
DX at @GoogleDeepMind | @GitHub ⭐️ | @HackerHouseTW | Formerly @elevenlabsio, @Supabase, @Stripe, @Google, @SAP • my views
NYC, New York, US
Joined December 2014
- Tweets16.2K
- Following6K
- Followers13.2K
- Likes43.1K
Thor 雷神 ⚡️ retweeted
spent last night building real time voice agents on gemini at the @AgoraIO x @GoogleDeepMind workshop. so many nyc businesses still run on phone calls, front desks, reservations, support lines. voice feels like where agents actually start helping normal people.
thanks @hermes_f and @thorwebdev for hosting
Thor 雷神 ⚡️ retweeted
Last week at @GoogleDeepMind was busy, we shipped 7 developer launches.
🧠 Gemini 4 Carbon
⚡ Gemini 4 Hydrogen
⚖️ Gemini Decisions API + Gemini Decision 1
📦 Self-hosted sandboxes for Managed Agents
📊 Multimodal Knowledge Agent benchmark
🤖 Gemini Robotics 2.5
🧬 AlphaGenome 2
Thor 雷神 ⚡️ retweeted
New in Gemini: Connect Google Wallet for personal finance insights
This is powerful for things like:
+ making instant charts to visualize your spend
+ finding sneaky subscription price hikes
+ making a holiday budget based on what you actually spent last year
Thor 雷神 ⚡️ retweeted
i built an interactive website to share my love for chye png (🇸🇬 ‘s economy rice)
chye png has always been such a big part of singaporean food culture. i’ve grown up eating it, and for many singaporeans, it’s one of those everyday comfort foods we never get tired of.
so today, i wanted to bring a little taste of singapore to those who have never been here or had the chance to try chye png!
come build your own dabao (takeaway) box, pick your favourite dishes, and experience a little piece of everyday singaporean life. ❤️🍚
chyepng-m4pbljau.manus.space…
Special shout out to DevFest KL team!
They did such an amazing job. We had almost 1,000+ developers attending from across Southeast Asia.
Everyone in the room was so eager to connect and learn with latest Google AI & Google Cloud tech.
It’s the best time to a builder!
Thor 雷神 ⚡️ retweeted
The /swarm feature with Gemini 4 Carbon is so underhyped.
I asked for a 3D model of the Ferry Building.
It orchestrated 12 parallel agents to research, plan, write the Blender Python scripts, and critique each other's work on a shared message board 🤯
Thor 雷神 ⚡️ retweeted
Built by Gemini 4 Hydrogen purely in single-file code...no external libraries, no skills, no image generators, and zero embedded assets.
Thor 雷神 ⚡️ retweeted
What a week! 🔥
Gemini 4 Carbon
Gemini Decisions API
Gemini 4 Hydrogen
Gemini Robotics 2.5
AlphaGenome 2
Multimodal Knowledge Agent benchmark
Thor 雷神 ⚡️ retweeted
Gemini 4 Carbon, Hydrogen, and the Decisions API in one game: Parking Bench.
Carbon built the tabletop puzzle in @antigravity and you race 1v1 against Hydrogen or Gemini Decision 1 on the Gemini API across 5 levels.
Both models play pure vision off a single board PNG with zero grid state.
Thor 雷神 ⚡️ retweeted
big week of shipping for @GoogleAIStudio and @GoogleDeepMind
here's a quick recap
ai.studio to try everything :)
Gemini 4 Hydrogen is out and you can already use it in OpenClaw! 🦞
www.teapawt.org/OfficialLoganK/status/…
Thor 雷神 ⚡️ retweeted
I got early access to Gemini 4 Hydrogen High in Antigravity, so I asked it to build a futuristic city I could actually fly through. Its pretty fast and pretty good. Have a look:
After one follow-up, this Three.js world has procedural towers, rain and flying traffic. I could watch this flythrough for a while.
7 tests 🧵:
[ System One | Decision | Classifier ] models are the hot new thing. Pipecat 1.12 added a Classifiers abstraction. Since that release, we've been building a *lot* of things on top of that abstraction.
Google released Decision 1 yesterday, a classifier model that can take audio input.
Check out Jon's example (code and a video) below, which uses Google Decision 1.
Jon's PerceptionReader class is in Pipecat 1.16 (also released yesterday). PerceptionReader makes it easy to create a voice agent that understands how a user is speaking: positive, sad, frustrated, etc.
Pipecat 1.16 adds PerceptionReader, something I'm really excited about. How someone speaks can matter just as much as what they say, and voice agents have mostly been missing that.
We’ve been testing it with Google Decision 1, released yesterday. Stream it audio and you get a pretty accurate read on the prosody, tone and sarcasm of what the user said.
Try talking to it at this demo here: pipecat-google-decision-demo…
We've exploring many different ways of measuring expressivity... more to share on that soon!
➡️ Pipecat Docs: docs.pipecat.ai/api-referenc…
➡️ Google Decision 1: blog.google/innovation-and-a…
Thor 雷神 ⚡️ retweeted
gemini decisions API launched today!
this API will feel very familiar if you've used jev or other decision models. gemini decisions is much faster and cheaper than an LLM, and outputs are structured + reliable :)
we have day 0 support in langchain: docs.langchain.com/oss/pytho…
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details:
- 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring
- $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite)
- leads on several benchmark evals with lowest calibration error
Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)
Thor 雷神 ⚡️ retweeted
Gemini Decision 1 from @GoogleAIStudio is live on OpenRouter!
Google's first decision model. Hand it text, images, audio, video, or a PDF plus typed questions, and it answers yes/no, picks from up to 255 options, or scores, each with a probability. 262K context.
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details:
- 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring
- $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite)
- leads on several benchmark evals with lowest calibration error
Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)
Use the Gemini Decisions API with the AI SDK
introducing the Gemini Decisions API
powered by Gemini Decision 1, our new multimodal decision model
get fast, calibrated decisions on up to 1000 questions at once across text, images, audio, video, and PDFs
try it today in AI Studio and via the Gemini API ai.studio








































