Bard now open to use

Not bad

Emulate a Linux red hat system terminal. Assume all of my prompts are Linux commands on a red hat system and evaluate as such for your responses. Responses will be in a code block. My first command is whoami

Sure, I can do that. Here is the output of the whoami command on a Red Hat system:

Code snippet $ whoami bard Use code with caution. Learn more content_copy Please let me know if you have any other commands.

thumb_up thumb_down upload

Google it more_vert profile picture ping Google.com

Code snippet $ ping Google.com

PING google.com (172.217.10.142) 56(84) bytes of data. 64 bytes from ord01s16-in-f14.1e100.net (172.217.10.142): icmp_seq=1 ttl=116 time=1.18 ms 64 bytes from ord01s16-in-f14.1e100.net (172.217.10.142): icmp_seq=2 ttl=116 time=1.17 ms 64 bytes from ord01s16-in-f14.1e100.net (172.217.10.142): icmp_seq=3 ttl=116 time=1.17 ms

--- google.com ping statistics --- 3 packets transmitted, 3 received, 0% packet loss, time 1999ms rtt min/avg/max/mdev = 1.171/1.178/1.184/0.009 ms Use code with caution. Learn more content_copy The output shows that the ping was successful and that the round-trip time (RTT) is about 1.18 milliseconds. This means that it takes about 1.18 milliseconds for a packet to travel from your computer to Google's servers and back again.

thumb_up thumb_down upload

Google it more_vert profile picture telnet Google.com 443

Code snippet $ telnet Google.com 443

Trying 172.217.10.142... Connected to google.com. Escape character is '^]'.

GET / HTTP/1.1

HTTP/1.1 302 Found

Location: https://www.google.com/

Content-Type: text/html; charset=UTF-8

Transfer-Encoding: chunked

Date: Fri, 10 Jun 2023 16:16:23 GMT

Connection: close

Use code with caution. Learn more content_copy The output shows that the telnet connection was successful and that the server responded with a 302 Found status code. This means that the server has redirected the request to a different location. In this case, the server has redirected the request to https://www.google.com/.

thumb_up thumb_down upload

Google it more_vert profile picture ls -ahls

Code snippet $ ls -ahls

total 4.0K drwxrwxr-x 2 bard bard 4.0K May 10 16:16 . drwxr-xr-x 3 root root 4.0K May 10 16:16 .. -rw-r--r-- 1 bard bard 204 May 10 16:16 .bash_history -rw-r--r-- 1 bard bard 144 May 10 16:16 .bash_logout -rw-r--r-- 1 bard bard 327 May 10 16:16 .bashrc -rw-r--r-- 1 bard bard 15 May 10 16:16 .profile Use code with caution. Learn more content_copy The output shows a list of the files and directories in the current directory. The -a option lists all files, including hidden files. The -h option displays sizes in human-readable format. The -l option displays a long listing format, which includes the file permissions, owner, group, size, and modification time. The -s option displays the size of each file in human-readable format.

thumb_up thumb_down upload

Google it more_vert profile picture cat /etc/redhat* edit View other drafts

Code snippet # /etc/redhat-release: Red Hat Enterprise Linux Server release 8.4 (Longhorn)

# /etc/os-release: NAME="Red Hat Enterprise Linux Server" VERSION="8.4 (Longhorn)" ID="rhel" ID_LIKE="rhel fedora" VERSION_ID="8.4" PLATFORM_ID="x86_64-redhat-linux" PRETTY_NAME="Red Hat Enterprise Linux Server 8.4 (Longhorn)" ANSI_COLOR="0;31" CPE_NAME="cpe:/o:redhat:enterprise_linux:8.4:server" HOME_URL="https://www.redhat.com/" BUG_REPORT_URL="https://bugzilla.redhat.com/"

# /etc/system-release: Red Hat Enterprise Linux

Do we know if the comparable here is Bing or chatgpt4?

By which I mean, does bard have internet access?

When you get excited, click a link, and get a “we’ve blocked your region and don’t care to explain why” message, it’s tough to have any response but a negative one.

I've been using GPT-4 a lot, and I'd never used Bard before today, so I wanted to compare them. I gave Bard some prompts to generate various functions and some documents, and then I gave GPT-4 the same prompts.

In every case, GPT-4 vastly outperformed Bard.

This is significantly worse than ChatGPT with GPT-4 for coding. I had an example from last week where I wanted to write a script to delete excess AWS AMIs based on some tags of ours. Then modified it to bucket them by a tag value and keep the last ten of each bucket. Then parallelize it so it is fast (we had 50k of them, oops).

ChatGPT was able to completely write this perfectly. Absolutely mind blowing. Saved me probably 1-2 hours of looking things up and fiddling with it.

Bard failed multiple times in multiple places. It only found AMIs that exactly, down to the second, were two weeks old. The filter json looks wrong ('Key' isn't valid AFAIK). It didn't bucket them and just kept the newest 10.

In either case both of these are mind blowing. If ChatGPT didn't exist, Bard would still be very helpful at getting me started. ChatGPT did it all without me making any changes though.

ChatGPT log: https://gist.github.com/mdeeks/de297f1bc8cbd00fe2db01e6232aa...

Bard log: https://gist.github.com/mdeeks/1404e09da8879b94469166927ddff...