Когда пчелиная война 2?

11:12 its so cute how Gpt ran away 😭

Machines built in the likeness of man, it’s the beginning of the end for us all

A minecraft 3D Printer

A cool update: a bot that uses the /place command to speed up the process

why was the guy rapping in the beginning

I think we should train AI off the builds already built by players, like picture generation AI is trained

4:08 In Llama's defence, I can see how those could be described as one-block columns spaced 'one block apart' as requested at 2:48, it's just included the column itself in the measurement of 'spaced'.

Can you use baritone?

Awesome video, thanks. Can you please make a video on approximately all the different function approximators used by a real LLM like chat-gpt or mixtral-7B ? Like what different lists of function approximators they use for different tasks and how do they switch between different approximators depending upon the different types of inputs (which again need to be processed before this decision).

This is so cute, I love their little responses.

9:31 LLama be like : Well i just copy his homework it's gonna be fine.

Can you tell it to spam the crouch button if it sees you clicking the crouch button quickly?

So you know Build the Earth? Would be insane to build Cities with ai

Love this series

So cool! A while ago I had a thought of a Minecraft mod, which would add Beavers as a mob that were capable of navigating the world, collecting wood, and building wooden structures all on their own. I find it very exciting that such a thing might soon be possible.

Vision support would be sick gpt4o and a future llama model would be able to use it but idk about others

This is incredible! Love that you shared the source code!

Imagine how good GPT-4o turbo, Google Gemini 1.5 Flash pro, or Claude 3 Opus could now make a version of Boi morphs in something like Unity game engine

God, Im so excited for more of these videos. Im interesting how far will this go and it also spiked my interest in playing with llms, still lack the skills to do it but ill get there Keep it up, love it!

GPT always kills it in these kinda of challenges, good effort by claude though, you can see a lot of potential there. I think we can just accept that Gemini has to be some kind of money laundering exercise at this point

Could you have it use leaves as scaffolding? They would decay and remove themselves after a while

Gpt is way smarter. Has do bro do it

Atleast you gave gemni a job

Claude moving its head around crazily reminds me of the original steve mob ai

I know language just does what it does and marketing hype is real, but I really wish we'd stick to the smaller umbrella term of Machine Learning for Large Language Models, which are artificial neural networks, instead of the massive umbrella term of AI which contains way more than just Machine Learning. This pile of linear algebra is neat, but it feels like the average person is getting kind of a wonky picture from overbroad use of terms.

@Emergent Garden Recommendation from me: Your prompts have no leverage, what I mean is that the LLM does not handle complex building tasks well because its limited by the single shot answer it needs to generate. Your template for "NewAction" is a great idea, my idea to improve its leverage is to add another template "NewActionPlan" Which it then fills with a list of generated prompts that will then be fed back into itself one after another (kind of like writing a todo list before getting started) My vision for it was kind of like this: -You whisper"Build a bridge for me" -<LLM> "Okay lets plan this out" *used newActionPlan* -<LLM> Okay lets see whats first on the todo list... *used actionPlan[0]* <LLM> Sure I will build the supporting pillars *used newAction* ...etc Getting a shared reference point for superimposed building actions is of course something to consider. Using plans recursively might also be interesting, like making a plan for planning multiple plans for even more abstracted tasks. Some way of sensing the world is possible, maybe you can let it take screenshots of the game and feed the image into some of the multi modal image recognition capable models

give them baritone litematica and a schematic library to choose from

gemini is the smartest

you know we are doomed when gpt doesn`t know how to do an or gate but loves tnt

I knew they used slaves to build the pyramids

ai sucks

There’s so much potential for AI in gaming. Imagine the MineColonies mod but each NPC is actually intelligent and responds to what you do and build.

22:35 its missing the last output slot for when the image fed is not a number

Gemini: What is my purpose? Emergent Garden: You collect cactus Gemini: Oh My God...

gorgeous video

What llama model are you using ?

Be meaner to Gemini. Also give him more tasks. It's funny to see him fail

This is new

7:31 i thought there was a bug on the top right of my screen 🤦‍♂️

we got robots playing minecraft in creative mode before gta 6

Chatgpt really said "I am death, destroyer of worlds"

This is my favorite thing to follow. Please make more.

Very retro for me. I designed the first commercial neural network to recognize hand written numbers 35 years ago.

Hey! I was wondering if you could maybe create a tutorial on how to set this up for ourselves?

This would amazing, for those doesn't have friend.

8:33 birthday cake

You should add limitations to the builds like: "make a pyramid using the least amount of resources as you can" Could be interesting

video:i'm not a math guy just like me fr fr

What were you doing with that netherrite axe in your hotbat 🤔