Frank He

Think, Build, Ship

[Frank He @fshewl]

@RobertJBye Having been using for a while, feels magical :P

[Anthropic @AnthropicAI]

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software.

It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans.
https://t.co/NQ7IfEtYk7

[Frank He @fshewl]

@Jiaxi_Cui 我之前也很难理解，但发现codex在opencode也用不了，因为openai从来就不允许subscription用在3rd party上，anthropic只是现在才封而已，3rd party用API的话一直没问题。感觉是opencode明知故犯，竖靶子而已……

[Frank He @fshewl]

@SIGKITTEN Thanks for pointing this out. I didn’t even know this is the common practice for all. Anthropic seems just closed a loophole?

[Frank He @fshewl]

@thdxr Does it mean ChatGPT currently has exact restriction as Claude? I can’t use OpenAI subscription at open code, right? Then what is the problem of Anthropic blocking the loophole of using subscription credentials in 3rd party app?

[Frank He @fshewl]

NotebookLM is best productivity tool. It gives knowledge structure.

[Frank He @fshewl]

@yegle 我报名吧

[Frank He @fshewl]

@addyosmani Need agentic capability from Gemini in Chrome!

[Frank He @fshewl]

Here is mine:

“A crystal ball of thunder and snow, Harry Potter riding broomstick.”

https://t.co/SMa0mJOsM8

[Google Gemini @GeminiApp]

You have until 10pm PT tonight (8/24) to take advantage of this weekend’s free Veo 3 video generations in Gemini.

Here’s some inspiration to get you pumped up:

[Frank He @fshewl]

@dotey 应该叫Vibe Prototyping

[Karl Weinmeister @kweinmeister]

Want to take your AI project from a cool demo to a real-world application? 🚀

Get ready in "Accelerate AI with Cloud Run," a free, full-day, hands-on developer workshop!

👉 https://t.co/wnJniAhQCN

Registration is now open for our first tour in North America. Seats are limited!

[Frank He @fshewl]

Run Docker Compose seemlessly on Cloud Run, including your ai model!

[Steren @steren]

Announcing @Docker compose support for @GoogleCloud Run:
- Define your app in compose.yaml
- Run locally with docker compose up
- Deploy with gcloud run compose up

[Frank He @fshewl]

@yetone 感谢！

[Frank He @fshewl]

@ammaar I wanna try!

[Frank He @fshewl]

@tualatrix 上次我从湾区飞Vegas，到降落了我都没连上WIFI。只能放弃了。

[Frank He @fshewl]

I saw the live demo at GCP Next in April. It's really amazing to see how to use Nvidia GPU on Cloud Run with Ollama and Gemma open models to build agents!

[NVIDIA AI Developer @NVIDIAAIDev]

Smart Health Agent uses multi-agent workflows for real-time health metrics 🌟

Check out Jay’s demo using Gemma 3 on accelerated GPUs and all your favorite technologies like LangGraph Ollama deployed to Google Cloud Run.

Download or clone to see how you can use Gemma in action ➡️ https://t.co/4hqw2oZY07

[NVIDIA AI Developer @NVIDIAAIDev]

Smart Health Agent uses multi-agent workflows for real-time health metrics 🌟

Check out Jay’s demo using Gemma 3 on accelerated GPUs and all your favorite technologies like LangGraph Ollama deployed to Google Cloud Run.

Download or clone to see how you can use Gemma in action ➡️ https://t.co/4hqw2oZY07

[Frank He @fshewl]

Try Cloud Run GPU today! No quota request needed!
https://t.co/OxcLz1CxAt

[Gabe Monroy @gabemonroy]

The ability to quickly light up GPUs on Google's serverless stack is the result of architectural decisions made years ago. It's not an easy bolt-on for others.

[Steren @steren]

🚀Today at #GoogleIO, we're making AI deployments easier by introducing 3 new ways to deploy your apps to Cloud Run:
1⃣ Deploy AI Studio apps to Cloud Run in a click
2⃣ Deploy Gemma 3 to Cloud Run in a click from AI Studio
3⃣ Deploy code to Cloud Run from any MCP client with a new MCP server

[Frank He @fshewl]

Cloud Run GPU is GA today!

[Steren @steren]

Scale to zero, 5s startup time, on-demand, highly scalable.
Cloud Run GPUs, now generally available.