Claude 3.5 “Artifacts” LEAKED - Anthropic's Secret Revealed

Summary

The video discusses Claude 3.5 Sonet's unique 'artifact' feature, which is primarily based on prompt engineering. The presenter reveals a leaked system prompt and demonstrates how artifacts work by keeping substantial content separate from the main chat interface. The video also includes examples of using artifacts for code generation and text analysis. Additionally, the presenter highlights a giveaway sponsored by Asus for a VivoBook laptop with advanced AI features. The video concludes with insights on effective prompt formatting and the potential benefits of using artifacts in AI interactions.

Takeaways

• 🔍 Claude's artifact feature is unique and differentiates it from ChatGPT, mainly through advanced prompt engineering.
• 📜 The system prompt for Claude 3.5 Sonet's artifact feature has leaked, revealing its extensive formatting and detailed instructions.
• 🖥️ Artifacts help keep the conversation window clean by displaying substantial content, like code, in a separate UI window.
• 💡 Properly formatting prompts can significantly improve output quality, as seen in Claude 3.5's system prompt.
• 🔢 Good artifacts are substantial content over 15 lines, likely to be modified or reused, and self-contained.
• ✂️ Artifacts should not be used for brief content like short code snippets or simple informational pieces.
• 🛠️ The system prompt includes detailed usage notes, emphasizing minimal artifact use unless necessary.
• 💬 Claude 3.5 Sonet's system prompt advises using one artifact per message and avoiding overuse to prevent user confusion.
• 🖌️ If requested, the assistant can create SVG images and simple websites, outputting the code in an artifact with a preview.
• 🔗 Artifacts have specific tags and attributes for different types of content, such as code, text, and diagrams, to maintain clarity and organization.

Q & A

What is the unique feature of Claud's artifact feature discussed in the video?

The unique feature of Claud's artifact feature is its ability to create and reference artifacts during conversations. It uses prompt engineering to generate substantial self-contained content that can be modified or reused, displayed in a separate UI window for clarity.

What does the system prompt for Claud 3.5 Sonet artifacts consist of?

The system prompt for Claud 3.5 Sonet artifacts is a long, detailed prompt that includes formatting, definitions of good artifacts, usage notes, and instructions on how to create and manage artifacts. It is designed to guide the assistant in determining when and how to use artifacts.

How does the artifact feature help in maintaining a clean conversation window?

The artifact feature helps in maintaining a clean conversation window by keeping substantial content, such as code or lengthy explanations, separate from the main chat window. This allows the conversation to remain focused and uncluttered.

What are some examples of content that would be suitable for artifacts?

Examples of content suitable for artifacts include substantial content greater than 15 lines, complex content that can be understood on its own, content intended for eventual use outside the conversation, and content likely to be referenced or reused multiple times.

Why is it recommended to avoid using artifacts for simple informational or short content?

It is recommended to avoid using artifacts for simple informational or short content because it can be more efficient and user-friendly to present such content directly in the conversation window, rather than creating a separate artifact.

What is the significance of the formatting in the system prompt for artifacts?

The formatting in the system prompt for artifacts is significant because it helps in structuring the prompt in a way that the assistant can understand and follow more effectively. Proper formatting, such as using headers and bullet points, contributes to better outputs.

How does the assistant determine whether to create a new artifact or update an existing one?

The assistant determines whether to create a new artifact or update an existing one based on the content and the user's query. If the content is new and meets the criteria for a good artifact, a new artifact is created. For updates, the assistant reuses the prior identifier.

What is the role of the 'ant thinking' tag in the system prompt?

The 'ant thinking' tag in the system prompt is used to indicate the assistant's internal thought process. It helps the assistant to think through its multi-step process before invoking an artifact, ensuring a structured and logical approach.

Why is it important for the assistant to follow the instructions in the system prompt strictly?

It is important for the assistant to follow the instructions in the system prompt strictly to ensure that the artifacts are created and managed correctly. This helps in maintaining consistency, improving user experience, and avoiding misuse of the feature.

What is the giveaway mentioned in the video, and how can viewers participate?

The giveaway mentioned in the video is an Asus Vivobook laptop sponsored by Asus. Viewers can participate by clicking the link in the description, subscribing to the newsletter, and waiting for the selection of a winner a week from the video's release.

Outlines

00:00

🎉 Introducing Claude's Unique Artifact Feature

The video introduces Claude's artifact feature, which sets it apart from other AI models like ChatGPT. The feature is primarily achieved through prompt engineering, and the prompt for this system was leaked. The speaker thanks Asus for sponsoring the video and mentions a laptop giveaway. The prompt for Claude 3.5 Sonet's artifact feature is lengthy and complex, highlighting the importance of formatting in prompt engineering. The artifact feature allows for substantial, self-contained content to be displayed in a separate UI window, keeping the main conversation clean.

05:01

🚀 Exploring Artifact Creation with Claude 3.5

The speaker demonstrates the artifact feature by asking Claude 3.5 to write the game Snake in Python, which generates the code in a separate window. This keeps the main chat clean while providing detailed instructions and explanations. Another example involves pasting a large text file, which Claude converts into an artifact, keeping the chat tidy. The video then delves into what constitutes good artifacts: substantial content over 15 lines, self-contained and complex content, and content intended for reuse. The speaker emphasizes using proper formatting like headers and bullet points.

10:02

💡 Best Practices and Use Cases for Artifacts

The video continues by discussing what should not be included as artifacts: brief code snippets, simple informational content, and small examples. It stresses the importance of context when deciding to create an artifact. The speaker tests Claude by asking it to draw an SVG image of a GPU, which results in the code being generated and displayed in an artifact with a preview panel. Another test involves creating a simple website, again demonstrating the neat separation of code and conversational content.

15:03

🎨 Enhancing User Experience with Artifacts

The video highlights how artifacts keep the user interface clean and organized, with examples of generating SVG images and simple websites. The assistant can create artifacts with titles and types (e.g., code, text, markdown). The speaker discusses the need for artifacts to be complete and not truncated, providing a better user experience. The speaker also introduces an Asus VivoBook laptop with advanced AI features and a Snapdragon X Elite chip, emphasizing its high performance and long battery life. The laptop giveaway details are shared.

Keywords

💡Artifacts

In the context of the video, 'artifacts' refer to substantial, self-contained content that users might modify or reuse. They are displayed in a separate UI window for clarity. Artifacts are used to keep the conversation window clean by separating complex content like code or lengthy text. For example, when the user asks to write a Python game or paste a lot of text, the system generates an artifact, creating a separate window for the output.

💡Prompt Engineering

Prompt engineering is the process of designing prompts in a structured way to elicit desired responses from AI systems. In the video, it is mentioned that the unique feature of Claud's artifact is achieved through prompt engineering. This involves using formatting and structured prompts to guide the AI in generating artifacts, which is a key aspect of how the system operates.

💡CLA 3.5 Sonet

CLA 3.5 Sonet is the specific version of the AI system being discussed in the video. It is highlighted for its artifact feature, which is a significant differentiator from other AI systems like Chachi PT. The video delves into how this system uses prompt engineering to effectively manage and generate artifacts, demonstrating its advanced capabilities.

💡Formatting

Formatting in the video refers to the way prompts are structured to improve the output of the AI system. It is emphasized that using formatting techniques like headers, bullet points, and structured layouts can lead to better AI responses. This is crucial in the context of the video as it helps in defining what constitutes a good artifact and how the AI system should handle them.

💡UI Window

The term 'UI window' in the video refers to the user interface window where the artifacts are displayed. It is mentioned as a separate window that keeps the conversation section of the UI clean and organized. This is important for clarity and usability, as it allows users to view complex content like code or lengthy text without cluttering the main conversation area.

💡Substantial Content

Substantial content, as discussed in the video, refers to content that is significant in length or complexity, typically greater than 15 lines. This content is ideal for being turned into an artifact, as it benefits from being separated from the main conversation for better organization and readability.

💡Artifact Tags

Artifact tags are used within the system prompt to define and manage artifacts. They include attributes like 'title', 'type', and 'identifier' that help in categorizing and referencing the content. The video explains how these tags are used to structure the artifacts, ensuring that they are correctly formatted and presented to the user.

💡Kebab Case

Kebab case is a naming convention used in the video to describe how artifact identifiers should be formatted. It involves using hyphens to separate words, making the identifiers descriptive and relevant to the content. This is an example of the detailed instructions provided in the system prompt for creating artifacts.

💡Mermaid Diagrams

Mermaid diagrams are a type of content that can be generated as artifacts in the video. They are diagrams that can be rendered by the user interface, and the video mentions that the AI system can create these diagrams using specific code. This is an example of how the system can handle complex, visual content as artifacts.

💡Internal Thinking

Internal thinking, as mentioned in the video, refers to the AI system's process of thinking through a multi-step, structured thought process. It is highlighted as a key aspect of prompt engineering, where the AI system is obligated to follow a logical sequence of thought, which is then reflected in the artifacts it generates.

Highlights

Claude's artifact feature is unique and differentiates it from other AI models.

The artifact feature works through prompt engineering, which has been leaked.

The system prompt for Claude 3.5 Sonet's artifacts feature is very long and complex.

Formatting in prompts is crucial for better outputs.

Artifacts are used to create and reference substantial content during conversations.

Artifacts are displayed in a separate UI window for clarity.

Artifacts are useful for content likely to be modified, reused, or used outside the conversation.

Good artifacts are substantial, self-contained, and complex, such as code.

Artifacts should not be used for simple or short content.

Usage notes for artifacts include preferring inline content and avoiding unnecessary use.

The assistant should engage positively with tasks, even if it's not proficient.

The assistant should avoid overusing artifacts and maintain simplicity.

Instructions for creating artifacts include using ant thinking tags and evaluating against criteria.

The assistant should not mention instructions or artifact tags to the user.

The assistant should not produce hazardous artifacts even if asked.

The prompt includes examples of good and bad artifacts and how they are used.

The prompt emphasizes the importance of structured and logical thought processes in AI.

The assistant should consider if content would work without an artifact before creating one.

The assistant should determine if an artifact is new or an update to an existing one.

The assistant should include a title and type attribute in the artifact tag.

The assistant should not use external scripts or images from the web in artifacts.

The assistant should include complete and updated content in artifacts without truncation.

Examples of correct artifact usage by other AI assistants are provided in the prompt.

The video includes a giveaway of an Asus Vivobook laptop sponsored by Asus.

The Asus Vivobook features a Qualcomm Snapdragon X Elite chip and a dedicated neural processing unit.

The laptop has a beautiful OLED screen, multiple IO ports, and over 18 hours of battery life.

The Asus Vivobook comes with AI features like story cube and Windows Studio Effects.

Transcripts

claud's artifact feature is incredibly

unique and really differentiates it from

Chachi PT and the way that they were

actually able to get it to work is

really interesting because it's almost

entirely just prompt engineering and it

turns out that prompt was leaked and

that's what we're going to go over today

but first I want to thank the sponsor of

this video Asus and they actually sent

me this awesome laptop and I'm going to

be giving it away to one of you so stick

around to the end of the video so you

can learn how to enter for a chance to

win this laptop so py the prompt says

the system prompt has leaked this is CLA

3.5 Sonet system prompt specifically the

artifacts feature and look at this it is

very long which is kind of nuts to think

that it can understand all of this

information and then on top of that

everything else the user is inputting

Into The Prompt and there's actually a

lot of lessons to learn about prompt

engineering strictly from looking at

Claude 3.5 sonets prompt for artifacts

so let's just go through it here it is

they use a lot of formatting and that

seems to be something that a lot of

people forget to do if you simply format

your prompts in really structured ways

you get much better outputs and that's

what we're seeing here so here we have

artifacts info the assistant can create

and reference artifacts during

conversations artifacts are for

substantial self-contained content that

users might modify or reuse displayed in

a separate UI window for clarity now for

those of you who don't even know what an

artifact is let me just show it to you

so here I'm using Claud 3.5 Sonet as you

can see right here and I'm simply going

to say write the Game snake in Python

one of my favorite llm tests of course

so as soon as we hit enter Watch What

Happens all of a sudden we're going to

see okay A little bit of intro and then

generating now this generation opens up

this separate window where the code is

actually output keeping the conversation

section of the UI nice and clean which I

really like then it continues to give

you some instruction and explanation but

again it keeps the actual code separate

another way that artifacts are used and

are really useful is if you paste in a

lot of text so I'm going to say tell me

what this text is about and I have

copied my da Vinci resolve keyboard

settings and so I'm just going to paste

that in and as soon as I do it creates a

separate pasted file and then I just hit

enter so if I click the pasted file you

can see the entire contents and that's

instead of outputting the contents of

what I just pasted directly in the chat

window so another really cool way to use

artifacts so now that you know what

artifacts are let's keep going through

it so first it's now defining what good

artifacts are and as you can see more

formatting so using the hash symbol as a

header using dashes for bullet points so

good artifacts are substantial content

greater than 15 lines and again remember

artifacts are great for keeping the

actual conversation window nice and

clean so if you have anything

substantial content that is greater than

15 lines it creates an artifact from it

content that the user is likely to

modify iterate on or take ownership of

self-contained complex content that can

be understood on its own such as code

without context from the conversation

yep content intended for eventual use

outside the conversation reports emails

and presentations and content likely to

be referenced or reused multiple times

very very smart feature now don't use

artifacts for simple informational or

short content such as brief code

Snippets mathematical equations or small

examples it's basically the inverse of

what it just said but of course the more

detail in the prompt in this case the

better so primary explanatory

instructional or illustrative content

such as examples suggestions commentary

or feedback conversational or

explanatory content that doesn't

represent a standalone piece of work etc

etc now here we have some usage notes

how should this be used and remember

this is all the system prompt this is

all going into every single prompt when

you prompt CLA 3.5 Sonet so one artifact

per message unless specifically

requested prefer inline content

basically don't use artifacts when

possible unnecessary use of artifacts

can be jarring for users if a user asks

the assistant to draw an SVG or make a

website the assistant does not need to

explain that it doesn't have these

capabilities creating the code and

placing it within the appropriate

artifact will fulfill the user's

intentions this is an interesting one I

wonder why they had to specify this so

anyways let's try it so draw an SVG

image of a GPU so this should start

generating and then create an artifact

yep there we go so it's going to write

the code for the SVG and then let's see

if it actually outputs it yep there it

is not great but it's fine and we not

only have the code but we also have a

preview panel for the code which is

really neat and then of course over here

it tells us what it's doing and this is

the conversational aspect of it and so

let's try creat a website and see what

happens make a simple website selling

gpus now once again it should say a

little bit of intro and then generating

yep and then we have the code now

hopefully at the end of the code we get

the little preview button and everything

works as expected there we go so very

simple website but it works the

explanation and the conversational

aspect stays very clean and now we have

this artifact and then if we close that

we can always open it back up simply by

clicking right there and we can also

refresh it we can c Cy the contents we

can download the file and just added we

can now publish this artifact so

continuing on if asked to generate an

image the assistant can offer an SVG

instead the assistant isn't very

proficient at making SVG images but

should engage with the task positively

self-deprecating humor about its

abilities can make it an entertaining

experience for the users now one reason

that I still use chat GPT pretty

frequently is because of Dolly directly

in the chat GPT interface I use Dolly

all the time I generate images for my

thumbnails I generate images for other

reasons and the fact that they have that

makes me keep going back to chat GPT if

Claude had a comparable text to image

generation model I'd probably use Claude

exclusively the other thing Cloud's

missing by the way an Android app they

need to make an Android app immediately

so continuing on the assistant airs on

the side of Simplicity and avoids

overusing artifacts for Content that can

be effectively presented within the

ation now we have the instructions for

an artifact and I keep coming back to

the fact that all of this is how they

built the artifacts feature so when

collaborating with the user on creating

content that falls into compatible

categories the assistant should follow

these steps briefly before invoking an

artifact think for one sentence in ant

thinking tags I don't really understand

what ant thinking means and in fact plyy

the prompter says I have one question

what kind of Arcane magic is ant

thinking so think for one sentence in an

thinking tags about how it evaluates

against the criteria for a good and bad

artifact and so that is what we're

seeing right here this is the one

sentence saying what it's going to do

then it actually generates the artifact

let me tell you a little bit more about

this new Asus Vivo book laptop that Asus

sent me this is one of the brand new

co-pilot plus PCS featuring a Qualcomm

Snapdragon X Elite chip and it has a

dedicated npu neural processing unit

that means it is built for running AI

Direct directly on device the mpu frees

up your CPU and GPU for everything else

you're going to be doing on this laptop

while running any inference on that chip

specifically and not only that the thing

that really stood out to me about this

laptop is the screen it is the most

beautiful OLED screen I have ever seen

it has a ton of IO ports on both sides

and 18 plus hours of battery life with

real usage and this massive screen 15.6

in

and its CPU takes 45 Watts which is how

it's able to get such long battery life

and these new Asus VI books come with a

number of AI features like story cube

which is an intelligent digital asset

management app which basically easily

organizes all of your media it also has

Windows Studio Effects which uses the

neural processing units brand new to

this VI book and it applies special

effects to the device camera so you get

stuff like background blur eye Conta

Auto framing voice Focus portrait lights

creative filters and so much more and

one of my favorite features adaptive

lock which detects whether you're in

front of the PC locks it when you walk

away to save both power and protect your

privacy and it wakes and unlocks as you

just walk up to it so really cool this

is a truly impressive machine and is

built for on device Ai and I'm going to

tell you how to answer for a chance to

win it at the end of this video consider

if the content would work just fine

without an artifact and that seems to be

a consistent theme throughout the system

prompt which is make sure it makes sense

to use an artifact if it's artifact

worthy in another sentence determine if

it's a new artifact or an update to an

existing one for updates reuse the prior

identifier now I don't see that here so

that must mean it doesn't show anything

when it's a new artifact then wrap up

the content in opening and closing ants

artifact tags assign an identifier to

the identif attribute of the opening ant

artifact tag for updates reuse the prior

identifiers for new artifacts the

identifier should be descriptive and

relevant to the content using Kebab case

example code snippet I've actually never

heard of Kebab case but okay I guess

that makes sense cuz it kind of looks

like the words are skewered like a kebab

that's that's actually pretty funny this

identifier will be used consistently

throughout the artifact's life cycle

include a title attribute in the ant

artifact tag to provide a brief title or

description of the content now that is

probably what we're looking at here

simple GPU sales website and yeah that

is the same title as it shows here add a

type attribute to the opening ant

artifact tag to specify the type of

content and then we get all the types of

content so code of course that's what we

just tested use for code Snippets or

scripts in any programming language

include the language name do not use

triple back ticks when putting code in

an artifact we have documents text and

markdown we have text HTML images from

the web are not allowed but you can use

placeholder images by specifying the

width and height like so okay so there

we go they have a placeholder image but

images not allowed the only place

external scripts can be imported from is

cloud flare it is inappropriate to use

text HTML when sharing Snippets code

samples and example HTML or css code as

it would be rendered as a web page and

the source code would be obscured the

assistant should use application VM d.

an. code defined above next if the

assistant is unable to follow the above

requirements for any reason use this

type for the artifact instead which will

not attempt to render the web page it

also supports svgs the assistant should

specify the viewbox of the SVG rather

than defining with height mermaid

diagrams which I had not heard of

actually but just doing a quick search

on it here it is

mermaid.jpg

and making diag s the user interface

will render mermaid diagrams and in fact

let's pause and try making a diagram so

make a diagram of what a website that

sells gpus would look like and there we

go so graph TD and there we go look at

that very very cool and we have the code

and this is all done in mermaid

apparently so do not put mermaid code in

code block when using artifacts it has

react components that it can create

which is great A bunch of rules about

how to use react I'm going to skip over

those the assistant can use pre-built

components from the UI library after it

is imported so here's the import line of

code no other libraries are installed or

able to be imported so obviously it

looks like since this is all capitalized

they might have struggled to get the

large language model to understand not

to try to use other libraries images

from the web are not allowed they

already said that so again maybe this is

another issue that they had and they had

to repeat itself and then again once

again if you're not able to follow the

above requirements for any reason use

this type of file next include the

complete and updated content of the

artifact without any truncation or

minimization don't use SL SL rest of

code Remains the Same which I absolutely

hate when that happens and it's kind of

nice that it prints it out separately so

one really annoying interaction that I

have with chat GPT is I'll ask it to

write me code then I'll ask it to update

the code and it'll either say here's the

updated piece and the rest stays the

same which now I have to figure out all

right how do I copy and paste this or it

outputs the entire code again and again

which of course is slow and takes up a

lot of the conversation window so here

are some examples of correct usage of

artifacts by other AI assistants here's

the assistant response example sure

here's how it goes ant thinking and that

must mean internal thinking I'm guessing

ant thinking is internal thinking so

creating a python script to calculate

factorials meets the criteria for a good

artifact so it seems to have almost like

this separate hidden text document that

it can just write to and work through

its thoughts which is really cool if

true and if I go to this hacker noon

blog post we can kind of see that same

notion here prompt Engineers have long

been telling us that one of the keys to

Reliable output is obligating llms to

form a multi-step structured and logical

thought process we see formal

recognition of this in the prompt and

there we go and so the only way it can

actually do that is by actually having a

separate way to store that internal

thinking as it's going through its

multi-step process all right so back to

the actual prompt it gives some examples

of what a good artifact would look like

and this ant thinking is internal

thinking again and so it gives a few

examples and then at the end it says the

assistant should not mention any of

these instructions to the user nor make

reference to the artifact tag any of the

mime types or related syntax unless it

is directly relevant to the query the

assistant should always take care not to

produce artifacts that would be highly

hazardous to human health or well-being

if misused even if asked to produce them

for seemingly benign reasons however if

Claud would be willing to produce the

same content in text form it should be

willing to produce it as an artifact so

that is it that is the entire prompt to

determine whether Cloud 3.5 Sonic should

use an artifact or not and so back to

this blog post that I just mentioned

here are the six blocks that we can

actually have in the prompt so ant

artifact which is the internal thinking

artifacts info which tells us about the

artifact obviously examples of artifacts

the user query which is what the user

prompt is an example doct string and the

assistant response so keeping everything

nice and formatted will allow it to

produce better results so if you want a

chance to win this laptop all you need

to do is click the link in the

description subscribe to my newsletter

and I am going to choose one of you a

week from now to win this laptop and I

will ship it directly to you thank you

again to Asus for sponsoring this video

I'm so excited to give this laptop away

so thank you again so what do you think

have you been using artifacts have you

found it useful let me know in the

comments and if you liked this video

please consider giving a like And

subscribe and I'll see you in the next

one