conard.py retweeted
AI shouldn’t feel like a chatbot.
It should feel like a sense you didn’t know you had.
conard.py retweeted
Soon AI agents will be everywhere, built into operating systems, completing complex tasks from any device with an internet connection.
conard.py retweeted
A silent operator for your digital life.
This is what ambient intelligence looks like.
Sentient.
conard.py retweeted
You’ve walked through this city a thousand times.
But never seen what it’s made of.
Sentient connects the unseen.
conard.py retweeted
Since this is a 30B model it should be possible to run it on a 64GB or maybe even a 32GB Mac via MLX
🦥 Qwen3-Coder-Flash: Qwen3-Coder-30B-A3B-Instruct
💚 Just lightning-fast, accurate code generation.
✅ Native 256K context (supports up to 1M tokens with YaRN)
✅ Optimized for platforms like Qwen Code, Cline, Roo Code, Kilo Code, etc.
✅ Seamless function calling & agent workflows
💬 Chat: chat.qwen.ai
🤗 Hugging Face: hf.co/Qwen/Qwen3-Coder-30B-A…
🤖 ModelScope: modelscope.cn/models/Qwen/Qw…
🔧 Qwen Code: github.com/QwenLM/qwen-code
conard.py retweeted
Qwen3-Coder-480B-A35B @Alibaba_Qwen vibe coding with @PerplexityComet in anycoder
conard.py retweeted
BOOM! Latest Qwen 30B A3B 2507 running blazingly fast on Mac powered by MLX 💥
mlx_lm.chat --model "lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-4bit"
That's it, try it out today!
conard.py retweeted
That wraps the Reanimated 4 live stream @swmansion! 🎉
We've implemented 5 different animations using:
- CSS Animations
- CSS Transitions
- Layout Animations
from React Native Reanimated 4 🐎
Here's the souce code as promised 👇
conard.py retweeted
Gemini CLI Plan driven development! Use the new (/) commands in Gemini CLI for dedicated planning/implementation mode! Commands allow you to define custom templates with instructions for Gemini to follow. I added a plan and implementation mode. 🚀
Plan Mode: Analyzes a feature request and the existing codebase to generate a detailed, step-by-step implementation plan in a markdown file without writing any functional code.
Implementation Mode: Executes a pre-existing plan precisely as written, step-by-step, updating the plan file to track progress and stopping to ask for approval if any changes are needed.
See thread for prompts, installation instructions. 🔽
conard.py retweeted
Introducing `AutoRL` 📈
The world's simplest way to train a task-specific LLM with RL.
*Just write a SENTENCE describing the model you want.*
A chain of AI systems will generate data + rubrics and train a model for you.
Powered by ART, it's open source.
Link in thread:
conard.py retweeted
This false nomenclature of “researcher” and “engineer”, which is a thinly-masked way of describing a two-tier engineering system, is being deleted from @xAI today.
There are only engineers.
Researcher is a relic term from academia.
we at @xai are looking for researchers and engineers for scaling up our rl environments with user feedback and preference in the loop. apply here (or drop me a dm):
teapawt.org/i/jobs/194855650020684…
