NEXT TOKEN / BLOG
AI products, technology, and first-hand experience. Topics worth expanding, details worth keeping.
Browse by episode Subscribe via RSSNo articles found. Try other keywords or episodes.
Flash off-the-shelf firmware, rework the interface into Chinese, bolt on a voice output path, and a small desktop dev board goes from toy to an assistant terminal that gets used every day; as for taking over the whole house, that is still just a vision.
Read moreRecording by itself produces no value; review does. When watch, training, and health data are automatically compiled into a weekly report, continuous logging and scheduled review finally connect into a closed loop.
Read morePhone 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.
Read moreAs the cost of generating content approaches zero, what becomes scarce is no longer output but a reason for people to keep coming back. Works, a consistent set of preferences, and feedback from real users are where trust comes from.
Read moreA 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.
Read moreSwitching to open-source or self-trained models to cut costs only works once the business is stable and quality can be verified independently. This article discusses the conditions under which that decision should be made.
Read moreMoving 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.
Read moreAs models start acting on intent rather than literal instructions, the center of gravity in collaboration shifts from prescribing every step to stating goals and acceptance criteria. Which constraints still need to be written down explicitly is worth discussing separately.
Read moreThe rendered layer and the source are two separate states, and that is the root of a whole class of stubborn problems in WYSIWYG editors. One migration from Milkdown to CodeMirror 6 shows where the openings for modifying an existing system lie, and who owns the responsibility for acceptance.
Read moreA game script and worldbuilding document that sat on a hard drive for a year became a playable experience prototype over this holiday. Which stretch of the road from idea to playable got compressed, and which judgments remain in human hands.
Read moreHow open a piece of software is to agents depends on whether it exposes capability interfaces, whether results can be inspected, and whether the host can carry the execution. From 3D modeling to editing tools, this line of judgment is taking shape.
Read moreProjects, 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.
Read moreLooking things up, placing orders, paying, making promises to others — delegating to an agent involves different tiers of authority. The difference between an assistant and a digital alter ego hides in every single "should I ask first?"
Read moreWhichever service holds your memory is the one you have to ask for it back when you switch tools. A file system you own lets personal context move between multiple agents — but sync, backup, and multimodal material are still unfinished roads.
Read moreThe ceiling of what a life assistant can do often is not the model — it is where the information it can see lives: the same school notice is readily at hand in email, but hard to reach inside a group chat.
Read morePersonal 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.
Read moreResale discounts on model APIs keep thinning; profit has to be earned by turning tokens into usable services. This article maps the cost structure of AI applications and the opportunity in "experience arbitrage."
Read moreWhether 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.
Read moreWhen content serves both human readers and agents, the open web and a subscribable entry point take on new value. A gap discovered while assembling AI sources shows this still has to be done deliberately on the Chinese internet.
Read moreOnce 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.
Read moreOnce 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.
Read moreModels keep getting faster and code keeps getting cheaper to write, but the speed at which software reaches users has not automatically caught up. Between individual output and organizational delivery sits a whole set of steps that have yet to be redesigned.
Read moreA 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.
Read moreRemembering a fact, tracking a goal, and completing a task are three different states. When an assistant cannot tell them apart, it keeps nagging about matters that ended long ago.
Read moreWhen an agent needs to connect to a new service, should the user tap once to authorize, or go apply for an API key themselves? The difference in that one small step separates two generations of product design.
Read moreBuying 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.
Read moreFiltering 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?
Read moreWith 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.
Read moreAccuracy 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.
Read moreAn 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.
Read moreBeyond 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.
Read moreThe same idea—"have AI make a game"—can cost wildly different amounts and produce wildly different results depending on how the task is expressed. One attempt at building a planet shows how engineering expression determines the size of the task.
Read moreRecording, editing, platform uploads, and the website transcript used to be separate manual chores. When the steps beyond writing code can also be handed to an agent, the most human-intensive part of the pipeline shifts from operating to deciding.
Read moreThe basic execution capabilities of an agent are being taken over by managed services and mature frameworks. The question an application team has to answer is not whether to build in-house, but which responsibilities to hand over and which to keep.
Read moreAfter the prompts are tuned and the pipeline works, model behavior can quietly shift one day. This article breaks the "models got dumber" debate into separate questions: versions, routing, pricing, and compatibility.
Read moreOnce model prices fall, the first thing to change is not the capability rankings but which tasks become worth handing to a model. This article maps how cheap models expand usage, and how they divide work with frontier models.
Read moreNext Token publishes articles on AI products, technology, and first-hand experience, drawing on its conversations and independent research. Each article links to its source episodes and supporting references.
