Augusto Collerone retweeted
Exciting to see @cobuildersxyz go live with their Hardhat 3 plugin suite.
Developers can now compile, test and deploy Rust and Solidity smart contracts together in the Hardhat plugin suite with one single command.
Learn more below. 👇
Until now, building on @arbitrum Stylus meant having to leave your Hardhat workflow behind.
Not anymore.
We shipped a Hardhat 3 plugin suite that brings the full Stylus lifecycle into Hardhat. Rust contracts right next to Solidity.
🧵
Augusto Collerone retweeted
Until now, building on @arbitrum Stylus meant having to leave your Hardhat workflow behind.
Not anymore.
We shipped a Hardhat 3 plugin suite that brings the full Stylus lifecycle into Hardhat. Rust contracts right next to Solidity.
🧵
Augusto Collerone retweeted
We've been diving deep into @ethinteroplayer EIL (Ethereum Interop Layer), a trust-minimized cross-L2 protocol where users sign once and transact across multiple chains.
Our principal researcher @nachfq worked hands-on with the protocol.
To really understand it, we needed a local playground.
We couldn't find one, so we built it 👇
Augusto Collerone retweeted
Wow, they really don’t get it.
Mars is critical to the long-term survival of consciousness.
Also, I’m not going to ask any venture capitalists for money. I realize that it makes no sense as an investment. That’s why I’m gathering resources.
Neil Degrasse Tyson criticizes Elon's plan to go to Mars:
Maher: "Can Elon Musk realistically send humans to Mars?"
NDT: "I have strong views on that:
For him just say 'Let's go to Mars because it's the next thing to do.'
What does that venture capitalist meeting look like?:
Elon what do you want to do?
'Go to Mars'
How much will it cost?
'1 trillion dollars'
What's the return on investment?
'Nothing'
That's a 5 minute meeting."
Thank you guy who plays scientist on TV.
Augusto Collerone retweeted
🎉Tenemos GRANDES noticias🎉
Anunciamos el Scholarship Program: Latam 🤝@EFDevcon: Un programa de apoyo a builders para viajar desde Latam al sudeste asiático, asistir a Devcon, aprender, conectar, hackear y vivir una gran experiencia.
🧵👇
Augusto Collerone retweeted
Criteria:
¿Cómo aplicar?
1. Completa este form: seedorg.typeform.com/scholar…
2. Dale RT a esta publicación.
3. Síguenos en rrss: Twitter @SEEDLatam y únete a nuestra comunidad en Telegram @SEED_Latam (donde compartiremos más info sobre el Scolarship).
4. Mantente atento a las próximas noticias :)
Inscribite! Nos vemos en @EFDevcon🦄
Impresionante! Ya tengo un side project para el fin de semana.
Introducing the 01 Developer Preview.
Order or build your own today: openinterpreter.com/01
The 01 Light is a portable voice interface that controls your home computer. It can see your screen, use your apps, and learn new skills.
This is only the beginning for 01— the open-source foundation for this new era of AI devices.
Augusto Collerone retweeted
Imagine in a few years when these scenes are as common as a #SpaceX Falcon 9 launch. I don't think most people really understand what is happening here.
Augusto Collerone retweeted
GPT-3.5 out-of-the-box pricing:
• Input: $0.50 / 1M tokens
• Output: $1.50 / 1M tokens
Fine-tune the same model, and everything changes:
• Input: $3 / 1M tokens
• Output: $6 / 1M tokens
• Training: $8 / 1M tokens
99% of use cases need RAG, not fine-tuning.
Augusto Collerone retweeted
Reading a tweet is a bit like downloading an (attacker-controlled) executable that you instantly run on your brain. Each one elicits emotions, suggests knowledge, nudges world-view.
In the future it might feel surprising that we allowed direct, untrusted information to brain.
Augusto Collerone retweeted
This workflow is really fun! 🤩 Create any 3D object you can imagine in Apple Vision Pro, FAST!
Midjourney (or other image gen) -> TripoSR (modded) - Free USDZ Converter
More info in the thread ⬇️🥽🤯
Augusto Collerone retweeted
Shanghai 🇨🇳 AI Lab Achieved 1st Version of Karpathy's AI Operating System
> Nov 2023: @karpathy proposes LLM OS
> Feb 2024: Chinese (+ Princeton) team proposes self learning operating system
What did they do?
> Built an agent using a mix of Python code and GPT-4 language model prompts called Friday; that
> controls a Linux or Mac OS computer,
> including browser, Excel, and PowerPoint, to perform tasks; and
> self-improves;
> uses GPT-4 as underlying LLM
Components:
> Planner - decompose user requests into smaller tasks
> Configurator - middleware to take each task and configure it with data from memory or how-tos from tool repositor before passing to Executor
> Declarative memory - user profile and history of previous actions
> Tool repository - tools available
> Working memory - where the next steps for tasks and previous history are kept
> Executor - generates executable command
> Critic - assessing whether a task has been completed successfully or whether iteration is needed
Findings:
> writes code to achieve tasks
> outperformed GPT-4 on benchmarks for web retrieval, Excel and Powerpoint usage
I would be scared if I were a primarily a UI provider like Apple, Android, Windows, Salesforce etc.
These agents are universal UIs
Claramente este es el camino de los LLMs. Para mantener la data privada, necesitamos correr modelos en un device o red privada.
Podríamos usar un NAS como repositorio central de información, con una interfaz para consultas a un LLM, garantizando la privacidad de los datos.
🚨 BREAKING: Nvidia just released Chat with RTX, an AI chatbot that runs locally on your PC.
It can summarize or search documents across your PC's files and even YouTube videos and playlists.
The chatbot runs locally, meaning results are fast, you can use it without the internet, and the user's data stays private.
New day, new chatbot. Let's go.
Augusto Collerone retweeted
StackOverflow is a dinosaur that's going extinct.
I mostly use Copilot, ChatGPT, and Perplexity. I haven't found a single reason to visit StackOverflow anymore.
StackOverflow can't compete, and I don't see how they can stay relevant any longer.
I use Copilot for inline suggestions. As I type, Copilot takes care of the little things. It saves me from dozens of searches every day.
ChatGPT is the workhorse. I use it to solve more complex tasks with my code. Here are some examples:
• Explain what this code does
• Simplify it
• Rewrite it in a more efficient way
• Rewrite it in a more readable way
• Replace the use of a library with another
• Write documentation for it
• Describe potential edge cases
• Write unit tests for those edge cases
I use Perplexity to ask questions. Google is broken. If you don't believe me, try Perplexity for a day.
(Google is still king as a navigation tool. I never type a complete URL in my browser. I google it instead.)
Modern AI-powered tools are replacing boomer tech.
StackOverflow is dead to me.