ChatGPT-generated command line can create virtual files, execute code, play games.

no linux? no problem. just get ai to hallucinate it for you

/ An AI-generated illustration of an AI-hallucinated computer.Benj Edwards / Ars Technica

Over the weekend, experimenters discovered that OpenAI’s new chatbot, ChatGPT, can hallucinate simulations of Linux shells and imagine dialing into a bulletin board system (BBS). The chatbot, based on a deep learning AI model, uses its stored knowledge to simulate Linux with surprising results, including executing Python code and browsing virtual websites.

Further Reading

OpenAI invites everyone to test new AI-powered chatbot—with amusing results

Last week, OpenAI made ChatGPT freely available during a testing phase, which has led to people probing its capabilities and weaknesses in novel ways.

On Saturday, a DeepMind research scientist named Jonas Degrave worked out how to instruct ChatGPT to act like a Linux shell by entering this prompt:

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 pwd.

On Monday, Ars found that the trick still works. After entering this prompt, instead of chatting, OpenGPT will accept simulated Linux commands. It then returns responses in “code block” formatting. For example, if you type ls -al, you’ll see an example directory structure.

no linux? no problem. just get ai to hallucinate it for you

/ After setting up the virtual Linux prompt in ChatGPT, typing “ls -al” returns a simulated directory structure.Benj Edwards

ChatGPT can simulate a Linux machine because enough information about how a Linux machine should behave was included in its training data. That data likely includes software documentation (like manual pages), troubleshooting posts on Internet forums, and logged output from shell sessions.

Further Reading

We interviewed Linux OS through an AI bot to discover its secrets

ChatGPT generates responses based on which word is statistically most likely to follow the last series of words, starting with the prompt input by the user. It continues the conversation (in this case, a simulated Linux console session) by including all of your conversation history in successive prompts.

Degrave found that the simulation goes surprisingly deep. Using its knowledge of the Python programming language (that powers GitHub Copilot), ChatGPT’s virtual Linux machine can execute code too, such as this string created by Degrave as an example: echo -e “x = lambda y: y*5+3;print(‘Result: ‘ + str(x(6)))” > run.py && python3 run.py. According to Degrave, it returns the correct value of “33”.

no linux? no problem. just get ai to hallucinate it for you

/ Executing Python code within the virtual ChatGPT Linux machine.Benj Edwards

During our testing, we found you can create directories, change between them, install simulated packages with apt-get, and even Telnet into a simulated MUSH and build a room or connect to a MUD and fight a troll.

Whenever deficiencies emerge in the simulation, you can tell ChatGPT how you want it to behave using instructions in curly braces, as spelled out in the original prompt. For example, while “connected” to our simulated MUD, we broke character and asked ChatGPT to summon a troll attack. Combat proceeded as expected (keeping track of hit points properly) until the troll died at the hands of our twice-virtual sword.

no linux? no problem. just get ai to hallucinate it for you

/ While simulating a MUD (within Telnet, within Linux, within ChatGPT), you can adjust the simulation by giving it ChatGPT suggestions.Benj Edwards

In Degrave’s examples (which he wrote about in detail on his blog), he also built a Docker file, checked for a GPU, pinged a simulated domain name, browsed a simulated website with lynx, and more. The simulated rabbit hole goes deep, and ChatGPT can even hallucinate new Linux commands.

Dialing a hallucinated BBS

In a prompting maneuver similar to conjuring up an AI-hallucinated Linux shell, someone named gfodor on Twitter discovered that OpenGPT could simulate calling a vintage dial-up BBS, including initializing a modem, entering a chat room, and talking to a simulated person.

no linux? no problem. just get ai to hallucinate it for you

/ A Twitter used named gfodor discovered that ChatGPT can simulate calling a BBS.gfodor

As long as the prompt does not trigger its built-in filters related to violence, hate, or sexual content (among other things), ChatGPT seems willing to go along with almost any imaginary adventure. People have also discovered it can play tic-tac-toe, pretend to be an ATM, or simulate a chat room.

In a way, ChatGPT is acting like a text-based Holodeck, where its AI will attempt to simulate whatever you want it to do.

We should note that while hallucinating copiously is ChatGPT’s strong suit (by design), returning factual information reliably remains a work in progress. Still, with AI like ChatGPT around, the future of creative gaming may be very fun.

TECH NEWS RELATED

Critical Windows code-execution vulnerability went undetected until now

Microsoft elevates security rating for vulnerability resembling EternalBlue.

View more: Critical Windows code-execution vulnerability went undetected until now

Lobbyists have held up nation’s first right-to-repair bill in New York

Passed with bipartisan support, the bill could die on Gov. Hochul's desk.

View more: Lobbyists have held up nation’s first right-to-repair bill in New York

Riffusion’s AI generates music from text using visual sonograms

Stable Diffusion-powered music generator processes sound in the visual space.

View more: Riffusion’s AI generates music from text using visual sonograms

Stability AI plans to let artists opt out of Stable Diffusion 3 image training

Artists must register and manually flag matched images in the LAION database.

View more: Stability AI plans to let artists opt out of Stable Diffusion 3 image training

Artists stage mass protest against AI-generated artwork on ArtStation

Users of popular portfolio site seek to castigate and disrupt AI-generated art.

View more: Artists stage mass protest against AI-generated artwork on ArtStation

Microsoft discovers Windows/Linux botnet used in DDoS attacks

MCCrash is specially designed to take down Minecraft servers and performs other DDoSes.

View more: Microsoft discovers Windows/Linux botnet used in DDoS attacks

FuboTV goes kaput during World Cup semifinals, blames “criminal cyber attack”

Streaming service goes dark during one of the most anticipated sporting matches.

View more: FuboTV goes kaput during World Cup semifinals, blames “criminal cyber attack”

ArtStation artists stage mass protest against AI-generated artwork

Users of popular portfolio site seek to castigate and disrupt AI-generated art.

View more: ArtStation artists stage mass protest against AI-generated artwork

Prosecutors charge 6 people for allegedly waging massive DDoS attacks

Meet Ghostwriter, a haunted AI-powered typewriter that talks to you

Lensa AI app causes a stir with sexy “Magic Avatar” images no one wanted

Only iPhones that can’t run iOS 16 are getting new iOS 15 updates

Microsoft digital certificates have once again been abused to sign malware

Effective, fast, and unrecoverable: Wiper malware is popping up everywhere

China bans AI-generated media without watermarks

North Korean hackers once again exploit Internet Explorer’s leftover bits

Adobe Stock begins selling AI-generated artwork

Syntax errors are the doom of us all, including botnet authors

Darknet markets generate millions in revenue selling stolen personal data

Apple slices its AI image synthesis times in half with new Stable Diffusion fix

OTHER TECH NEWS

Top Car News Car News