Pinned Tweet
I work on agents that can work with each other, and with us. A2A for agent collaboration. A2UI for agents driving your design system. Open standards with AAIF. I'll share things I'm building, questions I'm stuck on, and what we learn making these work outside demos.
3
216
alan blount retweeted
Knowledge Catalog, Google Cloud's universal context engine, turns knowledge into shared business context so agents answer and act with higher accuracy and trust ↓
alan blount retweeted
This is my favorite type of launch blog.
Even if you don't care about A2UI—you should, personalized UIs are the future—open the link and see:
✅ Clear why, with examples
✅ List of what's new in 1.0
✅ Proof points from users
✅ Links galore
developers.googleblog.com/a2…
I tend to talk fast and skip a lot of the details, but I ended up getting totally sucked in watching this video build up from first principles step by step how to understand the mechanics under A2UI.
It's brilliant, and I enjoyed watching all 1hr of it
A2UI reached version 1! 🚀
This protocol lets agents define a component tree, and frameworks like #Angular or #React render it.
Our video explains how A2UI works and shows it in action:
🎥 youtube.com/watch?v=kZ7fzADj…
#A2UI #AgenticAI #GenerativeUI
3
76
alan blount retweeted
When Google’s A2UI team says your language inspired theirs 🫡
The Google team really cooked with 1.0. Best explanation I’ve read of why generating code for Generative UI is a bad idea.
OpenUI + A2UI interop coming soon!
alan blount retweeted
🎉 Introducing Open Intelligent UI in your app
Powered by A2UI 1.0 and CopilotKit
It takes just two lines of code, to get full generative UI inside of your application:
✨ Use your own components, or our pre-built catalog
🔌 Any model, any agent stack
⌚️ Lower latency and fewer tokens
🩺 Self-healing output
Add generative UI anywhere in your product with Surfaces, starting from our ready-made catalog. Set it up in 2 lines of code!
Get Started (repo, docs): go.copilotkit.ai/open-intell…
alan blount retweeted
a much anticipated launch! amazing seeing the work @CopilotKit and @Google co-contributed to A2UI go live
🤸♂️play around with it at go.copilotkit.ai/a2ui-playgr…
big thanks to @zeroasterisk & @MotwaniVishal for enabling this partnership
alan blount retweeted
Yes, working on an official interop:
github.com/modelcontextproto…
alan blount retweeted
Replying to @GoogleCloudTech
alan blount retweeted
Just wanted to share a (very much WIP) little side project of mine showcasing the benefits/speed of @googlegemma DiffusionGemma 🙂 (text diffusion model)
Project is called “DiffusionGearvis” (mix between DiffusionGemma and Jarvis, IronMan’s AI assistant) and I wanted to implement some features for which I believe text diffusion can really shine, the first one being computer use.
With the success of Muse from Meta, it is very clear that computer use has tremendous value for users. However, this feature is 1) notoriously slow 2) raises serious privacy concerns (screenshots and other personal data uploaded to the cloud). DiffusionGemma can help with both 🙂 It is super fast thanks to text diffusion and is open-weight so people can run it privately on their own desktop / VM. All the demo videos were run locally on a desktop with a single @NVIDIAAIDev RTX 5090 with speech-to-text and text-to-speech from @kyutai_labs (stt-1b-en_fr and pocket_tts) .
This is with the vanilla NVFP4 checkpoint served on @vllm_project so performance can vastly be improved with dedicated fine-tuning or distillation from larger open-weights models. I hope that in a few months, the open-source community will create some fast “local Muse” on top of it :
Kaggle.com/arenas #1 example is pelicans riding a bicycle... This makes me very happy. @simonw
99
alan blount retweeted
Muse Spark Open from @Meta is now available on the Gemini platform.
Meta's coding-optimized open-weight model is available for developers building long-running agentic coding workflows.
Try Muse Spark Open now → goo.gle/4zvPTXL
Serendipity. When we planned for Sita to make a UCP / AP2 walkthrough on adventofagents.com/2026/10/1…
... we didn't know it was the day after @google launched the new universal cart in the US. blog.google/products-and-pla…
[Insert A-team "I love it when a plan comes together" meme]
alan blount retweeted
Google’s new Gemini 4 Argon equals GPT-6 Astra on the Artificial Analysis Intelligence Index at 60% of the Cost per Task with discounted prices. Google is now back to being one of the top three labs in intelligence achieved
Gemini 4 Argon is @GoogleDeepMind’s first proprietary model above the Flash class in over 7 months. With high reasoning (the highest available), it scores 53 on the Artificial Analysis Intelligence Index, matching GPT-6 Astra (max, 53) and 1 point ahead of GPT-6.1 Sol (max, 52), with gains driven by lower hallucinations and stronger agentic capabilities.
At its current 50% pricing discount and with cache discounts increased to 95%, Gemini 4 Argon costs $1.99 per Intelligence Index task, 60% of GPT-6 Astra (max), but 2.7x GPT-6.1 Sol (max). After the discount ends, this will rise to $3.98 (~1.2x GPT-6 Astra (max)).
Gemini 4 Argon is currently being rolled out to selected users and is not publicly available. The 50% discount is an initial promotion. Google has not yet confirmed the promotion end date
Key benchmarking results for Gemini 4 Argon with high reasoning:
➤ Google returns as one of the top three labs on intelligence: Gemini 4 Argon (high) scores 53 on the Artificial Analysis Intelligence Index, matching GPT-6 Astra (max, 53) and 1 point ahead of GPT-6.1 Sol (max, 52). This is 23 points above Google’s previous non-Flash model, Gemini 3.1 Pro Preview (30) and 12 points ahead of Gemini 3.8 Flash (high)
➤ Launch discounts of 50% make Gemini 4 Argon competitive on Cost per Task: At current discounted pricing, Gemini 4 Argon (high) costs $1.99 per Intelligence Index task, 60% of GPT-6 Astra (max, $3.26) for a comparable level of intelligence. This cost efficiency is driven by lower token prices, rather than reduced token use, with Gemini 4 Argon averaging 62k output tokens per task, compared with 27k for GPT-6 Astra (max). Google has not yet confirmed the promotion end date, but on standard pricing, Cost per Task will increase to $3.98
➤ Stronger agentic performance: Historically a weaker area for Gemini models, Gemini 4 Argon shows improvements across agentic evaluations. It ranks #1 on AutomationBench-AA at 77.5%, 6 points ahead of Claude Sonnet 5.5 (max, 71.3%). On Terminal Bench 4, Gemini 4 Argon achieves 57%, a +53 point improvement from Gemini 3.1 Pro Preview, only behind Claude Sonnet 5.5 (max, 64%), Claude Opus 5.5 (max, 60%) and GPT-6 Astra (59%). On AA-Briefcase, it reaches 1494 Elo. This is driven by a 65% rubric pass rate, the highest we have recorded, but lower Analytical Quality (1576 Elo) and Presentation Quality (1308 Elo)
➤ Lowest hallucination rate among leading models: On AA-Omniscience, Gemini 4 Argon has a 15% hallucination rate, the lowest of any model scoring 45+ on the Intelligence Index, compared with 51% for GPT-6 Astra (max) and 54% for GPT-6.1 Sol (max). This means Argon is much more likely to acknowledge when it does not know an answer rather than guess incorrectly. On accuracy, Gemini 4 Argon scores 50%, a 5 point decrease from Gemini 3.1 Pro Preview, and 13 points below GPT-6 Astra (max, 63%). With this slightly lower accuracy, its overall AA-Omniscience score of 42 remains in line with GPT-6 Astra (43) and GPT-6.1 Sol (42)
Key model details:
➤ Context Window: 1M tokens
➤ Multimodality: Text, image, video, and speech input, with text output
➤ Pricing: $4/$20 per 1M input/output tokens at standard pricing, currently discounted 50% to $2/$10. Cached input tokens receive a 95% discount ($0.10 per 1M at discounted pricing), up from 90% on Gemini 3.8 Flash
➤ Long Decode Continuation: We tested Gemini 4 Argon with Long Decode Continuation, a new Gemini API feature that pauses long responses and resumes them across follow-up calls. This lets reasoning run up to 1M output tokens without request timeouts
alan blount retweeted
Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking 🚀
Excited for these two SOTA live audio models with frontier price and performance.
Extended thinking can run tool calls and think in parallel, which makes it incredibly cool and smooth to use 👇
🤖 Made with AI
alan blount retweeted
Today, we’re announcing the general availability of extended capabilities in Gemini Enterprise Agent Platform!
Take full advantage of our centralized, end-to-end platform to simply and securely scale and manage your agents and workflows → goo.gle/3RYp6Dv
Python, MCP, A2A, and a whole lot about how to build multi-agent systems.
This goes well beyond building a single agent: it focuses on how multiple agents can collaborate towards a goal.
Best part:
The book will show you how to build everything from scratch. You start with a simple agent and then add complexity as the book progresses.
Amazon link: amzn.to/3OVgk7M


























