Author of Crawl4AI. AI & software builder, systems thinker, founder of Kidocode. I build, analyze, and advise on hard technical problems.
Singapore
Joined September 2009
- Tweets2.8K
- Following379
- Followers3.1K
- Likes3.7K
Unclecode (Hossein) retweeted
New in Claude Code: claude plugin eval
See what value your plugin is adding, or if it needs more work.
You can create test cases, run your plugin or skill against those test cases, score those runs, then run each case again without the plugin to see the differences.
Unclecode (Hossein) retweeted
大神出手了，以后新模型是哪家的不用猜了。
这个modelprint开源工具解决了这个问题，今天的Ox Alpha 确定了是GLM 新模型！
工具地址：
unclecode.github.io/modelpri…
开源代码库在这里：
github.com/unclecode/modelpr…
Everyone guessed who made Ox Alpha today. I fingerprinted it instead. One page, 9 infrastructure probes: tokenizers, error codes, hidden templates. I ran • the mystery model against 12 suspects. One family matches every tokenizer test: GLM. Plumbing does not lie. Tool in reply, bring your own keys. Link in reply
Unclecode (Hossein) retweeted
"If a problem takes 20 tasks to solve and I can get open models to do 15 out of 20 tasks, then that brings down my compute bill at the end of the day... and that makes me very happy!"
Loved this conversation between @DynamicWebPaige and @steipete about the complementary relationship between frontier models like Fable 5 and open/local models like Gemma 4. Includes a shoutout to Transformers.js and our recent agentic WebGPU kernel optimization work! 🤗
“Agentic kernel optimization is the future of on-device inference”
@xenovacom used Fable 5 to write kernels that pushed Gemma 4 to a massive 255 tok/s on WebGPU with M4. He shared the demo, so you can try in your browser!!
Unclecode (Hossein) retweeted
To get good animations from an AI you need to get good at telling it what you want:
- "stagger this list of items"
- "make this animation direction-aware"
- "spacial consistency", "crossfade", "layout animation",
I made a motion vocabulary for this:
animations.dev/vocabulary
Unclecode (Hossein) retweeted
How do you keep Claude working until the job is done? Claude Code helps with this in a few ways, including one we shipped recently: /goal.
Unclecode (Hossein) retweeted
OpenAI Symphony is actually great
You can 5x Coding agent outcome with it + Good codebase harness
Played with it past few days and here is my setup:
- Playwright CLI
- Boot skill
- WORKFLOW.md
...
Broken it down in 12 mins below so you can do the same 👇
Unclecode (Hossein) retweeted
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude.
Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
Unclecode (Hossein) retweeted
For the developers building with Claude, a direct line from the team.
Follow for changelogs, API releases, community updates, and deep dives.
Unclecode (Hossein) retweeted
Use /schedule to create recurring cloud-based jobs for Claude, directly from the terminal.
We use these internally to automatically resolve CI failures, push doc updates, and generally power automations that you want to exists beyond a closed laptop
Unclecode (Hossein) retweeted
Google just dropped an official CLI for gmail, drive, calendar sheets and more
complete with skills and an MCP server 👌
Introducing the Google Workspace CLI: github.com/googleworkspace/c… - built for humans and agents.
Google Drive, Gmail, Calendar, and every Workspace API. 40+ agent skills included.
Unclecode (Hossein) retweeted
Gemini 3's hidden power = Awesome UI Animator
It actually contains good knowledge around popular animation libraries
You just need right prompt spec + process to unlock it
Here is my process 🧵👇
Unclecode (Hossein) retweeted
You can now fine-tune LLMs and deploy them directly on your phone! 🚀
We collabed with PyTorch so you can export and run your trained model 100% locally on your iOS or Android device.
Deploy Qwen3 on Pixel 8 and iPhone 15 Pro at ~40 tokens/sec.
Guide: docs.unsloth.ai/new/deploy-l…
Unclecode (Hossein) retweeted
We teamed up with @NVIDIA and @MatthewBerman to teach you how to do Reinforcement Learning!
Learn about:
- RL environments, reward functions & reward hacking
- Training OpenAI gpt-oss to automatically solve 2048
- Local Windows training with @NVIDIA_AI_PC RTX GPUs
- How RLVR (verifiable rewards) works
- How to interpret RL metrics like KL Divergence
Full video tutorial: youtube.com/watch?v=9t-BAjzB…
Unclecode (Hossein) retweeted
Introducing SAM Audio: the first unified AI model that allows you to isolate and edit sound from complex audio mixtures. This could mean isolating the guitar in a video of your band, filtering out traffic noises, or removing the sound of a dog barking in your podcast, all with text, visual, and time span prompts.
about.fb.com/news/2025/12/ou…
Unclecode (Hossein) retweeted
Introducing 1st full-stack AI Designer
An AI agent that can plan, generate graphic assets, Video animation, production UI code all with full context
Design like this could easily cost $5~$10k just 1 year ago, but now is possible to deliver in 10 min without any design skills
Learnt from @KyleSkelly and I just can't resist to build it in @SuperDesignDev, very satisfying to have image/video/code gen all in one place with consistent context
You can try this on superdesign.dev today