Through OCI, @Tabnine leverages Command R to help power its AI code assistant that can generate, explain, and maintain code to accelerate and simplify software development.
CODE
-
OpenDevin Generates Custom Math Problems for Children’s Learning
By
–
On Father’s Day last weekend, I sat with my daughter to help her practice solving arithmetic problems. To give her practice problems, I used OpenDevin, an open-source agentic coding framework, to write a Python script that generated questions that she enjoyed answering at her own
-
Mastering Differential Privacy: Pure vs Approximate Methods
By
–
I had a dream last night where someone was asking whether pure or approximate differential privacy was better for situations with gross outliers and I (correctly) told them both would work. Now I can honestly say: I can answer that question in my sleep.
-
AI Powers Coding and Web Design: Screenshot to Code Testing
By
–
We're using it non-stop today on coding–mostly for web design, but here's a fun game test from screenshot to code
— Allie K. Miller (@alliekmiller) 20 juin 2024
↓https://t.co/ff303WECu6We're using it non-stop today on coding–mostly for web design, but here's a fun game test from screenshot to code ↓
-
Claude 3.5 Sonnet outperforms GPT-4o with new Artifacts feature
By
–
Coding with Claude 3.5 Sonnet is 10x more efficient than GPT-4o or any other LLMs out there.
— Shubham Saboo (@Saboo_Shubham_) 20 juin 2024
Plus, the new Artifacts feature can generate and run code next to your chat providing an amazing user experience. pic.twitter.com/eRfPkBUvraCoding with Claude 3.5 Sonnet is 10x more efficient than GPT-4o or any other LLMs out there. Plus, the new Artifacts feature can generate and run code next to your chat providing an amazing user experience.
-
AI Fixes Code Error in Seconds, Developer Improves Game
By
–
The code had an error. I told it to fix it. It did it in seconds.
— Allie K. Miller (@alliekmiller) 20 juin 2024
Related: I need to up my mancala game. pic.twitter.com/O4FVqdljHPThe code had an error. I told it to fix it. It did it in seconds. Related: I need to up my mancala game.
-
Claude 3.5 Sonnet Builds Functional Mancala Web App in 25 Seconds
By
–
This is wild.
— Allie K. Miller (@alliekmiller) 20 juin 2024
In just 25 seconds, Claude 3.5 Sonnet coded a fully functional Mancala web app for me 🕹️
I only provided ONE screenshot of the game's instructions.
It did the rest:
– Coded the entire game
– Previewed it so I could test
– Provided rules of play pic.twitter.com/WLweZUGt5CThis is wild. In just 25 seconds, Claude 3.5 Sonnet coded a fully functional Mancala web app for me I only provided ONE screenshot of the game's instructions. It did the rest:
– Coded the entire game
– Previewed it so I could test
– Provided rules of play -
Claude can program a playable snake game
By
–
It can program a snake game that you can play directly within Claude.
-
Function Calling and Data Extraction Techniques for LLMs
By
–
Function calling is a powerful way to extend the capabilities of LLMs and AI agents by letting them use external tools. Our new short course Function calling and Data Extraction with LLMs, created with @NexusflowX and taught by @JiantaoJ and @VenkatKSrini, demonstrates how to… pic.twitter.com/VkXYqDPZcu
— Andrew Ng (@AndrewYNg) 20 juin 2024Function calling is a powerful way to extend the capabilities of LLMs and AI agents by letting them use external tools. Our new short course Function calling and Data Extraction with LLMs, created with @NexusflowX and taught by @JiantaoJ and @VenkatKSrini
, demonstrates how to -
Anthropic Sonnet 3.5 Shows 68% Improvement in Agentic Coding
By
–
Las pruebas internas realizadas por Anthropic muestran una mejora notable en tareas de "Agentic Coding". Es decir, tareas de programación que requieren ver un repositorio de código, hacer mejoras, arreglar fallos… Donde Opus resolvía el 38% Sonnet 3.5 ahora resuelve el 64%