TanStack Start is the only framework with isomorphic loaders, and data-loading (TanStack Query) integrated with SSR, including streaming Fine-grained data loading & invalidation baked in, with SSR / Streaming No other solution makes sense and AI doesn't change that Incidentally the only other framework that comes close is SvelteKit. They have isomorphic loaders. Just missing a TanStack Query data loading-equivalent, with SSR/Streaming integration. If someone could convince the maintainers supporting this for grownup web apps is actually valuable they could match TanStack's functionality 👀

I am once again trying Paper and once again I will tell you this is truly an example of how not to do onboarding. I mean this as constructive criticism, but hopefully everyone can learn a thing or two as this is an important investment you can make in your own products and it is _entirely in your control_. 1) for starters, there's basically no actual onboarding 2) there's a small widget to setup MCP, which I hear you basically must use to get value out of it 3) you click it, you have to install a desktop app - ok fine odd, its 2026, but whatever 4) there's then once again no onboarding, its just the web view wrapped in a desktop app 5) click a new tiny widget in the corner and get sent to docs 6) docs tell you to click a button that doesnt exist 7) be willing enough at this point to continue, create a new document or click into one, then you'll find a buried connect button (or the same button that tricked you previously) and you can finally register the MCP there are so many ways you could improve upon this, but i really hope folks take this seriously. it doesnt matter how good your product is if you dont make it easy for new customers to use it, and thats more true now than ever with the market expanding sorry this is ranty but i really hope people consider this stuff

📦 Chrome 154 - Responsive iframe resizing 🤯 Letting an <iframe> resize based on the size of its embedded document Haven't all widget/extension authors dreamed of this for years? 😆 Instead of using postMessage({resize}) bram.us/2026/09/23/responsiv…

This is an extremely good watch. The things that felt novel/interesting to me: 1. Lock down your agents Humans tend to like 'sharp knife' abstractions - that are powerful, but you can cut yourself if your use them wrong. Lauren says agents perform much better in extremely locked-down environments. Abstractions are designed so they can't screw up, and lint rules enforce it. They built a whole internal framework (Dune) to keep the agent on track. That helps optimise agents that don't have a large context window to work productively in your codebase. 2. Create verification infrastructure To trust the results of any agent, you either need to sit and watch it OR have it provide evidence of its improvement. This has always made sense to me, but Lauren really pushes it hard here: - Invest in custom CLI's that let the agent drive the app and measure its performance - Make the app "factory ready" from the get-go - i.e. deployable to an environment where the agent can mess about with it 3. Feature Maps Lauren's software factory (what she calls an 'outer loop') often requires the agent to break down vague bug reports from users and to turn those into potential fixes. To aid that, they built a 'feature map' of all the main features in their application, which describe exactly how the app is supposed to function. This has become essential for helping the agent navigate the codebase, and figure out quickly how things are supposed to work. It's maintained along with the codebase, and kept in sync via automations. This is the kind of documentation I usually warn against. It goes stale quickly and can confuse agents if it's not kept up to date. But Lauren's team are using it as critical navigation infrastructure, and it makes it possible for agents to explore faster and better - even on a large codebase. So it sounds like navigation docs like this are worth it if they enable new behavior. Banger talk - watch the whole thing on 2x.

Muse, Instinct, OpenClaw, Claude Code… All successful agents have 3 key components: 🧠 Brain → model, harness (logic) 👐 Hands → tools, computer, browser 🗃️ Files → memories, skills, repos The 'easy' way is to throw all these in 1 stateful computer (a Mac Mini) Like, you run 𝚌𝚕𝚊𝚞𝚍𝚎 or 𝚏𝚡 in your mac, you keep it running all day with 𝚌𝚊𝚏𝚏𝚎𝚒𝚗𝚊𝚝𝚎, it has storage, and CLIs and apps installed. But if you want to cost-efficiently run agents in the cloud, you actually start breaking down these parts. 🧠 The harness can run in Fluid compute. To make it reliable across restarts, rollouts, crashes, you make its event log durable using Workflow. 👐 The hands can be a dedicated browser fleet like Browserbase/Kernel, a computer like Sandbox, and even more efficient lightweight tools like just-bash. 🗃️ 🆕 What was missing was a way to also decouple storage. Imagine you want to run a memory consolidation cron job every night ("dreaming"). You can read/write to the files directly without 'booting up' the agent's full computer. Today we're introducing the perfect companion to Sandbox: Drives. We shipped the computer for agents, now we're giving you the 'external disk' you can attach at will. It's early, and we'll be expanding capabilities here quickly. Btw, breaking apart the agent into these independent parts not only optimizes costs in a big way, it also *massively* improves security and auditability. I'd argue you can't even run a secure agent otherwise!

Introducing Rollouts. Rollouts write a monitoring plan, then watch changes as they deploy. Deployments are verified, so regressions are caught before users see them.

i always keep two versions of Codex. AMA

Hot take: this is what pacing looks like. None of today's releases were Astra or Fable tier. This is intentional. The point of "pacing" isn't to stop iteration and improvement. The goal is to prevent the development bigger models from spiraling out of control. Opus and Sol class models are a great place for our focus to go right now. Lots of opportunity for real wins without as much risk :)

who designed Github dashboard that's (almost) entirely useless 🤯

grok 4.7 just refactored my entire codebase in one call 67 tool invocations. 1M+ new lines. 24 brand new files it modularized everything. broke up monoliths. cleaned up spaghetti none of it worked but boy was it beautiful

I built a little sandboard in @threejs and webgpu to play with, and yes, on mobile multitouch is supported still a first draft, but i really like the feel of it You can play at: sand.scottsun.io Source: github.com/scottstts/Sandboa…

you will use opus 5.5 more than fable 5.1 opus 5.5 is coming in at $4/$20 per 1M tokens. that's cheaper than opus 5 at $5/$25, and massively cheaper than fable 5 at $10/$50. if opus 5.5 actually gets close to fable 5 level capability at this price, this could be a game changer for anthropic. because fable is capped at 50% of weekly usage even on max, and on pro it requires usage credits, while opus is part of the normal plan limits. and opus usage will last much longer than fable, especially on max plans because opus 5.5 could also be more token efficient than opus 5.

The Death of the Meat Proxy is here Welcome to Multiplayer Mode from OpenClaw @jlehman_ and @heyneighbor sat down for a deep dive into this new set of features and how the OpenClaw maintainers use them everyday 00:01 Meet Josh 00:46 The “meat proxy” problem 03:25 Why not a Slack bot? 07:03 Live shared-session demo 08:55 UI mockups + @ mentions 11:31 Permissions + security 13:20 Team visibility + handoffs 15:06 Prompt requests 18:17 Team adoption 21:30 Shared dashboards 22:09 Build a content dashboard 25:41 Organizing work + future feedback 27:45 The multi-claw idea 30:07 Could it replace Slack? 33:26 Coordination over throughput

Agent: *screenshots the page* Agent: *scrolls* Agent: *screenshots again* Agent: *clicks the wrong button* Agent: *screenshots again* Page with WebMCP: hi, here are the 4 things you can do here, with descriptions Agent: oh thank god

Turborepo 2.11 • Native Rust, Python, and Golang (Experimental) • 4x faster startup • Zero known issues • 𝚍𝚎𝚟𝙴𝚗𝚐𝚒𝚗𝚎𝚜.𝚙𝚊𝚌𝚔𝚊𝚐𝚎𝙼𝚊𝚗𝚊𝚐𝚎𝚛 support • nub and aube support • Production pruning for smaller Docker images turborepo.dev/blog/2-11

We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.

I got access to Jev earlier today (thank you @hackgoofer). I have run ~5,000 requests so far, (which cost me around $2!), across classification, model routing, intent, steering, and many other things. tl;dr, Jev enables a new intelligent decision-making primitive, separate from deterministic code and LLM calls. This allows a class of decision-making that was neither suited to dumb, unintelligent code, nor to slow, expensive LLMs. It is super fast and cheap, and I think I will likely end up making a few Jev calls to every LLM call I make in my product. I think probably any company using LLM requests today can probably add a Jev call pre and/or post LLM calls to quite literally make their product much better for free, and have better tool calling behavior in many cases. I happened to have a personal benchmark for this as I’d been working on a ton of proactivity and classification tasks. I have been using the deepseek flash and more recently gpt 5.6 luna family of models as reasonably smart classifiers with low latency. Think questions like: - Did this conversation output contradict something they’ve mentioned before? - Should we send a followup message to this user based on our rules? - It’s been a few seconds of silence. Should we proactively send a message? In the past, I’ve been forced to write a bunch of what I call decision chains, mostly because an LLM classification call is very expensive in TIME (avg 4s), and less importantly can cost quite a bit if run on every message. Imagine a normal chat app. If you added 4s to every response to figure out if the response is good before sending it out, that ends up being pretty bad. So instead, I usually have to write some code that is a crude heuristic that runs quickly and decides whether to run the classifier. Obviously this sucks because you call the classifier many times that you don’t want to, which makes your p95 bad, and you also miss cases with the heuristic, and you also have to manage all of these weird chains. With Jev, it’s cheap enough, and fast enough (p50 ~150ms, p95 ~350ms in my testing!) that you can easily run it every turn. Heck you can reasonably run it before generation AND post generation, for any application that isn’t realtime voice, and still feel snappy. But this is just one use case. Think: smarter model routing, better context packing, better responses, better observability for intent/tags/safety, smarter retries and so much more. By simply thinking about the inputs and outcomes you want to enforce, you can use Jev to supercharge most model calls and reduce bad user outcomes. The more “quirks” a model has, the more valuable it ends up being. It’s a bit weird and unintuitive using Jev. Generally, you want to decrease the # of questions you ask a classifier, or it makes more mistakes. In fact, you might want to ask your questions kind of in a compound way, because the reasoning happens in a shared scratchpad of sorts. Adding questions muddies the scratchpad and makes it take longer. With Jev, you feel incentivized to go the other way, to formulate your query as a set of independent questions. It doesn’t feel like adding more questions decreases your performance on others. You can go a bit deeper to improve tool calls. Many model tools are things like turning on settings, or other things. You can easily improve models that are not very good at tool calling with Jev, by simply figuring out when to run them. You can do a pre-LLM call to figure out when to unfurl different tool definitions, in order to make your main LLM run better, you could run a background task with Jev + another LLM to reduce tool and context burden on your main LLM, and free it to be responsive. I’ve only scratched the surface of my testing but very excited!