OpenAI's 'AGI Robot' Develops SHOCKING NEW ABILITIES | Sam Altman Gives Figure 01 Get a Brain

Summary

Figure AI, in partnership with OpenAI, presents a groundbreaking amalgamation of robotics and neural networks. The robot, Figure 01, demonstrates advanced capabilities such as full conversations, understanding and responding to visual cues, and executing complex tasks like picking up trash and handling objects. The robot operates through a combination of a large language model for reasoning and neural network policies for physical actions, showcasing a significant step towards general AI and practical applications in embodied AI.

Takeaways

• 🤖 Figure AI is a robotics company that has partnered with OpenAI to integrate robotics and AI expertise.
• 🔄 The collaboration aims to showcase the synergy of metal and neural networks, marking a significant advancement in the field.
• 🍎 Figure One, the robot, can engage in full conversations with people, demonstrating high-level visual and language intelligence.
• 🧠 The robot's actions are powered by neural networks, not pre-programmed scripts, allowing for adaptive and dexterous movements.
• 🎥 The video demonstrates the robot's ability to understand and execute tasks based on visual input and verbal commands.
• 🔄 The robot can multitask, such as picking up trash while responding to questions, showcasing its ability to handle complex tasks.
• 🤔 Figure AI's technology suggests the potential for general AI robots (AGI), with capabilities beyond scripted movements.
• 💻 The robot's neural networks are likely running on a model provided by OpenAI, possibly GPT-4 or a similar advanced model.
• 📈 The partnership between Figure AI and OpenAI highlights the potential for scaling up embodied AI technology.
• 🚀 The demonstration of the robot's capabilities, such as handling objects and understanding context, indicates significant progress in AI and robotics.
• 📌 The video serves as a clear example of the integration of AI and robotics, moving towards more autonomous and interactive machines.

Q & A

What is the significance of the partnership between Figure AI and OpenAI?

The partnership between Figure AI and OpenAI is significant because it combines Figure AI's expertise in building robotics with OpenAI's advanced AI and neural network capabilities. This collaboration aims to create robots that can understand and interact with their environment in a more sophisticated and autonomous manner.

How does Figure AI's robot utilize neural networks?

Figure AI's robot uses neural networks to perform a variety of tasks. These include low-level dexterous actions, such as picking up objects, as well as high-level visual and language intelligence to understand and respond to human commands and questions.

What does the term 'end-to-end neural networks' refer to in the context of the video?

In the context of the video, 'end-to-end neural networks' refers to the complete system of neural networks that handle all aspects of a task, from perception (seeing or understanding the environment) to action (physically manipulating objects), without the need for human intervention or pre-programming.

How does the robot determine which objects are useful for a given task?

The robot determines which objects are useful for a task by processing visual input from its cameras and understanding the context through a large multimodal model trained by OpenAI. This model uses common sense reasoning to decide which objects are appropriate for the task at hand.

What is the role of the 'speech to speech' component in the robot's operation?

The 'speech to speech' component allows the robot to engage in full conversations with humans. It processes spoken commands, understands the context, and generates appropriate verbal responses through text-to-speech technology.

How does the robot handle ambiguous or high-level requests?

The robot handles ambiguous or high-level requests by using its AI model to interpret the request in the context of its surroundings and the objects available. It then selects and executes the most appropriate behavior to fulfill the command, such as handing a person an apple when they express hunger.

What is the significance of the robot's ability to reflect on its memory?

The robot's ability to reflect on its memory allows it to understand and respond to questions about its past actions. This capability provides a richer interaction experience, as the robot can explain why it performed certain actions based on its memory of the situation.

How does the robot's whole body controller contribute to its stability and safety?

The whole body controller ensures that the robot maintains balance and stability while performing actions, such as picking up objects or moving around. It manages the robot's dynamics across all its 'degrees of freedom', which include leg movements, arm positions, and other body adjustments necessary for safe and effective task execution.

What is the role of the 'Vis motor Transformer policies' in the robot's learned behaviors?

The 'Vis motor Transformer policies' are neural network policies that map visual input directly to physical actions. They take onboard images at a high frequency and generate detailed instructions for the robot's movements, such as wrist poses and finger joint angles, enabling the robot to perform complex manipulations and react quickly to its environment.

What are some of the challenges that Figure AI and OpenAI aim to overcome with their partnership?

Figure AI and OpenAI aim to overcome challenges related to creating robots that can operate autonomously in complex, real-world environments. This includes developing AI that can understand and reason about its surroundings, learn from new experiences, and execute a wide range of physical tasks without human intervention.

Outlines

00:00

🤖 Introduction to Figure AI and OpenAI Partnership

The script introduces Figure AI, a robotics company that has partnered with OpenAI to combine their expertise in robotics with OpenAI's capabilities. The video showcases the first instance of the amalgamation of metal and neural networks, highlighting the significance of the collaboration. The robot, Figure One, is seen interacting with its environment, picking up trash, and engaging in conversation, demonstrating the integration of high-level visual and language intelligence with dextrous robotic actions.

05:02

🧠 Behind the Scenes: Neural Networks and Multitasking

This paragraph delves into the technical aspects of how Figure One operates, emphasizing the role of neural networks in its functions. It explains that the robot is not pre-programmed for specific motions or responses, but rather learns from a neural network. The video clarifies that everything shown is powered by neural networks, and the robot's actions are not scripted. It also compares Figure One's capabilities to Google DeepMind's RT2 robot, highlighting the advanced level of Figure One's learning from vision and language models.

10:02

🗣️ Conversational Abilities and Memory

The script discusses Figure One's ability to have full conversations with people, thanks to the partnership with OpenAI. It explains how the robot can describe its visual experience, plan future actions, and reflect on its memory, all verbally. The paragraph also touches on the technical aspects of how the robot processes conversation history and images to generate language responses and execute actions, highlighting the integration of large multimodal models trained by OpenAI.

15:03

🤹‍♂️ Advanced Robotics and Learning from Observation

This section of the script focuses on the advanced capabilities of Figure One, such as learning from observations and performing complex tasks like manipulating deformable objects. It explains how the robot's behaviors are learned and not teleoperated, and how it can multitask and respond to commands while carrying out actions. The script also discusses the robot's ability to understand and execute ambiguous requests, showcasing its advanced reasoning and manipulation skills.

20:04

🎉 Conclusion and Future Prospects

The script concludes with a reflection on the impressive advancements in robotics and AI, particularly the partnership between Figure AI and OpenAI. It acknowledges the skepticism around such technologies but emphasizes the significant progress made. The speaker expresses excitement about the future of embodied AI and the potential for Figure AI to scale up this technology. The script ends with a call to action for viewers interested in joining Figure AI's efforts in advancing robotics and AI.

Keywords

💡Figure AI

Figure AI is a robotics company that has partnered with OpenAI to integrate their expertise in building robotics with advanced AI capabilities. In the context of the video, this partnership has resulted in the creation of a robot that can engage in full conversations with people, understand visual inputs, and perform complex tasks. The collaboration is highlighted as a significant development in the field of robotics and AI.

💡OpenAI

OpenAI is an AI research lab that collaborates with Figure AI to enhance the robot's capabilities with high-level visual and language intelligence. OpenAI's models provide the robot with the ability to understand and process both images and text, enabling it to engage in conversations, reason, and perform tasks based on the inputs it receives.

💡Neural Networks

Neural networks are a series of algorithms modeled loosely after the human brain, designed to recognize patterns and interpret data. In the video, neural networks are used to deliver fast, low-level, dexterous robot actions, mapping pixels directly to physical movements. They are a crucial component of the robot's ability to learn and perform tasks autonomously.

💡Robotics

Robotics refers to the branch of technology that deals with the design, construction, operation, and use of robots. In the video, Figure AI is a company that specializes in robotics, combining their mechanical expertise with OpenAI's AI capabilities to create advanced humanoid robots capable of understanding and interacting with their environment.

💡Conversations

Conversations in the context of the video refer to the ability of the robot to engage in interactive, multi-turn dialogues with humans. This involves understanding language, processing inputs, and generating appropriate responses, which is facilitated by the integration of AI models from OpenAI.

💡Multitasking

Multitasking refers to the ability to perform multiple tasks simultaneously. In the context of the video, the robot demonstrates multitasking by engaging in conversation while also carrying out tasks such as picking up trash or handling objects.

💡AGI (Artificial General Intelligence)

AGI, or Artificial General Intelligence, refers to AI systems that possess the ability to understand, learn, and apply knowledge across a wide range of tasks, much like a human being. The video suggests that the robot's capabilities, such as learning from observations and performing complex tasks, are indicative of progress towards AGI.

💡Vision Language Model

A vision language model is a type of AI model that can process and understand both visual data (like images) and language data (like text). In the video, the robot uses a vision language model to interpret its surroundings and generate appropriate physical actions based on the combined understanding of visual and textual inputs.

💡Teleoperation

Teleoperation refers to the remote control of robots or other mechanical systems. In the context of the video, teleoperation is contrasted with the robot's autonomous capabilities, emphasizing that the robot's actions are not controlled by a human operator but are instead learned and executed independently.

💡Embodied AI

Embodied AI refers to AI systems that are integrated with a physical body, allowing them to interact with the world in a more human-like manner. In the video, the partnership between Figure AI and OpenAI has led to the development of embodied AI, where the robot's physical form is enhanced by AI capabilities, enabling it to perform tasks and engage in conversations.

💡Multimodal Model

A multimodal model is an AI model that can process and understand multiple types of inputs, such as images, text, and audio. In the video, the robot utilizes a large multimodal model trained by OpenAI to understand both visual and textual information, which enables it to engage in conversations and perform tasks based on the context.

Highlights

Figure AI is a robotics company that has partnered with OpenAI to combine their expertise in building robotics with AI.

The collaboration aims to showcase the amalgamation of metal and neural networks, marking a significant advancement in the field.

Figure One, a robot developed by Figure AI, is capable of having full conversations with people, demonstrating high-level visual and language intelligence.

The robot's actions are not scripted or pre-programmed, but rather determined by neural networks, allowing for independent and adaptive behavior.

The robot can describe its visual experience, plan future actions, reflect on its memory, and explain its reasoning verbally.

Figure One's capabilities are the result of a partnership with OpenAI, integrating their models to provide advanced visual and language processing.

The robot's behaviors are learned, not teleoperated, meaning it operates at normal speed without human mimicry or VR guidance.

Figure One learns from both web data and robotics data, watching videos and reading information to understand and apply knowledge.

The robot's system involves a large multimodal model trained by OpenAI that understands both images and text.

Figure One can process the entire history of a conversation, including past images, to come up with language responses.

The robot can decide which learned closed-loop behavior to run to fulfill a given command, loading neural network weights onto the GPU and executing a policy.

Figure One can multitask, explaining its actions in real-time as it performs them, such as picking up trash while responding to a question.

The robot's system involves a loop of observe, decide, act, allowing it to balance while performing tasks like picking up objects.

Figure One can reflect on memory with a pre-trained model analog in the conversation's image and text history, showing short-term memory capabilities.

The robot's low-level manual manipulation is driven by neural network vis motor transformer policies, mapping pixels directly to actions.

Figure One's whole body controller ensures safe, stable dynamics, allowing it to maintain balance during tasks like grasping and lifting.

The partnership between Figure AI and OpenAI is expected to significantly advance the field of embodied AI, with Figure AI being a prime location for scaling up this technology.

The demonstration of Figure One's capabilities has shifted perceptions of advanced robotics, with even critics reconsidering their past skepticism.

Transcripts

so figure AI is the robotics company

that partnered up with open AI to

combine their expertise in building

robotics with openi well Ai and this is

the first time we can behold the

amalgamation of metal and neural Nets

now I'm exaggerating but this is kind of

a big deal take a

look

hey figure one what do you see right

now I see a red apple on a plate in the

center of the table a drying rack with

cups and a plate and you standing nearby

with your hand on the table great can I

have something to

eat sure

thing great

can you explain why you did what you

just did while you pick up this

trash on it so I gave you the Apple

because it's the only uh edible item I

could provide you with from the

table great so based on the scene right

now where do you think the dishes in

front of you go

next

the dishes on the table like that plate

and cup are likely to go into the drying

rack next great can you put them

[Music]

there of

[Music]

course

[Music]

all right so how do you think you

did I I think I did pretty well the

apple found its new owner the trash is

gone and the table wear is right where

it

belongs I agree thanks figure

one you're welcome if there's anything

else you need help with just let me

know

[Applause]

[Music]

so they're saying with opening eye

figure one can now have full

conversations with with people open ey

models provide high level Visual and

language intelligence figure neural

networks deliver fast low-level dextrous

robot actions everything in this video

is a neural network this I think is as

clear as it gets previous videos I think

I maybe questioned like exactly what was

happening like I wish they kind of

spelled out I mean this is pretty pretty

clear in what they're saying here

everything here is a neural network mean

the robot isn't scripted it's not

pre-programmed for certain motions it's

not pre-programmed to answer in a

certain way that's you know Chad GPT

that's GPT 4 or higher maybe that's

answering the questions and then the

robot is moving based on the neural

networks that figure AI has it sounds

like already independently developed

just to make sure that the people that

are like asking questions kind of like

know so this is film speed 1.0 right

endtoend neural networks speech to

speech reasoning and this is the figure

01 the robot Plus open Ai and look I

think it's fair that people are

skeptical we had somebody you know roll

a truck off a hill and then be like this

thing really functions and you know it

did not but at this point it's pretty

obvious I feel like to most people that

kind of been following these

developments that okay they they really

have the real deal you know for example

if Google deep Minds rt2 robot you know

they have they kind of explain what's

running it they have this Vision

language action model so almost kind of

like you can think of it of as like a

large language model with vision with

this action model kind of on top of it

that translates with the vision language

models kind of reasoning and seeing

translates that into movements of the

hand and the grippers ETC so text goes

in here and again this doesn't have

anything to do with figure this is

Google deep mine but maybe figure has

something similar right so you have the

large language model here and all the

speech to speech right so here's what

the should do and the language model

like reasons through it you also have

like the um Vision input right that kind

of combines and the output is in terms

of the movements of the robots so kind

of it's movements in the physical space

and that's why you're able to say

somewhat weird things like you know move

banana right as you can see in this

image there's a couple flags on this

table and there's a banana and you get

the command move banana to Germany right

and it figures out you know kind of what

you mean so it puts it on top of the

flag on top of the correct flag right it

doesn't pick up the banana and head to

Frankfurt so it would be very curious to

know if they're doing something like

this now of course it's a small startup

they're not going to post all their

Insider secrets on the internet maybe

sometime in the future we'll find out

but it is getting pretty impressive like

when you tell it to pick up the trash

while responding to a question you know

you know you tell me to do that like

that's something that I might struggle

with myself multitasking hard so it

looks like this Google Deep Mind rt2

paper was published in uh July 2023 and

here's Cory Lynch so Cory Lynch works at

figure AI so he's describing how this

robot is able to do what it's doing so

Corey his background was robotics at

Google and looks like he joined figure

AI uh around July 2023 crazy so he's

saying we are now having full

conversations with figure 01 oh is this

him I wonder so that's Cor

that that might be him interacting with

the robot so he's saying we are not

having full conversations with figure

one thanks to our partnership with open

AI our robot can describe its visual

experience plan future actions reflect

on its memory explain its reasoning

verbally technical Deep dive thread so

he's saying let's break down what we see

in the video so all the behaviors are

learned not teleoperated so this is kind

of a sticking point with some of these

demonstrations we've seen some

incredible things done by robots for

fair like low price points but they're

done with tele operation so for example

you're seeing here he's a robot cooking

a three course uh Cantonese meal right

grilling up some delicious steaks or

chicken eggs vegetables cracking some

eggs like this is absolutely incredible

so this is Telly operated and what that

means is for example here's an example

of it so as you can see here there's a

person standing behind it and they're

kind of mimicking those gestures up in

the air and the robot kind of like

repeats them another way of doing it is

with virtual reality where you kind of

demonstrate those movements and the

robot kind of repeats it and the robots

can learn from this and can generalize

but that's quite different from

something like this this rt2 from Google

deep mins you can see here it's kind of

showing you is like sucking up all the

information right it's watching all

these videos and all the previous robots

and the Wikipedia and YouTube and

everything everything everything so as

they say here it learns from both web

and Robotics data so it just looks at

things and reads things and it knows

things right it it drinks and it knows

things so they're kind of specifying

here okay so it's not teleoperated and

it's running at normal speed so the

camera footage is not sped up and again

we all kind of appreciate that are

skeptical because they've been burnt

before so I I think it just helps to

have little disclaimers like this

somewhere because I mean for the people

that follow this stuff you know I think

to most people probably this is what

they think of like Peak Advanced

robotics right the dancing robots like

to somebody that's not really following

looks at this and goes okay this this is

probably the most advanced thing there

ever is look at the Motions but the

people that are following this stuff

they're like yeah cool but this thing

learning from watching videos how to

operate in the real world is much cooler

right it being able to generalize like

if you say I need to hammer a nail what

objects from this scene might be useful

it's like let's grab a rock and then

prints out the action of how to use that

rock to hammer whatever it needs to

hammer kind of using that Chain of

Thought reasoning which is something

that we know from interacting with large

language models like chpt like you you

know that chpt can probably figure out

the rock can do something like this

right and then it links to the execution

the code that manipulates that rock in

the physical world right so this idea of

vision language model you know it may

not be pretty but this is what Peak

Performance looks like and it seems like

figure is there it's you know there's

definitely competition for these General

r robots so I think people begin to kind

of refer to them off hand as like AGI

robots as in to point out that these are

General robots which you know as cool as

these are they probably wouldn't say

this about the Boston Dynamic robots as

impressive as the the movements are the

movements are prescripted they're

following a routine so he continues we

feed images from the robots cameras and

transcribed text from speech captured by

the onboard microphones to a large

multimodal model trained by open AI that

understands both images and texts so

it's interesting that they don't spell

which model so they don't say GPT 4 you

know with vision they're like a model

maybe Jimmy apples will clue Us in so I

can't find the Tweet but somewhere a

while back he was saying that's weird

somewhere he was saying that um there's

a robot heading to your favorite AI lab

and I feel like maybe it was uh related

to this and so we feed images from the

robot's cameras and transcribe text from

the speech captured by onboard

microphone so this is a little detail

that's interesting so open ey has their

open source whisper which is a You Know

audio to text transcription I believe

it's open source as part of their kind

of Suite of products so in a previous

video I kind of try to paint AGI as a

series of parts that you're trying to

combine together and this is kind of a

good representation of it right cuz

think about what we have here we have

figure this robotics company likely

running with opening eyes whisper a

large language model it's called a GPT 4

could be something else something

specific right something of vision that

can understand images and text and all

that is hooked into the robot so all the

pieces are working together to create

this robot with a general ability which

is kind of what we think of AGI as we

don't have a specific definition but you

know obviously this is moving in that

direction if it can like walk around and

learn and reason like if it can hear

commands and then respond to them like

that's like Are We There Are we almost

there at the very least close the model

processed the entire history of the

conversation including past images to

come up with language responses which

are spoken back to the human via text to

speech the same model is responsible for

deciding which learned closed loop

Behavior to run on the robot to fulfill

a given command loading particular

neural network weights uh onto the GPU

and executing a policy and so this last

part that to me reads as different from

what Google Deep Mind has with their

little like they kind of toonize those

movements so here's from Google Deep

Mind to control a robot it must be

trained to Output actions we address

this challenge by representing actions

as tokens in the model's output similar

to language tokens and describe actions

as strings that can be processed by

standard natural language tokenizers

shown here so if somebody super smart in

the comments can maybe unpack this a

little bit just put the word GPU

somewhere in the comment and I'll kind

of search by that but you know what does

this tell us so this is something

different from the rt2 and I'll do my

best to post an update if we get more

information but to me I'm reading this

as there's a maybe like a finite

pre-trained number of actions that it

has like pick up or or whatever I

don't know you know pour some liquid

into this thing or push a button and

then the GPT model the open AI model

kind of selects which specific thing to

run and then runs it I mean I don't know

if that's true I I might be misreading

it but we'll we'll know more soon

hopefully so speech to text this is

where the person says can I have

something to eat right that feeds into

the open AI model Common Sense reasoning

from images it responds sure thing then

it goes into Behavior selection so it

has sort of these preexisting seems like

neural network policies for fast

dextrous manipulation and so those lead

into the whole body controller of safe

stable Dynamics so that's whole body

movement from legs and arms and Etc so

balancing while it's you know picking

stuff up Etc and then at the same time

the vision the robot as it's seeing

things right so it's seeing what it's

doing that kind of feeds back into you

know the GPT open AI model and the

neural network policies which is kind of

I guess an UDA Loop Orient observe

decide act all right so here's the

command here's like the acknowledgement

sure and then it goes into this Loop to

complete the task but interestingly it

sounds like it it can multitask so it

can like tell you what it's doing as

it's doing it and so the continue

connecting figure1 to a large

pre-trained multimodal model gives us

some interesting new capabilities so

again that's the big Point here that we

have a company good at building metal

robots figure one we have a company

that's excellent at building AI neural

Nets open AI so one plus the other now

it's able to describe its surroundings

use common sense reasoning when making

decisions for example the ishes on the

table like that plate and cup are likely

to go into the drawing rack next

translate ambiguous highle request like

I'm hungry to some context appropriate

behavior like hand the person and Apple

so that was the big test with rt2 SL RTX

whatever you want to call you know the

RT series of models you could give it a

general request I think one of the

examples was they said I'm tired and

it's like okay you know we have a Red

Bull would you like a Red Bull which you

know shows that we make them in our

image don't we and then describe why it

executed a particular action in plain

English for example it was the only

edible item I could provide you with

from the table and a large pre-trained

model that understands conversation

history gives figure one a powerful

short-term memory consider the question

can you put them there where does them

refer to and where is there answering

correctly requires the ability to uh

reflect on memory with a pre-trained

model analog in the conversation's image

and text history figure one quickly

forms and carries out the plan place the

cup on the drawing rack place the plate

on the drawing rack so one and two steps

one and two so I'm rewinding this to see

so when GPT 4 Vision just came out there

was a report testing a lot of its

abilities and so one thing that they

found is it's really good at figuring

out what we're pointing at so if you're

watching on video like if I do this like

I'm pointing to something like you know

which word I'm pointing to right and so

the vision models also pick up on that

very well like if I have an arrow

pointing to something like you know what

I'm pointing to so do they like the the

models they understand it very well

instead of for example needing to show

it coordinates or having to Circle

something like or or anything like that

basically just an arrow or something

pointing at something works very very

well so I was curious if he had to if he

was pointing at all or it was just sort

of an in context so I'm not seeing any

sort of visual Clues other than the

verbal command but I'm going to make my

prediction now we as a society as humans

we will be pointing a lot more I'm just

guessing but like if you point at

something and you stay in action that

might be like the easiest way to give

the most amount of information about

what needs to be done so next they

continue finally let's talk about the

Learned low-level B manual manipulation

so all behaviors are driven by neural

network Vis motor Transformer policies

mapping pixels directly to actions these

networks taken onboard images at 10

Hertz and generate 24 doof actions so in

robotics this is directions of Freedom

so for example wrist poses and finger

joint angles at 200 htz these actions

serve as high rate set points for the

even higher rate whole body controller

to track this is a useful separation of

concerns internet pre-trained models do

common sense reasoning over images and

text to come up with a highlevel plan

learned VIs motor policies execute the

plan performing fast reactive behaviors

that are hard to specify manually like

manipulating a deformable bag in any

position so like if you're picking up a

bag of potato chips right it's not hard

it's not solid so it will deform as you

grab it right you're not going to be

able to grab it if you don't provide

enough pressure If you provide too much

pressure you'll pop it so those look

like trash bags of potato chips so it's

grabbing it and even though it's kind of

crumbling out of the weight the robot's

still able to grasp it and throw it in

the trash they continue meanwhile a

whole body controller ensures safe

stable Dynamics for example maintaining

balance even just a few years ago I

would have thought having a full

conversation with a humanoid robot while

it plans and carries out its own fully

learned behaviors would be something we

would have to wait decades to see

obviously a lot has changed in my mind

figure is the best place in the world

right now to scale up embodied Ai and so

they are recruiting recruiting hard so

you can go to figure. A/C careers yeah I

mean it's very exciting even more so

with the new partnership with openai

which they announced so looks like the

first time I think we've heard of it was

this was February 29th so they're saying

openai plus humanoid robots and you know

at the time they posted this you know

where the robot makes a cup of coffee

and you know I think it was well

received although there were some

criticism there was a lot about this

demonstration that is fairly simp like

the coffee maker that they've used is

often the specific model is used for

robotic demonstrations because it's made

to be very simple to use you don't need

multiple digits you can have just one

claw like appendage you basically need

one finger to operate it you know

assuming that the Cure cup is in there

basically you just need to push the

handle down push a button it's done and

I think I even at the time said oh maybe

you know just I wasn't sure how

impressive it was just kind of that

demonstration alone kind of out of

context but I mean now it's definitely

shaping up and getting a lot more

exciting also I find myself regretting

more and more every time that I've said

anything negative about robots in the

past now as it's getting better and it's

talking you know you start reconsidering

some of your past words like maybe I

should not be talking crap about this

thing so with that said I think figurei

has excellent robots amazing robots I

love the robots maybe now Boston

Dynamics will uh be motivated enough to

learn a new Tik Tock dance crap I got to

stop doing that Boston Dynamics is great

Boston Dynamics makes good robots

anyways my name is West rth thank you

for watching