kat kampf
@kat_kampf
Product for AI Studio and the Gemini API @Google • she/her • views and subpar jokes are my own
Conversational image segmentation let's you more naturally use Gemini to parse images, e.g. "the car that is farthest away," "food that is vegetarian," or abstract concepts like "a tripping hazard" A personal favorite Gemini capability, such a cool building block 💥 Read more:…
Gemini 2.5 Flash-Lite, our fastest and most cost effective 2.5 model, is now stable and generally available 😃 $0.10 / 1M input tokens, $0.40 / 1M output tokens
Infinite Wiki ⁕ Every word is a hyperlink. Every description is generated in real-time (in ~1 second) ⁕ Runs on Gemini 2.5 Flash Lite. ASCII diagrams using 2.5 Flash
Finally got round to testing Veo 3 for ads- IKEA (inspo ad) Prompt below👇
Just getting back from vacation in Turkey I’m sure it was a very quiet stretch and nothing at all happened in AI land 🤗
Very excited to share that @windsurf_ai co-founders @_mohansolo & Douglas Chen, and some of their talented team have joined @GoogleDeepMind to help advance our work in agentic coding in Gemini. Welcome to our new team mates from Windsurf! theverge.com/openai/705999/…
Can't tell you how much I love OSS. Hours after sharing this post we now have support for video and audio modalities. The community makes working on this so much more rewarding. github.com/google-gemini/…
If you didn't know, Gemini CLI can work with your images and PDFs. Gemini can choose to read multi-modal content on its own or you can explicitly reference content with `@`.
I love this era of going from a specific idea -> app in minutes This week: mini app that takes my weekly CSA hauls, asks Gemini for recipe ideas, and then uses Imagen to show me what they would look like (with better cooking abilities 🥲)
👀
We're cooking up a fresh new design for AI Studio! ✨ And we'd absolutely love your input. If want to test an early prototype and share your thoughts on a call, just drop a reply below! Your feedback will help us shape it.
ICYMI: Imagen 4 and Imagen 4 Ultra are now available in AI Studio :) aistudio.google.com/app/prompts/ne…
Hello Gemini 2.5 Flash-Lite! So fast, it codes *each screen* on the fly (Neural OS concept 👇). The frontier isn't always about large models and beating benchmarks. In this case, a super fast & good model can unlock drastic use cases. Read more: blog.google/products/gemin…
Updates to the Gemini 2.5 family today! - gemini-2.5-pro and gemini-2.5-flash are now stable and generally available - We’re introducing Gemini Flash-Lite, our fastest and most cost effective 2.5 model⚡️
New model day new model day
Introducing our latest update to Gemini 2.5 Pro (06-05), which we expect to become our long term stable release. At a glance: - SOTA on HLE, Aider, and GPQA - Now supports thinking budgets - Same cost, on pareto frontier - Closes gap on 03-25 regressions