Thoughts Brewing, LLC

Thoughts Brewing, LLC Helping Businesses Solve Problems
Expert Fractional COO/CTO and AI services to elevate your business strategy and operations.

Refine Selected Text In Google Docs With GeminiGoogle Docs integrated Gemini into your right-click menu, making basic AI...
09/07/2026

Refine Selected Text In Google Docs With Gemini

Google Docs integrated Gemini into your right-click menu, making basic AI editing accessible without leaving your document.

I'll show you how to select text, right-click, and use the new Refine option. And talk about why you should review the output instead of automatically accepting Gemini’s first attempt.

The Google Docs Gemini Blueprint:
- Highlight & Right-Click: Select any block of text in your Google Doc, right-click, and choose Refine the Selected Text option.
- Select a Preset: Choose from built-in actions like Rephrase, Shorten, Elaborate, More formal, Bulletize, or Summarize.
- Use the Side Panel: Review the live markup changes in your document. Accept or reject the output, or use the open Gemini side panel to add custom prompts (like turning two sentences into a bedtime story or generating illustrations to add to the story).
- Workplace Applications: Highlight meeting notes, outline drafts, or raw text to generate stakeholder updates, meeting summaries, or executive reports directly in your document.

Whether you're testing AI writing tools for the first time or looking for a faster editing workflow in Google Workspace, this native shortcut eliminates copying and pasting between apps.

✨ Join the NotebookLM (Gemini Notebook) Weekend Masterclass:
https://maven.com/thoughts-brewing-llc/learn-notebooklm-in-a-weekend-2-cohort

🌟 REQUEST A VIDEO → https://thoughtsbrewing.com/en-us/youtube-video-request-page?utm_source=youtube

❓ ASK A QUESTION → https://thoughtsbrewing.com/en-us/ask-us-anything-business-tech?utm_source=youtube



▶️ Watch Next → Is the Bottom Bar in Gemini Needed?: https://youtu.be/3NZ0A1JDNoY?si=FKmcFEHS2qutXAmW

➡️ BLOG: https://thoughtsbrewing.com/en-us/blog-subscription?utm_source=youtube

➡️ SUBSCRIBE: https://www.youtube.com/

https://www.youtube.com/watch?v=d6tmcWKToc8

https://www.youtube.com/watch?v=d6tmcWKToc8

Gemini 3.8 FlashGoogle released Gemini 3.8 Flash only three weeks after Gemini 3.7 Flash. The new model costs the same d...
09/06/2026

Gemini 3.8 Flash

Google released Gemini 3.8 Flash only three weeks after Gemini 3.7 Flash. The new model costs the same during its introductory period/

I'll break down what Google updated in 3.8 Flash, demo how to select 3.8 Flash inside Google AI Studio and show you how OpenRouter can cut your input costs nearly in half.

Details and setup steps:
- Core Updates: Enhanced autonomous agent performance, long-horizon coding tasks, and enterprise workflow handling.
- Technical Limits: Accepts text, image, video, audio, and PDF inputs with a ~1M input token limit and ~65K output token limit.
- Access Method 1 (Google AI Studio): Navigate to aistudio.google.com, open the Playground, and select Gemini 3.8 Flash from the top model list.
- Access Method 2 (OpenRouter): Search for Gemini 3.8 Flash on openrouter.ai to compare providers offering rates as low as ~$0.38/1M input tokens.

Introductory API pricing through December 31, 2026:
- Input: $0.75 per million tokens
- Output: $3.75 per million tokens

Standard pricing beginning January 1, 2027:
- Input: $1.50 per million tokens
- Output: $7.50 per million tokens

Google says 3.8 Flash may use more tokens while working through difficult, multi-step tasks. If efficiency is your priority, Gemini 3.7 Flash remains supported and may still be the better choice.

📝 Google's Developer Documentation 1: https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash

📝 Google's Developer Documentation 2: https://ai.google.dev/gemini-api/docs/latest-model

🌟 REQUEST A VIDEO → https://thoughtsbrewing.com/en-us/youtube-video-request-page?utm_source=youtube

❓ ASK A QUESTION → https://thoughtsbrewing.com/en-us/ask-us-anything-business-tech?utm_source=youtube



▶️ Watch Next → Leader's Playbook for Gemini At work: https://youtu.be/-CQu9BnSbkI?si=XlzFM0bLO0YE-ep8

➡️ BLOG: https://thoughtsbrewing.com/en-us/blog-subscription?utm_source=youtube

➡️ SUBSCRIBE: https://www.youtube.com/

https://www.youtube.com/watch?v=uMrZGi90GTM

https://www.youtube.com/watch?v=uMrZGi90GTM

NVIDIA + Hugging Face: What's Changing?Nvidia has agreed to acquire Hugging Face for approximately $12.93 billion. If yo...
09/05/2026

NVIDIA + Hugging Face: What's Changing?

Nvidia has agreed to acquire Hugging Face for approximately $12.93 billion. If you use Hugging Face for models, datasets, applications, or hosted AI projects, the important question is what happens to the platform next.

I'll talk about why Hugging Face matters, what Nvidia may gain from the acquisition, and which parts of the platform longtime users will be watching closely.

Key findings and ecosystem details covered:
- Unconfirmed Reports: Major news outlets report a $12.9B to $13B acquisition, though official press releases from Nvidia or Hugging Face are still pending (at least as of when I recorded the video).
- Platform Scale: Hugging Face currently hosts over 3 million models (ranging from small language models to specialized tabular regression tools) and over 1 million public datasets.
- Core Features: A tour of Spaces (virtual machine sandboxes), Storage Buckets, and the HF Pro tier for expanded compute and inference.
- Strategic Drivers: Potential motivations behind Nvidia's interest, including controlling key developer communities, acquiring cloud compute infrastructure, and securing a stake in open-weights distribution.
- Market Context: Recent acquisition trends across AI infrastructure, including Stripe's acquisition of OpenRouter, and what changing ownership typically means for active users. (Watch: https://youtu.be/gsAMJwj6u2g?si=xVXDpyN89m1idfsJ)

UPDATE: This video was recorded while the acquisition was still being reported without official confirmation. On September 3, 2026, Nvidia confirmed that it had agreed to acquire Hugging Face for $12,930,300,000.

📝 Nvidia's Announcement: https://blogs.nvidia.com/blog/nvidia-to-acquire-hugging-face/

Nvidia says Hugging Face will remain an open platform supporting different models, frameworks, cloud providers, inference services, and computing platforms. Nvidia hardware will not be required to build or deploy through Hugging Face.

🌟 REQUEST A VIDEO → https://thoughtsbrewing.com/en-us/youtube-video-request-page?utm_source=youtube

❓ ASK A QUESTION → https://thoughtsbrewing.com/en-us/ask-us-anything-business-tech?utm_source=youtube



▶️ Watch Next → Stripe Buys OpenRouter: https://youtu.be/gsAMJwj6u2g?si=qf8EhF6ykh4IFYva

➡️ BLOG: https://thoughtsbrewing.com/en-us/blog-subscription?utm_source=youtube

➡️ SUBSCRIBE: https://www.youtube.com/

https://www.youtube.com/watch?v=nwvMS3HSnwg

https://www.youtube.com/watch?v=nwvMS3HSnwg

OpenAI Is Leaving CursorOpenAI has announced plans to pull its models from Cursor following SpaceX's acquisition of the ...
09/04/2026

OpenAI Is Leaving Cursor

OpenAI has announced plans to pull its models from Cursor following SpaceX's acquisition of the agentic coding platform. If your daily development workflow relies on OpenAI models inside Cursor, you need an exit plan before access disappears.

I'll walk through OpenAI's announcement, the November 12, 2026 shutoff date and list some alternative agentic coding tools you can switch to right now.

Key takeaways:
- The Deadline Warning: OpenAI proposed a November 12, 2026 shutoff date, but access could easily end sooner.
- Proprietary Alternatives: Codex, Claude Code, Google Anti-Gravity, Windsurf, GitHub Copilot, and Microsoft IntelliCode.
- Open-Source Alternatives: OpenCode, Hermes Agent, and OpenClaude.

📝 OpenAI's Announcement: https://openai.com/index/our-decision-on-cursor-following-its-acquisition-by-spacex/

🆓 Free ChatGPT Email Course → https://thoughtsbrewing.com/en-us/chatgpt-kickstarter-email-course?utm_source=youtube

🌟 REQUEST A VIDEO → https://thoughtsbrewing.com/en-us/youtube-video-request-page?utm_source=youtube

❓ ASK A QUESTION → https://thoughtsbrewing.com/en-us/ask-us-anything-business-tech?utm_source=youtube



▶️ Watch Next → ChatGPT Codex on Mobile: https://youtu.be/EKLOVdiUMuM?si=lbDcU_wxv876DHtg

➡️ BLOG: https://thoughtsbrewing.com/en-us/blog-subscription?utm_source=youtube

➡️ SUBSCRIBE: https://www.youtube.com/

https://www.youtube.com/watch?v=U0sDlg3pbLI

https://www.youtube.com/watch?v=U0sDlg3pbLI

Usage Limits In Gemini NotebookGemini Notebook has replaced its daily artifact limits with five-hour and weekly usage li...
09/03/2026

Usage Limits In Gemini Notebook

Gemini Notebook has replaced its daily artifact limits with five-hour and weekly usage limits. If you regularly create quizzes, slide decks, videos, flashcards, or other artifacts, your workflow may need an adjustment.

I'll explain how the new Gemini Notebook usage limits work, where to check them, and what Generate later does when you run out.

Key findings and workflow steps covered:
- The Shift to Compute Limits: Daily caps per artifact (like flashcards or quizzes) are replaced by dynamic 5-hour rolling windows and weekly account quotas.
- Tier Multipliers: Base standard limits apply to free plans, while Plus (2x), Pro (4x), and Ultra (5x or 20x) scale relative to an undefined standard baseline.
- How to Check Quota Resets: Navigate to Settings → Usage inside Gemini Notebook to view active percentage meters and exact clock reset times (I couldn't demo this in the video since the change hadn't rolled out yet).
- Generate Later Queueing: Users reaching limits can queue generation of artifacts to start later.
- Platform Restrictions: Generate Later functions exclusively on the web interface, not on mobile apps.

Current plan multipliers:
- No plan: Standard limits
- AI Plus: 2x standard limits
- AI Pro: 4x standard limits
- AI Ultra: 5x or 20x the AI Pro limit, depending on the subscription

Google has not published a specific numeric value for standard limits. Usage also varies based on prompt complexity, chat length, sources, models, and the features you use.

Generate later does not currently appear to be a scheduling tool where you choose a date and time. When you are out of usage, it delays the generation until capacity becomes available and notifies you when the artifact is ready.

📝 Google Documentation: https://support.google.com/gemininotebook/answer/17670842?hl=en&co=GENIE.Platform%3DDesktop&oco=1

✨ Join the NotebookLM (Gemini Notebook) Weekend Masterclass:
https://maven.com/thoughts-brewing-llc/learn-notebooklm-in-a-weekend-2-cohort

🌟 REQUEST A VIDEO → https://thoughtsbrewing.com/en-us/youtube-video-request-page?utm_source=youtube

❓ ASK A QUESTION → https://thoughtsbrewing.com/en-us/ask-us-anything-business-tech?utm_source=youtube



▶️ WATCH NEXT: 'How To Remove Watermarks in Gemini Notebook' → https://youtu.be/vL7kFtB7L0g?si=fs4dQG1q8k3KeqJh

➡️ BLOG: https://thoughtsbrewing.com/en-us/blog-subscription?utm_source=youtube

➡️ SUBSCRIBE: https://www.youtube.com/

https://www.youtube.com/watch?v=WiBfU5ecqUk

https://www.youtube.com/watch?v=WiBfU5ecqUk

Address

205 Van Buren Street, Suite 120, PMB 122
Herndon, VA
20170

Opening Hours

Monday 11am - 6pm
Tuesday 11am - 6pm
Wednesday 11am - 6pm
Thursday 11am - 6pm
Friday 11am - 6pm
Saturday 11am - 6pm
Sunday 11am - 6pm

Telephone

+17032969912

Website

,

Alerts

Be the first to know and let us send you an email when Thoughts Brewing, LLC posts news and promotions. Your email address will not be used for any other purpose, and you can unsubscribe at any time.

Contact The Business

Send a message to Thoughts Brewing, LLC:

Shortcuts

Share

Category