Codex's Agents Dashboard turns a pile of terminal tabs into one queue

OpenAI's Codex CLI has quietly grown the missing management layer for people who run several coding agents at once — an Agents Dashboard that groups every active session by project and state, plus a companion command that lets you message any session without opening it. A hands-on from developer and AI researcher Vladislav Guzey walks through the workflow, and it reads less like a feature tour than a small thesis about where developer tools are heading: when the work is automated but supervising the work isn't, the interface that wins is the one that answers "where is my attention needed?"

The dashboard's core move is triage. Sessions sort into states — blocked on you, working, ready for review — which replaces the old habit of scanning terminal tabs for whichever output changed most recently. The deeper fix is decoupling communication from navigation: a second terminal command accepts a task name or session ID plus a message (and even image attachments for visual bugs), so a script or a colleague can add context to a running agent mid-flight without taking over its screen. Guzey's honest caveat is worth keeping: none of this makes parallel work free — more agents still mean more decisions to make and more output to review. What it removes is pure navigation cost.

Our take: this is the same "agents need an operating layer" shift we've tracked across the ecosystem — we mapped the trend when agent tooling went desktop-native — but it hits differently coming from inside a mainstream coding agent rather than the open-source harness scene. When the primary interface becomes a queue of tasks competing for your attention instead of one conversation, the developer's job description quietly changes from writer of code to reviewer of queues. GitHub's issue tracker shows real usage forming around both features — including requests to extend the dashboard itself.

What to watch: whether Anthropic and Google's coding CLIs copy the state-triage model within weeks, and whether "agent fleet dashboards" become a standard job category in dev tools the way CI dashboards did.

Running three coding agents before lunch? Tell us in the comments whether a queue view would change how you supervise them.

Sources: openai/codex on GitHub

Kling 4.0 goes live with 30-second native video at 10-bit HDR

Kuaishou's Kling AI has spent two years becoming the video model people actually finish projects with. Its new flagship, Kling 4.0, went fully live on October 15 — and this round is less about prettier frames than about the two things that make a generated shot usable in a real edit: length and control. Kling 4.0 generates up to 30 seconds in a single native pass, outputs 10-bit HDR at 4K, 1080p and 21:9, and takes up to 15 reference assets in one task. That budget splits across ten images, fi

Brain organoids classified Braille at 83% — in a trio, not alone

Two stories today: human brain tissue on a chip decoded a tactile signal, and the data-centre company behind some of the largest AI contracts in Europe turns out to be six months behind on its flagship site. Human forebrain organoids grown on a microelectrode array classified Braille letters with 61 percent accuracy on their own and 83 percent when the responses of three organoids were combined, in a peer-reviewed study from the University of Bristol. The team took event-based tactile readings

Suleyman says Microsoft's base model beat OpenAI's on a quarter compute

Microsoft finished pre-training its biggest in-house model yet — then used it to make a point about the company it bankrolls. Microsoft AI completed pre-training of MAI-Base-2, a mixture-of-experts foundation model with 80 billion active and 2.8 trillion total parameters, and says the recipe is 4.2–12.3x more pre-training FLOPs-efficient than DeepSeek-V4-Pro-Base. The run itself is the number worth keeping: 16,000 Nvidia GB200 GPUs for 38 days across August and September, at 21% average model

Amazon's new Bee devices listen all day — for $11.99 a month

Amazon turned its always-listening Bee line into a two-device family on Thursday, and NVIDIA opened a 2.8-trillion-token Indic corpus recipe. The connecting thread: both are bets that the next AI money is in memory — yours, or your model's. Amazon put two new always-listening devices on sale, and both now lead to a subscription. Bee Frontier, the next-generation wristband that also clips to clothing, ships now at $74.99 in Onyx, Lavender and Sage — up from the $50 predecessor — with seven-day

Read more

Kling 4.0 goes live with 30-second native video at 10-bit HDR

Brain organoids classified Braille at 83% — in a trio, not alone

Suleyman says Microsoft's base model beat OpenAI's on a quarter compute

Amazon's new Bee devices listen all day — for $11.99 a month