Senior Software Engineer π¨βπ§. Pythonista π. Open Source Contributor π§βπ».
Rio Negro, Colombia
Joined December 2010
- Tweets3.8K
- Following280
- Followers186
- Likes10.2K
Danilo Britto π΅πͺπ¨π΄ retweeted
I know I've been prompting my agents correctly when they present interfaces at the grammar, noun, and verb level. Took a lot of skill crafting to get here but god it's refreshing to work at the correct abstraction level and not like "my brother in christ why is this a modal?"
Danilo Britto π΅πͺπ¨π΄ retweeted
hey, I just joined Anthropic
I've been lucky to help a bit on Claude Duet, with such talented people. It's a proactive agent... it comes to you with what needs you and checks before it acts
still lots to do, but we think you'll like it... join waitlist
claude.com/product/claude-duβ¦
Danilo Britto π΅πͺπ¨π΄ retweeted
π Meet Qwen-Image-2.1-Turbo β create and edit images in just 8 denoising steps! Open weights now available!
Built on Qwen-Image-2.1, Turbo is an accelerated checkpoint on the same 7B visual generation architecture.
Fewer steps does not mean lower quality: it still generates strong 2K images from text, and supports continued creation through natural-language edits, from adding accessories to changing a scene.
Start directly with Diffusers: load QwenImage21Pipeline and the checkpointβs recommended 8-step sampling schedule is ready to go.
π Prefer an API? Qwen-Image-2.1 Pro and Turbo APIs are now officially live. Choose a hosted API for your application, or use the Turbo weights in your own workflow.
π€ ModelScope:
modelscope.cn/models/Qwen/Qwβ¦
π€ Hugging Face:
huggingface.co/Qwen/Qwen-Imaβ¦
π Pro API:
modelstudio.console.alibabacβ¦
π Turbo API:
modelstudio.console.alibabacβ¦
What will you create with 8 steps? Share your results with us!
Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! π¨
A unified model for both generation and editing, delivering top-tier quality in a lightweight package.
Highlights: π
- Compact & exceptionally fast: A lightweight 7B architecture that outperforms most closed-source models, with drastically accelerated inference for multi-image inputs.
- Native transparency: Natively generates and edits RGBA layers, enabling seamless compositing and text editing within transparent images.
- Versatile, high-fidelity editing: Supports up to 10 reference images and precise local control while preserving strict fidelity for portraits and products.
- Broad coverage & stunning aesthetics: Excels at panoramas, infographics, and virtual try-ons, delivering realistic textures and elegant typography.
Start to create your next masterpiece with Qwen-Image-2.1! πΌοΈ
- Blog: qwen.ai/blog?id=qwen-image-2β¦
- GitHub: github.com/QwenLM/Qwen-Imageβ¦
- Model Scope: modelscope.cn/models/Qwen/Qwβ¦
- Hugging Face: huggingface.co/Qwen/Qwen-Imaβ¦
Danilo Britto π΅πͺπ¨π΄ retweeted
Python 3.15 is out now.
Here's our overview of what's new, including lazy imports, a new statistical sampling profiler (Tachyon), sentinel types and more.
astral.sh/blog/python-3.15
Danilo Britto π΅πͺπ¨π΄ retweeted
hyperfine 2.0 is out now! It includes support for alternative performance metrics like peak memory usage, CPU cycles, and more.
Danilo Britto π΅πͺπ¨π΄ retweeted
We just released Polars 2.0.
It removed many of our legacy decisions makes the streaming engine our default and promotes SQL to a first class citizen within Polars.
It comes with initial out-of-core (spill to disk) support, a new Map data type and a lot of performance improvements. In fact, we think Polars is now one of the fastest analytical SQL engines on a single node. See benchmarks in the post: pola.rs/posts/release-polarsβ¦
Danilo Britto π΅πͺπ¨π΄ retweeted
here's how i shipped 2,500 PRs last month to production
this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly
Danilo Britto π΅πͺπ¨π΄ retweeted
Try these in your first Opus 5.5 session:
β Hand over a whole task. Define "done" and when to check in.
β Drop "think carefully". It always thinks first.
β After a long run, check what it needs to go further.
Our playbook: claude.dev/blog/getting-the-β¦
Danilo Britto π΅πͺπ¨π΄ retweeted
We made claudeβ.ai 3x faster in two weeks.
Hereβs how we use Claude to measure, debug and improve performance. Prompts and methods included.
claude.dev/blog/how-we-made-β¦
Danilo Britto π΅πͺπ¨π΄ retweeted
Claude Opus 5.5 drew each frame of this animation in JavaScript. Here's "how browsers work" in 40 seconds.
Danilo Britto π΅πͺπ¨π΄ retweeted
Build your own thermal camera with our guide! learn.pimoroni.com/article/bβ¦
Danilo Britto π΅πͺπ¨π΄ retweeted
Introducing Qwen Intelligence, bringing personal intelligence within everyone's reach. π±β¨
It launches with three SOTA agents: π₯³
- Mobile Planner Agent: plans, decomposes & orchestrates complex tasks. #1 on MobilePA-Bench, MobilePA-Bench Business & Memory.
- Mobile-Use Agent: gets things done, API-first with GUI fallback. MobileWorld 82.1, MobileWorld-Real 92.2, AndroidDaily 97.2, 90% end-to-end success rate.
- Mobile Creative Agent: turns one sentence into ready-to-use creations. Image generated in 3s, about 2x faster than leading peers.
We're also opening up our benchmark suite: MobilePA-Bench, MobileWorld, MobileWorld-Real, and MobileWorld-Safety, covering planning, cross-app execution, real-device performance and safety.
π Learn more about the agents:
- Qwen Intelligence official website: qwenintelligence.com
- Mobile Planner Agent: github.com/Tongyi-MAI/Qwen-Pβ¦
- Mobile-Use Agent: tongyi-mai.github.io/Qwen-UIβ¦
- Mobile Creative Agent: arxiv.org/abs/2608.16887
π Explore our open benchmark suite:
- MobilePA-Bench: tongyi-mai.github.io/MobilePβ¦
- MobileWorld (GitHub): github.com/Tongyi-MAI/Mobileβ¦
- Leaderboard: tongyi-mai.github.io/MobileWβ¦
Danilo Britto π΅πͺπ¨π΄ retweeted
Jev is awesome but for the love of god please STOP posting fake demos
Danilo Britto π΅πͺπ¨π΄ retweeted
Kev-0.5B: A tiny open source Jev-like decision model with a TypeSafe-compatible API based on Qwen2.5-0.5B that you can train and run on a MacBook Pro.
Model card and weights are available on GitHub
github.com/jaredpalmer/kev
Danilo Britto π΅πͺπ¨π΄ retweeted
At Anthropic, Claude now writes 80% of our code. Engineers ship 8x more code per quarter.
Side effect: Tests grew 10x. CI jobs up 25x in 6 months. Here's what helped us scale:
claude.com/blog/agentic-codiβ¦
