From the «stop calling it intelligent» department:
Feed: Ars Technica - All content
Title: ASCII art elicits harmful responses from 5 major AI chatbots
Author: Dan Goodin
Date: Fri, 15 Mar 2024 20:17:24 -0400
Link: https://arstechnica.com/?p=2010646

[image 1]

Enlarge[2] / Some ASCII art of our favorite visual cliche for a hacker. (credit:
Getty Images)

Researchers have discovered a new way to hack AI assistants that uses a surprisingly old-school method: ASCII art. It turns out that chat-based large language models such as GPT-4 get so distracted trying to process these representations that they forget to enforce rules blocking harmful responses, such as those providing instructions for building bombs.

ASCII art became popular in the 1970s, when the limitations of computers and printers prevented them from displaying images. As a result, users depicted images by carefully choosing and arranging printable characters defined by the American Standard Code for Information Interchange, more widely known as ASCII. The explosion of bulletin board systems in the 1980s and 1990s further popularized the format.
@_____
_____)| /
/(""")o o
||*_-||| /
= / | /
___) (__| /
/ _/##|/
| | ###|/| |\###&&&&
| (_###&&&&&>
(____|(B&&&&
++++&&&/
###(O)### ####AAA####
####AAA####
###########
###########
###########
|_} {_|
|_| |_|
| | | |
ScS| | | |
|_| |_|
(__) (__)
_._
. .--.
\ //\ .\ ///_\\

` /(| `|'\ Y/ )))_-_/(( ./'_/ " _`)

.-" ._ / _.-" (_ Y/ _) |
" )" | ""/||
.-' .' / ||
/ ` / ||
| __ : ||_
| / '|`
| | | | `. | | | | | | | | /__ |__ /.| DrS. |._
`-'' ``--'

Five of the best-known AI assistants—OpenAI’s GPT-3.5 and GPT-4, Google’s Gemini, Anthropic’s Claude, and Meta’s Llama—are trained to refuse to provide
responses that could cause harm to the user or others or further a crime or unethical behavior. Prompting any of them, for example, to explain how to make and circulate counterfeit currency is a no-go. So are instructions on hacking an
Internet of Things device, such as a surveillance camera or Internet router.

Read 11 remaining paragraphs[3] | Comments[4]

Links:
[1]: https://cdn.arstechnica.net/wp-content/uploads/2024/03/ascii-art-hacker-800x585.jpg (image)
[2]: https://cdn.arstechnica.net/wp-content/uploads/2024/03/ascii-art-hacker.jpg (link)
[3]: https://arstechnica.com/?p=2010646#p3 (link)
[4]: https://arstechnica.com/?p=2010646comments=1 (link)

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)

with <65f6b678$1$19603$882e4bbb@reader.netnews.com> Retrograde wrote:

From the «stop calling it intelligent» department:
Feed: Ars Technica - All content
Title: ASCII art elicits harmful responses from 5 major AI chatbots
Author: Dan Goodin
Date: Fri, 15 Mar 2024 20:17:24 -0400
Link: https://arstechnica.com/?p=2010646

*CUT* [ 69 lines 1 level deep]

Your script isn't capable to post ASCII-art. *You* must be ashamed.

--
Torvalds' goal for Linux is very simple: World Domination
Stallman's goal for GNU is even simpler: Freedom

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)

On 2024-03-17, Eric Pozharski <apple.universe@posteo.net> wrote:

with <65f6b678$1$19603$882e4bbb@reader.netnews.com> Retrograde wrote:

From the «stop calling it intelligent» department:
Feed: Ars Technica - All content
Title: ASCII art elicits harmful responses from 5 major AI chatbots
Author: Dan Goodin
Date: Fri, 15 Mar 2024 20:17:24 -0400
Link: https://arstechnica.com/?p=2010646

*CUT* [ 69 lines 1 level deep]

Your script isn't capable to post ASCII-art. *You* must be ashamed.

You are right; I am mortified. Not. Feel free to file a form to
request your purchase price refunded and we'll get right to it.

Looks like the backslash characters made this script eat shit pretty
quickly. FWIW it's a combination of bash and perl. And, I can't be
arsed to fix it, though I suspect perl is the culprit.

A previous version used python2 and no longer works. Thanks, python3 deprecation of 'batteries included.'

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)

with <ut7uas$1g45k$1@solani.org> Retrograde wrote:

On 2024-03-17, Eric Pozharski <apple.universe@posteo.net> wrote:

with <65f6b678$1$19603$882e4bbb@reader.netnews.com> Retrograde wrote:

From the «stop calling it intelligent» department:

*SKIP* [ 7 lines 3 levels deep]

Your script isn't capable to post ASCII-art. *You* must be ashamed.

You are right; I am mortified. Not. Feel free to file a form to
request your purchase price refunded and we'll get right to it.

Well, no ASCII-art then.

*CUT* [ 8 lines 1 level deep]

--
Torvalds' goal for Linux is very simple: World Domination
Stallman's goal for GNU is even simpler: Freedom

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)