Why & When You Should be Using Claude over ChatGPT

Summary

This video script explores the advantages and disadvantages of two leading AI language models, OpenAI's Chat GPT and Anthropics' CLA. It compares their features, such as Chat GPT's tooling and CLA's superior coding capabilities, and provides guidance on when to use each for tasks like project management, writing, and coding. The script also discusses the importance of custom instructions for personalized AI experiences and suggests scenarios where each model excels, emphasizing the need to mix and match them for optimal results.

Takeaways

• 😀 Chat GPT and Anthropic's CLA are the two AI models that stand out among many others for their advanced features.
• 🔍 Chat GPT offers unique tools such as data analysis, image generation, and web browsing capabilities.
• 🔗 Chat GPT allows for sharing of GPT instances with others, which can be powerful for collaborative problem-solving.
• 📚 Anthropic's models are preferred for their more human-like tone and style in writing.
• 📁 Anthropic's CLA projects can handle more extensive context and are better for coding projects, especially with the Sonnet 3.5 model.
• 📱 Chat GPT has the advantage of a mobile app, providing convenience for on-the-go use.
• 🔄 Chat GPT and CLA projects have their own set of advantages and disadvantages, making them suitable for different use cases.
• 🛠️ Chat GPT is ideal for creating AI applications or prompts to share with others, thanks to its customization and sharing capabilities.
• 🎓 Chat GPT excels as an assistant, tutor, or coach due to its conversational and practical approach.
• 🖌️ CLA projects are excellent for writing and coding projects that require maintaining a consistent style or handling multiple code snippets.
• 🔄 The choice between Chat GPT and CLA projects should be based on the specific needs of the task at hand, such as the need for tooling, context handling, or project-based work.

Q & A

What are the two AI models mentioned in the script that stand out among others?

The two AI models mentioned are OpenAI's Chat GPT and Anthropics' CLA (Claude).

What is the current best model according to the script?

The current best model mentioned is Sonnet 3.5, which is part of the Anthropics CLA suite.

What are the advanced features offered by Chat GPT and Claude that are causing confusion?

The advanced features causing confusion are the 'gpts' and 'projects' within Chat GPT and the 'CLA' projects in Anthropics, as they offer different ways of working with the models.

What is unique about Chat GPT's image generation tool?

Chat GPT's image generation tool, known as DALL-E, is unique because it allows for image creation, which is not available in Claude at the time of the script.

What is the browsing feature of Chat GPT and how does it work?

The browsing feature of Chat GPT allows it to search the internet, retrieve up to five links, and use the content of those pages within its answers. It's not perfect and sometimes requires specific instructions to use.

What is the advantage of Chat GPTs over Claude projects in terms of sharing?

Chat GPTs can be shared with others, allowing them to use the GPT without needing a paid plan, which is not possible with Claude projects at the time of the script.

What is the main advantage of Claude projects over Chat GPTs in terms of coding?

Claude projects, particularly with the Sonnet 3.5 model, are considered better at code due to an improved tone and extensive knowledge base.

What is the context window limitation of Chat GPTs?

Chat GPTs have a limited context window in their knowledge base. The script suggests a rule of thumb of up to 15 pages of content for reliable context retention.

What are the tooling advantages of Chat GPTs that are not available in Claude projects?

Chat GPTs offer tooling advantages such as data analysis with the code interpreter, image generation with DALL-E, browsing the internet, sharing GPTs, conversation starters, and actions for external API calls.

How does the script suggest using custom instructions to enhance the AI experience?

The script suggests using custom instructions to personalize the AI experience, making it more intuitive and tailored to individual needs, and enabling the AI to better assist with specific tasks.

What are some concrete examples of when to use Chat GPTs and when to use Claude projects?

Use Chat GPTs for sharing AI applications, building solutions for others, and tasks that require the tooling advantages of Chat GPTs. Use Claude projects for writing or coding projects that benefit from a longer context and better tone/style, and where multiple chats are needed.

Outlines

00:00

🤖 AI Models Comparison and Use Cases

The paragraph discusses the prevalent AI models, specifically Chat GPT and Anthropics CLA, and their advanced features like gpts and projects. It highlights the confusion among users regarding when to use each model and promises to provide clear answers. The script also mentions Google's Gini 1.5 Pro for its large context window and video uploading capability. The advantages of Chat GPT's tooling, such as data analysis, image generation, browsing features, and shareability, are contrasted with its disadvantages, including a less human tone and limited context window. The paragraph sets the stage for a deeper dive into specific use cases for each model.

05:00

🔍 Advantages and Disadvantages of CLA Projects

This paragraph explores the benefits and drawbacks of using Anthropics CLA projects, positioning them as the opposite of Chat GPT's features. It emphasizes the ability to have multiple chats within a project, better coding capabilities with the Sonet 3.5 model, and a more human-like tone and style. The longer context window in the knowledge base is also noted. However, the lack of tooling such as prompt presets, external API access, image generation, and browsing is pointed out as a disadvantage. Additionally, the paragraph mentions the search function's limitation in CLA projects and the importance of custom instructions for personalizing the AI experience.

10:02

🛠️ Use Cases for AI Models in Projects and Assistance

The final paragraph delves into concrete use cases for both Chat GPT and CLA projects. It suggests that CLA projects are ideal for writing and coding tasks due to their ability to maintain consistent style and context across multiple chats. The paragraph also advises on when to use Chat GPT, such as for building solutions to share with others, utilizing its tooling for data analysis and image generation, and for creating custom tutors or assistants. It concludes by emphasizing the importance of personal context in customizing AI solutions and the effectiveness of Chat GPT for repetitive, specific tasks.

Keywords

💡AI Advantage Community

The AI Advantage Community is a professional network mentioned in the script, likely consisting of individuals who are knowledgeable about and interested in artificial intelligence. It is used as a reference point to highlight the consensus among professionals regarding the effectiveness of certain AI models. In the video, the community's opinion is sought to emphasize the popularity and utility of AI models like OpenAI's Chat GPT and Anthropic's CLA.

💡CLA (Claude 3.5)

CLA, or Claude 3.5, refers to a specific AI model developed by Anthropic. It is highlighted in the script as a model that stands out due to its advanced features and capabilities. The script mentions that it is particularly good at coding tasks and has a preferable tone and style in its responses, making it a preferred choice for certain projects over Chat GPT.

💡Chat GPT

Chat GPT is an AI model developed by OpenAI that is capable of engaging in conversation and performing tasks such as data analysis, image generation, and web browsing. The script discusses the advantages of Chat GPT, including its tooling and the ability to share GPTs with others, making it a versatile assistant for various tasks.

💡Projects

In the context of the script, 'projects' refers to a feature within AI models like Anthropic's CLA where multiple chats can be conducted within a single interface. This is contrasted with Chat GPT, which allows only one chat at a time. Projects are useful for handling complex tasks that require multiple interactions and the ability to reference previous conversations within the same context.

💡Data Analysis Tool

The Data Analysis Tool, formerly known as the Code Interpreter, is a feature of Chat GPT that allows users to analyze data by running Python code in a sandbox environment. This tool is highlighted as a significant advantage of Chat GPT, enabling tasks such as data visualization and cleaning.

💡Image Generation Tool

The Image Generation Tool, referred to as 'DI' in the script, is a unique capability of Chat GPT that allows it to generate images. This feature is not available in Anthropic's CLA, making it a distinctive advantage of Chat GPT for tasks that require visual output.

💡Browsing Feature

The Browsing Feature of Chat GPT enables the AI to access the internet and retrieve content from up to five links to use in its responses. While not perfect, this capability allows Chat GPT to provide more informed answers by incorporating external information, which is a notable advantage over CLA.

💡Conversation Starters

Conversation Starters, or prompt presets, are a feature of Chat GPT that allows users to set up predefined prompts for others to use. This is beneficial for sharing GPTs with others, as it ensures that they can achieve consistent results without needing to know how to craft effective prompts themselves.

💡Actions

Actions in the script refer to the ability to implement external API calls within Chat GPT. This feature allows users to perform tasks such as saving conversation results to a database or triggering other applications, enhancing the utility of Chat GPT in various workflows.

💡Mobile App

The Mobile App mentioned in the script is an advantage of Chat GPT, allowing users to switch context from their laptop to their mobile phone. This mobility is highlighted as a convenience for users who may need to use Chat GPT on the go, enhancing its accessibility and usability.

💡Custom Instructions

Custom Instructions are a feature that allows users to personalize their experience with AI models. By setting up custom instructions, users can tailor the AI's responses and behavior to their specific needs. The script emphasizes the importance of custom instructions in making AI models more intuitive and user-friendly.

Highlights

There are two standout AI models: OpenAI's Chat GPT and Anthropics' CLA.

OpenAI's GPT-3.5 is currently the best model for advanced features.

Chat GPT offers unique capabilities like data analysis tools, image generation, and browsing features.

Chat GPT allows sharing of GPTs with others, enhancing collaboration.

Anthropic's models are noted for a more human-like tone and style in writing.

GPTs have a limited context window, but a rule of thumb is up to 15 pages of content.

CLA projects can handle more context and are more reliable for extensive documents.

CLA allows multiple chats in one interface, which is beneficial for project-based work.

GPTs are advantageous for repetitive, specific tasks and have a mobile app for convenience.

CLA is better for coding projects, especially with the Sonet 3.5 model.

CLA projects are ideal for writing tasks where style consistency is crucial.

For coding projects, CLA's context awareness across multiple files is a significant advantage.

GPTs are excellent for creating AI applications or prompts to be shared with colleagues.

GPTs are superior for assistant, tutor, or coach roles due to their conversational and practical nature.

GPTs provide unique tooling like data analysis, image generation, and web browsing not available in CLA.

CLA projects are better suited for exploratory work where the outcome is not predetermined.

GPTs are more effective for tasks that require customization to a specific context.

GPTs can be used to build custom tutors for learning, leveraging personal context.

CLA's search function only looks at project names and descriptions, not the chat content.

Both GPTs and CLA projects can be customized with personal instructions for a personalized experience.

CLA does not offer a store, as projects are typically one-off and not recurring.

Transcripts

so these days there's really a lot of

good and very useful AIS AKA llms out

there but across our team the AI

Advantage Community my Professional

Network and The Wider internet the

consensus seems to be clear there's

really two of them that stand out open

eyes chat GPT and anthropics CLA right

now son 3.5 is the best model and both

of these offer Advanced features in

forms of gpts and projects these are

more specific ways of working with the

models rather than just talking to it as

you would to an assistant or a human but

this seem to have caused a lot of

confusion particularly the claw projects

feature because it is very different

from the gpt's feature inside of cat GPT

these days I get many mails comments and

questions in the community around when

to use what when do I want to use chat

GPT when do I want to use cloud when do

I use GPT when do I use project and

there's actually quite specific answers

to all of these questions and in this

video I'll present all of them to you

one more honorable mention should

actually go to gini 1.5 Pro from Google

their model has the largest context

window and it has the added capability

of you being able to to upload the

videos but that's a different topic so

without further Ado when do you use gpts

when do you use projects let's start by

looking at gpts and their advantages and

disad advantages as of today some the

advantages here are very clear the

tooling is just unmatched you have the

data analysis tool formerly known as the

code interpreter which helps you analyze

data by running python code in a sandbox

this opens up a lot of opportunities

with either data visualization or

cleaning and all sorts of other little

things that the packages available

within python in this environment can do

for for you then you obviously have the

image generation tool with di this is a

unique capability within chat GPT that

you do not have with mopic as of now you

also have a browsing feature it can go

out into the internet retrieve up to

five links and use the content of those

pages within its answer it's not

incredible but it's good enough a lot of

times it works although it is a little

hesitant to use this you often have to

specifically tell it hey go out there

and browse the internet go to this URL

and check it out nevertheless it's not

perfect but it's there and you can use

it here's another advantage that in my

opinion is maybe the biggest argument

here if you build gpts versus projects

you can actually share them and I don't

mean just sharing the conversation you

can actually share the GPT and let

somebody else use it now with GPT 40

being free to everybody only a few

messages but still free you could send

that GPT to any one of your co-workers

or family members and they can simply

check it out without having a paid plan

this can be very powerful if you solve a

specific problem of the GPT that the

other person might not know how to

approach with AI another unique

advantage of gpts is that you have these

conversational starters AK prompt preset

again this is a feature that you want if

you set it up for somebody else you

don't want them to guess what kind of

prompt they should run you just want to

set it up for them share it with them

and they get the results and then

obviously you have actions which allows

you to implement external API calls into

your GPT so you can do things like save

the results of a conversation to a

database or trigger some other

application as soon as the GPT is done

doing its thing and then last but not

least when it comes to advantages of

gpts over projects is you have the

mobile app and it's really easy to

switch context from your lapt top to

your mobile phone it's actually really

convenient and if you have use cases

that you might want to use on the go

it's great to have the mobility between

the gpts now what are the disadvantages

of gpts well they're kind of a

reflection of the advantages of the

project but let me briefly go for them

and as mentioned previously after going

through these advantages and

disadvantages we'll look at what

concrete examples you might want to be

using gpts over claw for or the other

way around so in the end we get more

specific rather than talk about the

features but the features are important

because to achieve a lot of results you

do need to have knowledge of the

features so disadvantages of gpts well

first of all a lot of people State and I

would agree that generally anthropics

models have a preferable tone of voice

and style to their writing it's just

more human more fluid it doesn't have

this chat GPT stink that so many people

point out and if for honest most people

are kind of allergic to it at this point

at least within the ey bubble that we're

in it might be a subjective thing but

most people do agree on this another

disadvantage of gpts is that they have a

limited context window in the knowledge

based but a few months ago they shipped

a massive upgrad to the knowledge based

field feure now look I don't dare to

publicly State an exact number of how

much context you can actually put in

there because it just varies in practice

while teaching GPT building in the I

Advantage Community I came up with this

rule of up to 15 pages always works so

whether that's one PDF with 15 pages or

it's 151 page PDFs up to that amount

you're always safe and it includes

everything if you venture beyond that

here and there it starts losing pieces

of the context and I wouldn't fully

trust it now can you upload 100 pages

and is it going to work yes is it going

to miss out on information here and

there also so yes this seems to be less

of an issue with Claud but again this is

a very subjective and intuitive thing

that I'm communicating here they have no

official data on exactly how many tokens

are considered within these documents

but let me just tell you from all the

collective experience that I've soaked

in so far clot projects can take in way

more context and it works more reliably

both of them work but if you have up to

15 pages both of them work flawlessly

and then the last disadvantage of GPT

says that you can always only have one

chat as you can see in a second here

projects are set up in a way where you

can have multiple chats as you work on

the project this will make a lot of

sense when we talk about use cases but

before we do that let's talk about one

more thing which is the advantages and

disadvantages of claw projects now these

are kind of the Opposites of the pluses

and minuses we just talked about here so

let me go through these briefly Cloud

projects allows you to have multiple

chats in one interface as you're working

on the project you can start new and new

chats and you can keep everything in one

place it's sort of a folder for chat

something that I've been asking for and

chat GPT ever since it came out it's one

of the obvious features that opening eye

has refused to release so far probably

because they're more oriented towards

agentic feature of letting the llm

figure it out and building assistance

that work for you rather than a llm that

works with you next up CLA is just way

better at code especially the Sonet 3.5

model this consensus just has been

established at this point across the

internet how did they do it there's many

theories out there they might have

trained the model on synthetic code or

there's some other black magic going on

in the background but in practice if

you're doing coding projects Sonet 3.5

is usually better with the exception of

longer outputs of GPT 40 so if if you

need to put out a script that is a

little longer GPT 4 all within chat GPT

has more tokens that it can output in

one shot that is the one advantage when

it comes to coding okay next up clot

projects also have better tone and style

as we pointed out again might be

subjective but most people do agree it

sounds more human and then we have the

longer context within the knowledge base

this you work on your own project and

that's it there's no prompt presets with

conversation starters you cannot access

external apis and do things across the

internet or your own apps with something

like actions and gpts there's no image

generation there's no browsing there's

no data analysis tool all right so those

are the features a few more important

notes for you once you're using these

tools so one really weird one and I wish

they changed this is if you use the

search function with an anthropics CLA

it doesn't look inside of the project it

only looks at the name and the

description so if you have a

conversation and something comes up in

there you cannot search for that as you

accumulate more and more projects more

and more chats it's really nice to be

able to look into the chat that's kind

of the whole point of the search

function just be aware with projects it

only looks at the names and descriptions

as of now please change that ofic maybe

we don't need the knowledge base I

understand how that can be a lot of

tokens but the chats should be

accessible secondly in both features you

can kind of pin the most important ones

in gpts it's called that it's called

pinning and inside of clot you can start

either projects or chats really

convenient I use it all the time you

should also be aware of the fact that

you have custom instructions for both of

these which are incredibly useful I've

been saying it in every prompting

related video on this channel how great

custom instructions are and how they

allow you to personalize your experience

for yourself I mean if you just look at

all the Apple announcements their whole

thing is hey we you we might not have

the best model but we have your personal

context and it's present within every

conversation and that's why we can

unlock all these incredible intuitive

and easy to use features for not

Millions but billions of consumers and

the whole thing is based upon your

personal context that's why I've been

preaching setting up custom instructions

with your personal context since around

March 2023 they're super important and

if you give it your personal context you

can actually turn a normal chat into a

personalized AI assistant and with gbts

you can share it with other people so

you can Empower your whole company

Department whatever it might be super

powerful stuff use custom instructions

okay last but before we get to use cases

that CLA actually doesn't offer a store

but it doesn't need it it's projects and

usually projects are going to be a

one-off thing once you're done

completing the project you kind of move

on whereas gpts are more like an

employee that you want to hire on a

recurring basis now you might not need

the employee for 8 hours a day but maybe

you need it for 30 minutes every single

week this is where gpts shine whereas

with projects once you're done you're

going to Archive them and probably not

return cuz the project is done so now

let's get to the part of when you should

be using projects and gpts in concrete

scenarios not just the features not just

things to be aware of and what scenarios

do I use them and What scenario do team

members community members use claw

projects well as the name suggests

everything that is Project based usually

you're better served with claw projects

as long as you don't need any of the

tooling inside of gpts and even more

concretely if you're writing something

clot projects is excellent because you

can give it examples of your writing

just like this you put in a few examples

of previous emails that you wrote you

save it as a PDF upload it to the cloud

projects knowledge base and then once

you prompt you can always always

reference that write in the style of

name of the document.pdf and it just

works super well with the improved tone

the extensive knowledge base where you

can upload a bunch of your writing too

you can just start writing all types of

things that you need to get knocked out

you need new email drafts or some

presentation whatever it might be as

long as it's Loosely related and you

want to keep the style consistent

projects are a fantastic way to do this

because with CLA models like Sonet 3.5

or Opus and between those two you'll

just have to test yourself they're very

similar for coding Sonet is but for

writing either son or Opus are fantastic

I think you're just going to be very

happy with the results and you can keep

the entire project within one chat very

useful but the next example is even

better and that is if you're creating a

coding related project if you're

creating a game or a website and you

have multiple code Snippets that you

don't all want to be housed in one page

well just upload the various python

files to projects and it will be aware

of your entire application and now if

you're prompting something new you're

doing it within the context of your

entire application and not just the one

code snippet or just the conversation

you had so far it's aware the entire

project huge now could you do this with

gpts 2 yes but again coding abilities

with mopic model are just better so

using coding projects for this is a

no-brainer now yes as I mentioned before

maybe you need the longer output of GPT

40 and you can generate some of the code

in there if you need a longer script but

then you can import it to Cloud projects

just add the python file to the

knowledge base and you take advantage of

the long context awareness of cloud to

complete your project although some of

the code might have come from cat GPT so

as you can see to get the most out of

these models today you need to be aware

of the multiple advantages and

disadvantages and ideally you mix and

match them and then also clot projects

are just generally speaking better for

anything where you're going to have five

or more chats for or more chats and

you're not exactly sure what they're

going to look like with gpts it's more

like a laid out track that you're going

to be following that's what really makes

sense within that interface but with

projects it's more exploratory it's more

like okay I'm starting this project

here's a bunch of context here's some of

my writing here's some python files that

I might have and now let me talk to you

and let me figure out what else we need

to add here whereas if you build a GP

you already know what the use case is

you already know what you're going to be

doing so that's clot projects and when

do you want to use gpts well a very

clear one is if you want to build a

solution for somebody else if you want

to share a AI application or a prompt

with a colleague there's no better ways

to do it today than with gpts you can

customize it to their context with the

customer instructions you can add useful

prompts to them in the conversation

studies you can even add an action and

this is the most common one that I

personally use that saves it to a

database so you bring it outside of chat

GPT without having to do anything just

simply add a keyboard shortcut that

engages the action and you can save it

to an ocean database and your

counterpart doesn't need to know

anything about prompt engineering API

calls or even how to use it because you

set it all up the instructions are there

The Prompt presets are there the action

is there they just go in and once

they're done they press one key and

everything that you need gets saved to a

database now look this is quite complex

and if you're interested in learning

this yes I do teach you this is one of

the learning paths within our AI

Advantage Community but again we give

the base presets out for free so if you

have enough knowledge and if you want to

just customize these and figure all of

this out by yourself you can absolutely

do that this channel is here to to

support you on that Journey too another

use case for gpts is everything that has

to do with assistants Tutors or coaches

it might be a base model it might be a

system prompt I'm not exactly sure but

when it comes to tutoring and actually

assisting you with your work gpds are

just so much better the entire ethos

behind GPD 40 is the model trying to get

your work done for you or with you it's

very conversational it's very practical

and when it comes to something like an

assistant or a tutor gpts are just the

perfect tooling for that and actually

with my free GPT Builder GPT one of the

best use cases is building little custom

tutors for whatever you might be

learning I have a separate video of that

and you can check out the free GPT that

builds gpts for you in the description

below and another reason to use gpts is

obviously the tooling data analysis

image generation and web browsing is

just something you don't get with

anthropics claw today I'm sure it'll

come over time but as of today if you

want these well got to use GPT for all

and then last but not least I would just

generalize and say gpts are just better

if you have a repetitive task that is

super specific and this is the reason

why the store didn't work so well

because the store tries to give you

generalized Solutions and the best gpts

are the ones that are custom to your

very specific context it's the reason

why I think that the Apple Integrations

will actually work really well for all

the users there because they have your

personal context and the gpts from the

store don't they're generic by

definition but everybody who integrates

AI into their workflows and actually

builds custom gpts finds that yeah of

course it is useful to have a

brainstorming body for every single

YouTube video that is aware of the last

10 uploads all the titles and thumbnails

have I've ever used and has a keyboard

shortcut menu of various brainstorming

techniques that I apply every single

time when I create new video ideas of

course that's useful but that's probably

not useful to you that's a GPT that I

build for myself and that I use all the

time but that's because it has all my

personal data and context and that's why

it works so well this is where GPT Shine

versus projects are exactly that there a

oneoff project where you might not be

sure where the journey leads yet and

once you're done with it going to

Archive it and that's the end of it all

right I hope this video was helpful to

you all the resources are in the

description below subscribe to the

newsletter for the free GPT assistant

that I mentioned and if you want to

learn even more about CLA and see some

of the examples that you could build

with it like turning PDFs into websites

or turning screens into animations or

just creating games from scratch check

out this video where I pointed out 21

use cases for claw 3.5 sonnets I'll see

you there