Richard C. Suwandi
@richardcsuwandi
AI PhD @cuhksz. Co-Founder @AIDDA_institute. Co-developed OpenEvolve, Kai @driaforall for automated research & discovery. Dev ambassador @Alibaba_Qwen
422 Following 1.2K Followers
AI conferences today are literally following scaling laws
10 years later, there are more than 60k submissions to ICLR 2027, a >120x increase 🤯
The code and weights are going open-source soon!
I got early access to @Alibaba_Qwen's new image model, Qwen-Image 2.1.
I ran 5 prompts (one-shot generation) covering a dense infographic, a multi-panel comic, a macro photo, a chalkboard menu, and a movie poster.
Thread below 🧵
Show more
I got early access to @Alibaba_Qwen's new image model, Qwen-Image 2.1.
I ran 5 prompts (one-shot generation) covering a dense infographic, a multi-panel comic, a macro photo, a chalkboard menu, and a movie poster.
Thread below 🧵
Show more
In today's agents, we have many classification steps that still burn a full LLM call.
This is a great write up on how we can utilize @typesafeai's Jev for those: model routing (cheap model for simple lookups, stronger one for hard debug) and auto mode (flag risky tool calls before they run).
Show more
I have mixed feelings about this
I've seen people describe Jev as an "AI if statement". But what if it actually WAS an if statement?
Introducing Probably: a programming language powered by Jev:
Jev baked into the language. “feels” asks a question. “match” routes between descriptions. “while” keeps going until something stops feeling true.
This is obviously a toy, but it's fun to think about what something like Jev unlocks. Jev makes the decisions, an LLM does the writing, and a little program ties it together.
Show more
🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities!
Native audio-video understanding, reasoning, and tool use come together in one model: understand the content, plan the task, execute with tools, and deliver the result.
Highlights: 🥳
- Audio-video intelligence that gets things done: jointly reason over what's seen and heard, and orchestrate tools across long workflows to auto-edit vlogs, translate short videos, and turn movies into recaps.
- A major leap: approaching Gemini 3.8 Flash in audio-video capabilities; +19.5 points on average in agent performance across WildClawBench-MM & UniClawBench.
- 1M-token context with agentic perception: actively explore long videos and locate key moments with higher accuracy, using 51.8% fewer tokens than static understanding on OmniVideoBench.
Video input costs are reduced by about 89% compared with Qwen3.5-Omni-Plus, making long-form audio-video understanding and agentic workflows more affordable than ever.
To help you build apps around Omni, we're also open-sourcing Qwen-MM-Plugins and Qwen-Live Harness! 🛠️
We can't wait to see what you build with Qwen3.8-Omni-Flash! 👀
- Blog:
- Qwencloud:
- Qwen Studio:
- API:
- Qwen-MM-Plugins:
- Qwen-Live Harness: coming soon
Show more
we need to pace dwarkesh podcast asap i can't keep up
Highly recommend this book for anyone learning LLMs from scratch. It has the most intuitive breakdown of attention mechanisms you'll find
Excited to share PlugBO 🔌, a modular framework for agentic Bayesian optimization (BO)
In a standard BO routine, we usually declare the surrogate family, the acquisition function, and the search bounds before the first evaluation, and we keep them fixed after that.
What if, instead, we treat those choices as live slots that an LLM agent can inspect and swap?
Show more
