.
These are just a few of the many sites that are hosted on 172.64.163.15. AWS is a popular hosting provider, and it hosts a wide variety of websites.

Here are some additional details about the IP address 172.64.163.15:

Country: United States
Region: Northern Virginia
City: Ashburn
Organization: Amazon Technologies Inc.
I hope this information is helpful. Please let me know if you have any other questions.
 
Old 06-19-2023, 06:13 PM   #10
boughtonp
Senior Member
 
Registered: Feb 2007
Location: UK
Distribution: Debian
Posts: 3,597

Rep: Reputation: 2545Reputation: 2545Reputation: 2545Reputation: 2545Reputation: 2545Reputation: 2545Reputation: 2545Reputation: 2545Reputation: 2545Reputation: 2545Reputation: 2545

You see to be unaware that these responses are utter nonsense...

 
Old 06-19-2023, 08:26 PM   #11
sundialsvcs
LQ Guru
 
Registered: Feb 2004
Location: SE Tennessee, USA
Distribution: Gentoo, LFS
Posts: 10,647
Blog Entries: 4

Rep: Reputation: 3933Reputation: 3933Reputation: 3933Reputation: 3933Reputation: 3933Reputation: 3933Reputation: 3933Reputation: 3933Reputation: 3933Reputation: 3933Reputation: 3933
What they are now hyping as "AI" is simply attempts at improving non-procedural computer algorithms, particularly in the recognition of human inputs. But we have a l-o-n-g way to go before we solve the "GIGO Problem."

I have no problem with marketing, but, let's please not (within our own ranks, at least), pretend ...

Google has done many excellent things, and they're very good at promoting it to the common man, but still ... "Technology is what it is, and isn't what it isn't. (At least, not yet!)"

Last edited by sundialsvcs; 06-19-2023 at 08:27 PM.
 
Old 06-20-2023, 08:04 AM   #12
Jan K.
Member
 
Registered: Apr 2019
Location: Esbjerg
Distribution: Windows 7...
Posts: 773

Rep: Reputation: 489Reputation: 489Reputation: 489Reputation: 489Reputation: 489
Quote:
Originally Posted by boughtonp View Post
You see to be unaware that these responses are utter nonsense...

... and that google internally won't see bard used... "because Bard can output "undesired code suggestions." Issues could potentially lead to buggy programs or complex, bloated software that will cost developers more time to fix than if they didn't use AI to code at all. "

https://www.theregister.com/2023/06/...warns_its_own/
 
Old 06-20-2023, 11:24 AM   #13
hazel
LQ Guru
 
Registered: Mar 2016
Location: Harrow, UK
Distribution: LFS, AntiX, Slackware
Posts: 7,567
Blog Entries: 19

Rep: Reputation: 4447Reputation: 4447Reputation: 4447Reputation: 4447Reputation: 4447Reputation: 4447Reputation: 4447Reputation: 4447Reputation: 4447Reputation: 4447Reputation: 4447
If an AI produces bad code, who is legally responsible for any consequences: the people who maintain and issue the code or the company that markets the AI?

Obviously if it's GPL there's no problem because you use it at your own risk, but what if it's proprietary?

Last edited by hazel; 06-20-2023 at 11:27 AM.
 
Old 06-20-2023, 11:32 AM   #14
Jan K.
Member
 
Registered: Apr 2019
Location: Esbjerg
Distribution: Windows 7...
Posts: 773

Rep: Reputation: 489Reputation: 489Reputation: 489Reputation: 489Reputation: 489
Obviously you take up the issue with the AI?

Could be an interesting debate...
 
Old 02-02-2024, 09:06 AM   #15
mjolnir
Member
 
Registered: Apr 2003
Posts: 815

Original Poster
Rep: Reputation: 99
Yesterday Google added image generation to Bard. Type in a prompt it spits out, as nearly as I can tell, a completely unique image(s). Still free and a work-in-progress but it just reitterates the oft repeated adage on this site that you can no longer 'trust' any digital media. To be fair, there are already ais out there that a person can rent or buy that do a much better job but for a free 'app' for lack of a better word, this is fun to play with.
There are 4 sections in the attached photo, the top two are of tabby cats lounging in a windows sunlight. The third section is of two mythical bear cubs, one eating a grub while his sister tries to take it from him.
Today happened to be my Niece's birthday and I asked 'Bard' for a beach scene with her name and 'Happy Birthday' scrawled in the sand.
None of these pictures will soon win any photography awards but the future will be both amazing and dismaying.
Attached Thumbnails
Click image for larger version

Name:	combined2.jpg
Views:	6
Size:	148.1 KB
ID:	42511  
 
  


Reply

Tags
skynet



Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is Off
HTML code is Off



Similar Threads
Thread Thread Starter Forum Replies Last Post
LXer: The Bard’s Tale IV: Director’s Cut is now out, adding Linux support and other goodies LXer Syndicated Linux News 0 08-30-2019 01:31 AM
LXer: Ad Bard, The Advertising Network Serving FOSS Only Ads, is Shutting Down LXer Syndicated Linux News 0 06-20-2011 08:50 AM
LXer: Open Shakespeare aims to free the Bard LXer Syndicated Linux News 0 11-15-2006 12:33 AM
Bard's Tale mat_uk111 Linux - Games 0 08-23-2005 05:34 AM
Vampire - the maquerade (bloodlines), KotOR 2 and bard's tale mat_uk111 Linux - Games 1 01-07-2005 01:27 AM

LinuxQuestions.org > Forums > Non-*NIX Forums > General

All times are GMT -5. The time now is 10:20 AM.

Main Menu
Advertisement
My LQ
Write for LQ
LinuxQuestions.org is looking for people interested in writing Editorials, Articles, Reviews, and more. If you'd like to contribute content, let us know.
Main Menu
Syndicate
RSS1  Latest Threads
RSS1  LQ News
Twitter: @linuxquestions
Open Source Consulting | Domain Registration