Following the recently added zoom feature, we have added a BGM feature to Make Demo GIF / MP4. By adding background music to silent demo videos, you can create more engaging MP4s for your viewers.
ChatGPT and Claude are great tools, but do you ever hesitate before typing something work-related or personal into them? On the other hand, setting up a local GPU environment to run Ollama yourself is a steep barrier in terms of both effort and cost.
So I built a private LLM chat environment using Google Colab's free GPU — one that never sends conversation logs outside the instance — and packaged it into a single notebook. Run the cells from top to bottom, and it's ready to go.
Today I'm releasing Colab Mosaic Clip — an open-source tool that applies a mosaic or solid-color mask to any time range and region of a video, entirely through a GUI, and exports the result as MP4. It runs ffmpeg and Pillow on Google Colab, so everything from specifying the time range to placing mosaic regions and exporting the final file is handled inside the notebook UI.
Today I'm releasing Ollama Colab Free Server, an open-source notebook that runs Ollama on Google Colab's free GPU and makes it instantly available as a backend for Claude Code and Continue. Execute the cells top to bottom, and a publicly accessible LLM server is up within minutes.
Make Demo GIF / MP4, released earlier this month, now includes a zoom feature. When you want to draw attention to a specific interaction in a screen recording, simply dropping in a GIF or MP4 does not always communicate what matters. This update adds an optional zoom effect that smoothly magnifies any area of the video to highlight button clicks, form inputs, or other key UI moments.
Today I'm releasing Make Demo GIF / MP4, an open-source tool that converts screen recordings into GIFs or MP4s optimized for GitHub READMEs and social media. It runs FFmpeg on Google Colab, letting you merge multiple videos, tune quality, and adjust playback speed — all through a notebook UI, no command line required.
Today we are releasing Ollama Multi-Model Benchmarker, an open-source tool for evaluating local LLMs before committing to a setup. It runs multiple Ollama models sequentially on Google Colab's free T4 GPU and produces a side-by-side comparison of generation speed, responsiveness, model size, and more.
My MacBook operates smoothly, but I recently wondered, "Are there any unnecessary files or settings accumulating where I can't see them?" prompting me to perform a system health check using the Terminal.
While there were no security issues, I discovered a shocking fact regarding my storage. A single hidden folder, invisible from the standard System Settings, was consuming a massive 109GB of space.
In this article, I will share the story of how I identified the cause of this storage hog and the steps I took to recover over 100GB of free space.
Have you ever tried connecting to public WiFi at a café or hotel, only to find that the authentication screen (captive portal) takes forever to appear, or doesn't show up at all?
I frequently struggled with this issue while working remotely, feeling the stress of "not being able to start work because I can't connect to the internet." However, after some investigation, I discovered that past WiFi connection history accumulated on the device was the culprit.
Based on my personal experience, this article explains how to organize and delete unnecessary WiFi history on both Mac and iPhone. This simple maintenance can improve the speed at which the login screen appears and ensure smooth connections to public WiFi.
Regarding this issue, I have finally successfully logged in and resolved the problem. I would like to share the conclusion with those who visited this article facing similar circumstances.
Initially, I requested an investigation through Billing Support to a specialized team. However, it took considerable time to coordinate the scope of responsibility between departments (Billing Team ⇄ Technical Team). Ultimately, I was informed that the "Technical Team could not investigate as it was outside their scope," and the case was closed with a suggestion to use the official community forums.
However, immediately after the support interaction ended—approximately 7 days after the error first occurred—the situation improved after I refrained from any operations. The 2-Step Verification (2SV) process, which had previously blocked me with the "We couldn't verify it's you" error, successfully went through. I was then able to configure my security settings and log in to Google Cloud.
Based on the login history, the presumed factor for resolution is: "By refraining from login attempts for a certain period, the system's security lock was automatically lifted."