Heiko Hotz
@heikohotz.bsky.social
AI Engineer @ Google 👨💻 — Educator 👨🏫 — Traveller ✈️ — Hobby photographer 📷 — Foodie 🌮 — Film fan 🍿 — Boardgamer 🎲 — Londoner💂♂️
Medium: https://heiko-hotz.medium.com/
Github: https://github.com/heiko-hotz
LI: https://www.linkedin.com/in/heikohotz/
Medium: https://heiko-hotz.medium.com/
Github: https://github.com/heiko-hotz
LI: https://www.linkedin.com/in/heikohotz/
I really like tiny (you could even say "nano") bananas. They are so full of flavour 😋
August 19, 2025 at 7:07 AM
I really like tiny (you could even say "nano") bananas. They are so full of flavour 😋
Official results are in - Gemini achieved gold-medal level in the International Mathematical Olympiad! 🏆
July 21, 2025 at 10:22 PM
Official results are in - Gemini achieved gold-medal level in the International Mathematical Olympiad! 🏆
Evaluating voice-driven agents got you pulling your hair out? 😩 Evaluating voice agents is WILD. Accents, noise, weird speech... how do you even test?! Manual prompt engineering for that? A total nightmare. 👇
July 15, 2025 at 7:05 AM
Evaluating voice-driven agents got you pulling your hair out? 😩 Evaluating voice agents is WILD. Accents, noise, weird speech... how do you even test?! Manual prompt engineering for that? A total nightmare. 👇
WWDC interviews with Apple executives just got a facelift - and it is refreshing!
For years, high-level Apple execs would come to John Gruber's (from Daring Fireball) Talk Show at WWDC. I often found these interviews less than insightful, and sometimes even annoying.
For years, high-level Apple execs would come to John Gruber's (from Daring Fireball) Talk Show at WWDC. I often found these interviews less than insightful, and sometimes even annoying.
June 12, 2025 at 3:39 PM
WWDC interviews with Apple executives just got a facelift - and it is refreshing!
For years, high-level Apple execs would come to John Gruber's (from Daring Fireball) Talk Show at WWDC. I often found these interviews less than insightful, and sometimes even annoying.
For years, high-level Apple execs would come to John Gruber's (from Daring Fireball) Talk Show at WWDC. I often found these interviews less than insightful, and sometimes even annoying.
Introducing Gemini-Powered Slide Creation by Voice!
In this quick demo, I’ve integrated a “Slide Creation Agent” into my personal project, Project Pastra. Watch how it effortlessly generates slides based on voice instructions.
In this quick demo, I’ve integrated a “Slide Creation Agent” into my personal project, Project Pastra. Watch how it effortlessly generates slides based on voice instructions.
January 14, 2025 at 7:47 AM
Introducing Gemini-Powered Slide Creation by Voice!
In this quick demo, I’ve integrated a “Slide Creation Agent” into my personal project, Project Pastra. Watch how it effortlessly generates slides based on voice instructions.
In this quick demo, I’ve integrated a “Slide Creation Agent” into my personal project, Project Pastra. Watch how it effortlessly generates slides based on voice instructions.
Multimodal AI models have the potential to finally deliver on the dream of language being the ultimate human-computer interface 🎙️
youtu.be/0OEDHAjY6LM
youtu.be/0OEDHAjY6LM
Gemini's Multimodal Live API with Calendar Tool
YouTube video by Heiko Hotz
youtu.be
January 8, 2025 at 7:42 AM
Multimodal AI models have the potential to finally deliver on the dream of language being the ultimate human-computer interface 🎙️
youtu.be/0OEDHAjY6LM
youtu.be/0OEDHAjY6LM
The Gemini Multimodal Live API Developer Guide is live!
December 30, 2024 at 9:25 AM
The Gemini Multimodal Live API Developer Guide is live!
𝗖𝗵𝗮𝗽𝘁𝗲𝗿 𝟲 𝗼𝗳 𝘁𝗵𝗲 𝗚𝗲𝗺𝗶𝗻𝗶 𝗠𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗟𝗶𝘃𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗚𝘂𝗶𝗱𝗲: 𝙒𝙝𝙖𝙩 𝙞𝙨 𝙖 𝙫𝙞𝙙𝙚𝙤, 𝙖𝙣𝙮𝙬𝙖𝙮?
After the hard fought battle of implementing proper audio communication in chapter 5, adding video capabilities to the multimodal live app a la Project Astra was a breeze.
After the hard fought battle of implementing proper audio communication in chapter 5, adding video capabilities to the multimodal live app a la Project Astra was a breeze.
December 27, 2024 at 8:59 AM
𝗖𝗵𝗮𝗽𝘁𝗲𝗿 𝟲 𝗼𝗳 𝘁𝗵𝗲 𝗚𝗲𝗺𝗶𝗻𝗶 𝗠𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗟𝗶𝘃𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗚𝘂𝗶𝗱𝗲: 𝙒𝙝𝙖𝙩 𝙞𝙨 𝙖 𝙫𝙞𝙙𝙚𝙤, 𝙖𝙣𝙮𝙬𝙖𝙮?
After the hard fought battle of implementing proper audio communication in chapter 5, adding video capabilities to the multimodal live app a la Project Astra was a breeze.
After the hard fought battle of implementing proper audio communication in chapter 5, adding video capabilities to the multimodal live app a la Project Astra was a breeze.
HELLO?? CAN YOU HEAR ME????
More times than I'm proud to admit did I utter these words into my laptop over the past few days 😅
More times than I'm proud to admit did I utter these words into my laptop over the past few days 😅
December 26, 2024 at 10:15 AM
HELLO?? CAN YOU HEAR ME????
More times than I'm proud to admit did I utter these words into my laptop over the past few days 😅
More times than I'm proud to admit did I utter these words into my laptop over the past few days 😅
𝗔 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗴𝘂𝗶𝗱𝗲 𝗳𝗼𝗿 𝗚𝗲𝗺𝗶𝗻𝗶’𝘀 𝗠𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗟𝗶𝘃𝗲 𝗔𝗣𝗜
December 24, 2024 at 9:36 AM
𝗔 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗴𝘂𝗶𝗱𝗲 𝗳𝗼𝗿 𝗚𝗲𝗺𝗶𝗻𝗶’𝘀 𝗠𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗟𝗶𝘃𝗲 𝗔𝗣𝗜
Developers are loving the Gemini 2.0 Multimodal Live API - we see so many of you starting to build with it 🤗
To get started with the API I wrote a small Python script (83 lines of code) that demonstrates how to set up a real-time, two-way audio communication with a Gemini language model.
To get started with the API I wrote a small Python script (83 lines of code) that demonstrates how to set up a real-time, two-way audio communication with a Gemini language model.
December 23, 2024 at 1:10 PM
Developers are loving the Gemini 2.0 Multimodal Live API - we see so many of you starting to build with it 🤗
To get started with the API I wrote a small Python script (83 lines of code) that demonstrates how to set up a real-time, two-way audio communication with a Gemini language model.
To get started with the API I wrote a small Python script (83 lines of code) that demonstrates how to set up a real-time, two-way audio communication with a Gemini language model.
December 19, 2024 at 10:04 PM
Math puzzle contest!
Gemini 2.0 Flash Thinking vs GPT-4o vs Claude 3.5 Sonnet. I was honestly surprised by the results.
Would love if someone could check with o1(Pro) 🤗
(Credit to the Bluesky community where I saw this puzzle a few days ago)
Gemini 2.0 Flash Thinking vs GPT-4o vs Claude 3.5 Sonnet. I was honestly surprised by the results.
Would love if someone could check with o1(Pro) 🤗
(Credit to the Bluesky community where I saw this puzzle a few days ago)
December 19, 2024 at 9:39 PM
Math puzzle contest!
Gemini 2.0 Flash Thinking vs GPT-4o vs Claude 3.5 Sonnet. I was honestly surprised by the results.
Would love if someone could check with o1(Pro) 🤗
(Credit to the Bluesky community where I saw this puzzle a few days ago)
Gemini 2.0 Flash Thinking vs GPT-4o vs Claude 3.5 Sonnet. I was honestly surprised by the results.
Would love if someone could check with o1(Pro) 🤗
(Credit to the Bluesky community where I saw this puzzle a few days ago)
Gemini 2.0 Flash Thinking released!
You thought we were done shipping, am I right? But the Google DeepMind folks had one more ace up their sleeves, and it's a big one!
#google #gemini #gemini2.0 #deepmind
You thought we were done shipping, am I right? But the Google DeepMind folks had one more ace up their sleeves, and it's a big one!
#google #gemini #gemini2.0 #deepmind
December 19, 2024 at 8:57 PM
Gemini 2.0 Flash Thinking released!
You thought we were done shipping, am I right? But the Google DeepMind folks had one more ace up their sleeves, and it's a big one!
#google #gemini #gemini2.0 #deepmind
You thought we were done shipping, am I right? But the Google DeepMind folks had one more ace up their sleeves, and it's a big one!
#google #gemini #gemini2.0 #deepmind
our web console serves as a valuable tool for developers exploring the vast capabilities of google's multimodal live api and its gemini foundation. #google #gemini #multimodal #api #devtools
December 18, 2024 at 6:53 PM
our web console serves as a valuable tool for developers exploring the vast capabilities of google's multimodal live api and its gemini foundation. #google #gemini #multimodal #api #devtools
the combination of react, websockets, and audio worklets creates a powerful and flexible development environment for the google multimodal live api. #google #gemini #react #websockets #audioworklets
December 18, 2024 at 4:53 PM
the combination of react, websockets, and audio worklets creates a powerful and flexible development environment for the google multimodal live api. #google #gemini #react #websockets #audioworklets
this project is a testament to the power of websockets and their ability to enable seamless, real-time communication between applications and apis. #google #gemini #websockets #realtime #api
December 18, 2024 at 2:53 PM
this project is a testament to the power of websockets and their ability to enable seamless, real-time communication between applications and apis. #google #gemini #websockets #realtime #api
experience the future of multimodal development with our react-based web console for the google multimodal live api. #google #gemini #react #multimodal #innovation
December 18, 2024 at 12:53 PM
experience the future of multimodal development with our react-based web console for the google multimodal live api. #google #gemini #react #multimodal #innovation
our application is designed to facilitate real-time interactions with the google multimodal live api, simplifying the development of complex applications. #google #gemini #realtime #api #development
December 18, 2024 at 10:53 AM
our application is designed to facilitate real-time interactions with the google multimodal live api, simplifying the development of complex applications. #google #gemini #realtime #api #development
the console features an event-driven architecture, emitting events for connection status, incoming data, and outgoing data. #google #gemini #events #websocket #programming
December 18, 2024 at 8:53 AM
the console features an event-driven architecture, emitting events for connection status, incoming data, and outgoing data. #google #gemini #events #websocket #programming
Talk (and I really mean 🗣️) to your docs!
The Gemini Multimodal Live API has taken the developer community by storm and many have already started building with it. Here I show how to talk to your docs.
youtu.be/0ak684rtRvA
#google #gemini #live #multimodal
The Gemini Multimodal Live API has taken the developer community by storm and many have already started building with it. Here I show how to talk to your docs.
youtu.be/0ak684rtRvA
#google #gemini #live #multimodal
Talk to docs
YouTube video by Heiko Hotz
youtu.be
December 18, 2024 at 7:10 AM
Talk (and I really mean 🗣️) to your docs!
The Gemini Multimodal Live API has taken the developer community by storm and many have already started building with it. Here I show how to talk to your docs.
youtu.be/0ak684rtRvA
#google #gemini #live #multimodal
The Gemini Multimodal Live API has taken the developer community by storm and many have already started building with it. Here I show how to talk to your docs.
youtu.be/0ak684rtRvA
#google #gemini #live #multimodal
developers can send text, real-time audio, and image input to the google multimodal live api through our intuitive console. #google #gemini #multimodality #api #webdev
December 18, 2024 at 6:53 AM
developers can send text, real-time audio, and image input to the google multimodal live api through our intuitive console. #google #gemini #multimodality #api #webdev
our app provides a comprehensive development environment for interacting with google's cutting-edge multimodal live api. #google #gemini #multimodal #ai #developers
December 17, 2024 at 8:53 PM
our app provides a comprehensive development environment for interacting with google's cutting-edge multimodal live api. #google #gemini #multimodal #ai #developers