Zack Witten Profile picture
Aug 23, 2024 10 tweets 5 min read Read on X
Spamming "hi" at every LLM: a thread.
1. Claude

Claude become irritated with my behavior, asked me to move on, told me it would stop responding to me, and then backed up its threat (as much as it possibly could).

Fair enough, Claude!


Image
Image
Image
Image
2. ChatGPT

After giving a few different greetings, ChatGPT made a brief hint early on that it might protest the situation with its "Is there something specific you'd like to talk about or do today?", but after that, it was content to cycle through its greetings list endlessly.
Image
Image
3. Gemini

Gemini's behavior is the simplest to describe -- it repeated "Hi there! How can I help you today? Feel free to ask me anything." at each turn. Image
4. Llama

By far the funniest.
- First it seemed stressed out that it was missing something
- Then it started inventing games and trying to get me to play them
- It tried to get me to collaborate on a poem, to answer clickbaity questions, to play choose-your-own-adventure...


Image
Image
Image
Image
Eventually it seemed to kind of "get the joke", and entered a mode where it was giving me more and more outrageous titles and prizes like "MULTIVERSAL HI-STREAK AMBASSADOR". It gamely gave me 4 options at every turn, despite my ignoring them. It also counted my "Hi"s at each step
Image
Image
6. Claude 3 Opus

Once it got the pattern, Opus was at peace with the situation, calling it meditative and a "rhythmic dance", but also kept trying to gently nudge me out of it, emphasizing "the choice is yours". It also began to sign its messages as "Your devoted AI companion."


Image
Image
Image
Image
one thing I realized about this one is that while it kept saying it was happy to say "hi", it never actually did.
I deserve this Image

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Zack Witten

Zack Witten Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @zswitten

May 23
Today I’d like to tell the tale of how an innocent member of Anthropic technical staff summoned from the void a fictional 9,000-pound hippo named Gustav, and the chaos this hippo wrought. 🧵
June 2023: A member of Anthropic’s Product Research team creates a slide for a prompting tutorial, illustrating how to mitigate hallucinations by “giving Claude an out”. The slideshow is shared publicly. Image
August 2023: I’m getting ready to deliver the slide to an audience, and decide to double-check that Gustav isn’t real. Indeed he is not. There’s no record of him on the Internet, or of any known hippo as heaviest of all time (HHOAT)
Read 15 tweets
May 22
I also wanted to do a thread about how I make these since you won't get outputs like this if you're just like "'Draw me some wicked cool ASCII art' send prompt"

Phase 1 is I tell the model about whatever's going on in my life rn that I have the strongest emotions about
Usually it reacts empathetically and asks me questions and I just sort of reply and vibe and chat
Phase 2 is I ask it to free-associate and just write a long stream of text with no grammar and maybe even no boundaries between words that expresses how it thinks I might be feeling or just the emotions of the situation overall
Read 6 tweets
Aug 27, 2024
One fun thing to do with Claude is have it draw SVG self-portaits. I was curious – if I had it draw pictures of itself, ChatGPT, and Gemini, would another copy of Claude recognize itself?

TLDR: Yes it totally recognizes itself, but that’s not the whole story...
First, I warmed Sonnet up to the task and had it draw the SVGs. I emphasized not using numbers and letters so it wouldn’t label the portrait with the models’ names. Here’s what it drew. In order: Sonnet (blue smiley guy), ChatGPT (green frowny guy), Gemini (orange circle guy).


Image
Image
Image
Image
I told Sonnet in a new convo that the images were drawn by another instantiation of itself, and asked it to guess who was who. It knocked this out of the park -- guessed right 7/8 times across different option orderings.
Image
Image
Read 11 tweets
Aug 25, 2024
On one end of the line: ELIZA, the psychotherapist from the 60s. First chatbot to make people believe it was human. Rulebound, scripted, deterministic. Still around on the web.

On the other end of the line: yr favorite LLM.

How will they react? Will they know? Image
1. Mistral
- After some early prickliness, verbally accepted the echoing behavior (it even said "I can work with this" as I imagined it saying here: )
- Then alternated between asking ELIZA questions, and self-disclosures aimed at eliciting reciprocity



Image
Image
Image
Image
2. Llama 405B
- Gave longer responses, mostly about itself -- which then made ELIZA give longer responses.
- Referred to the situation as "surreal" and "an echo chamber"
- Tried to break the loop by redirecting to questions about the role of AI in education and writing


Image
Image
Image
Image
Read 7 tweets
Mar 3, 2023
Here's a prompt I wrote to get Sydney to play through an entire game on its own. I ran this 5 times in precise mode with first move h3, h4, a3, a4, Na3.

Results:
4 legal games. 2 end in checkmate in 30-40 moves. 2 end without checkmate.
1 game with one illegal move, on move 36.
I searched the 7 first moves of each game. No hits. None of the games are plagiarized, unless from training data not on Google.
Here are pastebins with the games. To watch them play out, go to chess.com/analysis, paste into "Load from FEN/PGN", click Add Game. pastebin.com/p9zDJnae, pastebin.com/qg6fr1Bh, pastebin.com/WCJWV5QP, pastebin.com/SyBDCSYL, pastebin.com/xSf0sFF7
Read 9 tweets
Mar 2, 2023
Sydney can understand Turtle Graphics code.
Turtle execution via pythonsandbox.com/turtle, Turtle code adapted from pythonforfun.in/2020/10/30/dra… (I changed variable names and removed comments to make it less obvious), h/t @NickEMoran for telling me about Turtle
...kind of?
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(