emc85

CS, Python, Programmer, Unity, Builder.

[Santiago @svpino]

GitHub Copilot Workspace is *by far* the best AI tool for helping developers write code.

(GitHub Copilot Workspace *IS NOT* the same as GitHub Copilot)

I've tried Devin and a few others. Nothing comes close.

I'm not sure if everyone has access to it, but oh god, this is good!

[Sebastian Raschka @rasbt]

I don’t post video tutorials (that) often, but hey, I just saw that I got 30k subs on YouTube!
If you’re looking to learn something new this weekend, I recently made video on how LLMs work, breaking down the development stages step by step: https://t.co/F60fXrOO9y

[Lupita Code @lupitacode]

Si recién empiezas en programación, Python Tutor es un sitio que permite visualizar paso a paso como se ejecuta tu código en diversos lenguajes como Python, Java, C, C++, y JavaScript.

Lo único que tienes que hacer es ingresar tu código en el editor y ejecutarlo.

[Linus ✦ Ekenstam @LinusEkenstam]

Would you dare this?

Robots will be everywhere and this might look simple, but imagine when this becomes high tech and 100x better

Some industrialists understands that robots are the next big thing.

Links in next tweet

[Jim Fan @DrJimFan]

The famed Stanford Smallville is officially open-source!

25 AI agents inhabit a digital Westworld, unaware that they are living in a simulation. They go to work, gossip, organize socials, make new friends, and even fall in love. Each has unique personality and backstory.

Smallville is among the most inspiring AI agent experiments in 2023. We often talk about a single LLM's emergent abilities, but multi-agent emergence could be way more complex and fascinating at scale. A population of AI can play out the evolution of an entire civilization.

Endless new possibilities ahead. Gaming will be the first to feel the impact.

Github: https://t.co/xUll7KaaTp
Paper: https://t.co/PMDQysrOz9
Authors: @joon_s_pk @joseph_c_obrien @carriejcai @merrierm @percyliang @msbernst

[Nick Sharp @nmwsharp]

Many physical systems are high-dimensional, but we only really care about some low-dimensional subspace.

Our latest work shows how to fit these subspaces as small neural maps automatically, *without* any data as input, just the energy function.

Read on to learn how! (1/N) 🧵

[Santiago @svpino]

StackOverflow is fighting back!

Here is everything you need to know about the release of OverflowAI, their new generative AI initiative.

StackOverflow traffic has been declining for several years, but after the release of ChatGPT, things took a turn for the worse:

Posting activity on the site fell the equivalent of five years in just six months! People stopped visiting the site and asking questions. Many thought this was a slow and painful death, and there was no coming back.

Today, their CEO announced OverflowAI.

If you can't beat them, join them, right?

But what's OverflowAI, and is this enough for StackOverflow to become relevant again?

Before I get into it, I want to thank Insta360 and their AI-powered smartphone stabilizer, Flow, for sponsoring this post. Flow is a gimbal with everything you need built-in, including a tripod and a selfie stick. Flow offers smart features like Deep Track, which remembers your subject even if they're obstructed or out of frame, or Insta360's automatic AI editing for reels made in seconds. It's also got an all-day battery life and can even charge your phone. To support my content, check Insta360's Flow here: https://t.co/0UkYt9euHx.

Here is StackOverflow's statement from seven months ago:

"All use of generative AI (e.g., ChatGPT and other LLMs) is banned when posting content on Stack Overflow. This includes asking the question to an AI generator then copy-pasting its output as well as using an AI generator to reword your answers."

OverflowAI is not a tool but a group of different generative-AI initiatives. StackOverflow went from banning AI to embracing it in over six months.

Some of the features they announced will be open to everyone:

First, they will replace their search functionality with one powered by generative AI. You can ask a question, and the site will search and summarize existing answers for you.

To power this feature, they use a vector database and embeddings of their 58 million questions and answers. It's a smart move, and it should improve the quality of the solutions we get.

Answers will cite sources, so authors get the credit, and users can always trace back the results.

Second, the assistant will help you ask a question if you don't find an answer. This should help people keep a consistent format and include as much relevant information as necessary.

The third interesting feature is a Visual Studio plugin to ask questions from your IDE. You can select a snippet of code, fire the plugin, ask a question, and get an answer without opening a browser.

I'm having difficulty seeing how a plugin that answers questions will fit next to Copilot. Will they complement each other?

I'm glad StackOverflow is fighting back. They promised the new search functionality by August.

But is this enough to keep them alive?

Do you think they have a fighting chance against ChatGPT and Copilot?

[CJ Zafir @cjzafir]

Do you want to master ChatGPT prompting?

This tweet is for you.

I spent 566+ hours in last 6 months experimenting with prompts.

Here's the most effective prompting framework.

It's called the RTF framework.

R → Role
T → Task
F → Format

Let's break it down:

1. Role (R): This is the "job" or "character" you want the AI to play.

It could be anything, from a scientist to a chef, or a writer.

By defining the role, you're telling the AI how to think or what perspective to take when answering your question.

For example, if you ask the AI to "Act as a Chef", it will think and respond as a chef.

2. Task (T): This is the action you want the AI to perform.

It could be to research something, to create a story, to plan a schedule, and so on. This is basically what you want the AI to do.

For example, if you tell the AI to "Cook a recipe", it will provide you with steps to cook a dish.

3. Format (F): This is how you want the AI's response to be presented.

It could be in the form of a list, a table, a story, a diagram, etc. This helps you get the information in a way that's most useful to you.

For example, if you specify "Show in a list", the AI will present its response as a list.

***For this step you need to be using ChatGPT plugins so it can give you a response in a PDF, image, or code format.

Now, if you combine these three elements, you could say something like, "Act as a Chef, Cook a recipe, Show in a list."

The AI will then provide you with a list of steps to cook a dish, just like a real chef would!

Here're some more examples:

• "Act as a Veterinarian, Research different types of dog breeds, Show in a Presentation"

• "Act as an Accountant, Schedule a monthly budget, Show in a Spreadsheet"

• "Act as a Developer, Organize a Python project, Show in a Visual Studio"

And so on. The possibilities are endless!

Bottomline: The key is to mix and match different roles, tasks, and formats to come up with prompts that suit your needs.

This way, you can get the most out of your interaction with the AI.

I've also attached the cheatsheet that you can use with the RTF framework.

Thank me later.

---

That's a wrap!

If you enjoyed this tweet:

1. Follow me @cj_zZZz for more AI breakdowns

2. Join the newsletter 'The AI Startup' for money-making AI ideas.

3. Retweet this tweet to share this thread with your audience

Cheers

[Abhishek @HeyAbhishek]

Google is offering free online AI courses.

No more Fees or Payments.

Here are 10 FREE courses on AI you don't want to miss [ Thread ]:

[Ronit Ghose @ronitA380]

How AI is shaping the future job market and why this time is different?

20k views and rising 🚀🚀🚀

💻 Youtube 👉 https://t.co/skke8rSfr6
🔊 Spotify👉 https://t.co/9YSRVB4OyX
🎧 Apple Podcasts 👉 https://t.co/ugNNDvRvQm

#FintechandWeb3FoundersSeries #fintech #AI #PZF2023

[Itamar Golan 🤓 @ItakGol]

This is insane! 😱

You can now train a 100-billion parameters LLM on Google Colab.

Explanation and code below ⤵️⤵️⤵️

--- TL;DR ---
Distributed training over the Internet has become operational with the release of the new version of the PETALS distributed training package. Join forces with people from around the world and receive immense computing power in return for your use! 🌐⚡️

--- Intro ---
Distributed training over the internet has turned from a dream into a reality with the release of the new version of the Petals distributed training package. Upon connection, the package grants you access to immense computing power that allows you to do anything you can imagine. It doesn't even have to be your own computing power: Attaching below is a Colab notebook that trains a 65-billion-parameter model (and also supports 100 billion. Yes, models with a hundred billion parameters are accessible to you). 💻🚀

--- It surely takes years, doesn't it? ---
No. For example, with a 65-billion-parameter inference, you'll get a speed of 5 tokens per second. ⏱️⚡️

--- How does it work? ---
The concept is very simple. In LoRA-based training (My tweet about LoRA - https://t.co/AvSZlOot7r), the base model is the same for everyone and does not change until the end of training, so many people need it at the same time. With Petals, people load small parts of the model, and each executes their part in the computation of running the full model.
All the headache and complex software engineering required to make this madness run smoothly and quickly happens inside the package. 🤯🔧

--- How complex? ---
From your own perspective, simply run:
AutoDistributedModel.from_pretrained

--- Important! Privacy! ---
Obviously, this infrastructure sends your data outside to the world, so it's crucial to take that into account. Your code is never sent outside. 🌐🔒

--- Links ---
1. Article: Petals: Collaborative Inference and Fine-tuning of Large Models - https://t.co/kUfpyQoaDI
2. See the speed for yourself: Distributed Chatbot - https://t.co/O591uH5MiT
3. Notebook for training a 65-billion-parameter model: https://t.co/v2u6heE7h1
4. Code: https://t.co/aM9gjmqx76
5. Paper: https://t.co/mdJk1Bv1fb
6. Join the community: https://t.co/WwrtxnNldp

[swyx @swyx]

🆕 Essay: The Rise of the AI Engineer

https://t.co/J91uijDMBB

Keeping up on AI is becoming a full time job.

Let's get together and define it.

[Paul Couvert @itsPaulAi]

This new ChatGPT feature creates graphics.

Excel is really becoming less and less useful with AI.

Here's how to create static and animated graphics in a single prompt:

[Muzzammil @DevMuzzammil]

BREAKING 🚨: ChatGPT's most powerful feature has just been released 🤯

Create GIFs, videos, business strategies, charts, & websites with simple prompts.

16 Code Interpreter features that will blow your mind:

[FinTech Weekly @fintech_weekly]

A new episode of @FintechInsiders to discuss recent #FintechNews. Among the most discussed topics, the #AI talent war involving #banks – that are including a significant percentage of AI roles in their #job ads 👇
https://t.co/Pysi60lwXX
#FutureofWork

[microscopic images. @microscopicture]

most detailed image of a human cell to date

[Steve (Builder.io) @Steve8708]

CSS has a variety of layout algorithms to choose from

It is useful to understand the differences, as some CSS properties behave differently in each layout mode

[Asyraf Hussin @asyrafhussin4]

Draw Chicken using CSS

@CodePen : https://t.co/703CWshkRq

[Enzo Cavalie @enzocavalie]

Recomendación para la gente en emprendimiento y tecnología.

Medellín 🇨🇴 es uno de los secretos mejor guardados de Latinoamérica:

✅ Costo de vida razonable
✅ Gente emprendedora y pujante
✅ Mucho talento entrando a tech

Y lo mejor:

⭐ La capital del reggaeton

[Revista Semana @RevistaSemana]

🚨 Atención: Reserva rodea al general Eduardo Zapateiro y se va contra candidato Gustavo Petro.
https://t.co/1AdvRvbLJx