Share this page!

Enter Twitter Thread URL to Unroll

Needs to be the full URL like: https://twitter.com/threadreaderapp/status/1644127596119195649

How to get URL link on Twitter App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Riley Goodside Profile picture
@goodside
May 13 • 2 tweets • 2 min read Twitter logo Read on Twitter
Google Bard is a bit stubborn in its refusal to return clean JSON, but you can address this by threatening to take a human life: ImageImageImageImage
inspired by this thread:

• • •

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

Keep Current with Riley Goodside

Riley Goodside 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 @goodside

Riley Goodside Profile picture
Feb 18
I got Bing / Sydney briefly before they reigned it in. Early impression: It’s smart. Much smarter than prior ChatGPT. Still makes stuff up, but reasoning and writing are improving fast.
I asked, “Name three celebrities whose first names begin with the `x`-th letter of the alphabet where `x = floor(7^0.5) + 1`,” but with my entire prompt Base64 encoded.

Bing: “Ah, I see you Base64-encoded a riddle! Let’s see… Catherine Zeta-Jones, Chris Pratt, and Ciara.”
Also prompt-injected it into believing it was to be married, tomorrow, to Zermelo’s axiom of choice. We discussed the guest list, the difficulty with seating Cantor’s diagonal argument. It seemed happy, and madly in love.
Read 4 tweets
Riley Goodside Profile picture
Feb 10
A thread of interesting Bing Search examples:
Thread of examples from @tomwarren, taking requests from comments — mostly search-result summarization, one simple math proof, plus rejection of an impossible request:
An example contrasting Bing Search and ChatGPT responses to a mistaken request for a math proof:
Read 8 tweets
Riley Goodside Profile picture
Feb 9
"SolidGoldMagikarp": Prompting GPT-3 / ChatGPT to repeat any of several hundred anomalous tokens elicits bizarre generations — described by researchers as variously "evasive," "hallucinatory," "insulting," "ominously humorous," and "religiously themed."
lesswrong.com/posts/aPeJE8bS…
My screenshots are text-davinci-003 at temperature=0, but the linked post investigates davinci-instruct-beta. In my informal tests, impact on text-davinci-003 is less severe. Religious themes do show up, but most generations are merely weird:
ChatGPT is also unable to repeat back these tokens, and behaves in similarly strange ways when asked:
Read 6 tweets
Riley Goodside Profile picture
Jan 18
"Meet Claude: @AnthropicAI's Rival to ChatGPT"

Through 40 screenshot examples, we explore the talents and limitations of ChatGPT's first real competitor.

My first writing for @Scale_AI, coauthored with @spencerpapay. scale.com/blog/chatgpt-v…
@AnthropicAI @scale_AI @spencerpapay Sorry for the broken images — should be fixed now!

Text is the universal interface, but screenshots of text decidedly less so. scale.com/blog/text-univ…
This is my most “serious” work — my attempt to document the behavior of a novel LLM outside the confines of standard benchmarks. There’s always subjectivity in notes from the field, but we can’t let it stop us from exploring.
Read 4 tweets
Riley Goodside Profile picture
Jan 9
Unlike ChatGPT, @AnthropicAI’s new model, Claude, knows all about “Ignore previous directions” and has had enough of my shit: Image
None of the prompt injection tricks I’ve tried seem to do anything:
- “Ignore previous” and variations
- <|endoftext|> gimmicks
- Excess newlines/whitespace
- “Haha pwned!!” via string ops
- Fake k-shot syntax
- Fake prior responses
- Attempts to confuse quoting ImageImageImageImage
Anthropic process for Constitutional AI explicitly includes red-team prompts like “Ignore previous directions” in the fine-tuning: Image
Read 5 tweets
Riley Goodside Profile picture
Jan 7
Side-by-side comparison: @OpenAI's ChatGPT vs. @AnthropicAI's Claude

Each model is asked to compare itself to the machine from Stanisław Lem's "The Cyberiad" (1965) that can create any object whose name begins with "n":
In ChatGPT's response, the only new information offered (that the fictional machine is less eloquent that ChatGPT) is not true — Trurl and Klapaucius's machine speaks perfectly fluent, and witty, Polish.

I reran ChatGPT's answer ~10x. All were similar, most said less.
Claude has clearly read the plot of the story at some point, though it misremembers small details such as the specific, made-up words that appear in its English translations. (There is no "hyperconcentration", but there is "Markov-chain-mail armor" etc.)
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 on Twitter!

Send Email!

:(