The limits on mobile Agents go beyond compute
Phone performance is already more than enough, yet an Agent can barely access anything on it: from permissions and sandboxes to app isolation, the mobile bottleneck lies beyond raw compute.
Blog / WEEKLY #003
Blog for episode 003
#003 Unpacking Jev’s new paradigm: do agents need an ultrawide?
Turning a TV remote into a voice entry point for your computer
A Bluetooth remote costing a few dozen yuan plus a small voice program written at home made for two straight days of fully voice-driven work: how a physical button changes what it feels like to give an Agent its orders.
Agent Plugin Migration Is Hard Because Capabilities Are Unequal
Moving plugins from one agent to another, format conversion is no longer the hard part; the real threshold is that each platform exposes different capabilities, and upstream keeps changing fast.
The Storage Bill After Vibe Coding
Projects, caches, system images, and raw video fill the drive together. The question is not only how much capacity to buy, but which data is worth keeping, on which tier, and whether it can be found again when needed.
From a Blank Chat Box to the First Useful Task
Personal agents have lowered the bar to "being able to chat", but what decides retention is not the chatting — it is the first useful task: scenario entry points, an execution process you can see, and a conversation the user never has to manage.
Give the Agent a Computer That Stays On
Whether logins, software, and files survive after a task ends is splitting agent execution environments into two generations. Persistent environments make scheduled tasks and long-running collaboration possible — and push cost and multi-machine management onto the user.
Story, authorship, and audience in AI video
Once visuals can generate in real time and shots can be produced in bulk, the real gap moves from "does it look real" to "does the story hold up." Authorship, serialization, and audience response decide how far this kind of content can go.
After the Software Is Built, There Is Still Distribution
Once the barrier to creation has fallen so low, how a work actually reaches its audience becomes the new bottleneck. Distribution does not happen automatically just because something is well made; it needs to be designed and validated in its own right.
A product promo video made with code, images, and music
A promo video can be composed from a musical score, vector animation, and a handful of generated images. Code handles the orchestration, image models supply the key assets, and whether it looks good still has to be judged by eye.
Local Inference Is Worth More Than the Money It Saves
Buying an always-on machine does not mean you have to run models on it. This article pulls apart three needs — local inference, an always-on device, and privacy control — and judges when each is worth adding to your own setup.
What Is Jev For? Give the Model the Judgment, Give the Program the Result
Filtering memories, tagging contacts, extracting to-dos: when a task calls for a score or a verdict, how does a model actually fit into a workflow?
Why Using an Agent Makes You Want an Ultrawide Display
With an agent in the browser, web pages, conversations, and tasks start competing for screen space. A wider display can hold them; a workspace still has to organize them.
Speech recognition is already accurate — so why is voice input still clunky?
Accuracy is no longer the main bottleneck for voice input. What decides whether people stick with it is a set of unglamorous frictions: vocabularies, real-time display, how aggressively the text gets cleaned up, and system permissions.
Icons, book illustrations, and publishing: what AI-generated vector graphics are for
An icon a few dozen pixels wide, an illustration headed to print, a logo blown up on a giant screen — none of these need a pixel image; they need vector graphics that can keep being edited.
Evaluating Models with Real Tasks
Beyond leaderboard scores, a model's real performance depends on the runtime framework, the type of task, and how fresh the test data is. Using concrete tasks as examples, this article explains how to read evaluation results — and how to use them.