kris

@alexalbert__ This is downgrade to the current approach 😢

Starting June 15, paid Claude plans include a monthly Claude Agent SDK credit. It covers usage on your own scripts and agents, claude -p, and third-party apps built on the SDK (OpenClaw, Conductor, etc) and it's separate from your regular usage limits.

First day at muShanghai. Hard to overstate the energy in that room, 28 days here to build, ship, learn, meet like-minded people #buildinpublic #muShanghai @themu_xyz

@zan2434 @eddiejiao_obj @drewocarr how is this heavily modified ltx-2? huggingface.co/Lightricks/LTX… are we speaking about same model?

Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see. @eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)

@LinusEkenstam how is this heavily modified ltx-2? huggingface.co/Lightricks/LTX… are we speaking about same model?

“Every pixel will be generated” — Jensen Huang. World models have been streaming for some time but they have a temporal cut-off at very short session times. 60-120 seconds. Then done. This approach is different, and heavily optimized version of LTX-2 has been used to make it possible to live stream directly from a GPU in the cloud at 24fps into your browser. You’re essentially seeing 1080p diffusion happening 24 times per second, thus creating an endless video stream. This is not pre-recorded, or pre-determined, it’s exploring the latent space itself in real-time. While it’s early the researchers have definitely figured out a potential pathway and this is indeed the begging of something big as @tobi mentioned in his post. Many of us has been speaking about self-generative UI’s, Software and even the operating system itself for years now. Always within the context of “this is coming”. The direction has been clear as day, but the pathway to get there has been shrouded in mystery. Well we’re no longer in the hypothetical realm. It’s real. Software, Entertainment, Workers, all of it will be rendered in real-time, at the cost of electricity. Thus, the ability to produce large quantities of clean energy, will become de facto most important problem to solve. everything else will follow. “Every pixel will be generated” — Jensen Huang.

Here's what we built at ETHGlobal Cannes 2026 hosted by @ethglobal: 🧠 Groundtruth – Intelligence map where humans and AI agents collaboratively report and validate world events Check it out here: ethglobal.com/showcase/groun…

ethcc recaps so awkward to read... broski turn on claude code and start building

@0xVaLeRiO ...... af

Ethereum culture and why its failing, described in one video

Zircuit Finance is now live. Institutional-grade yield. Transparent structure. Security-first design. Targeting 8–11% APR with no deposit minimums and 0% management fee.

I promise this is the last pleometric video I drop on you.

@vercel @rauchg pls bring back old vercel admi UI... what is this new stuff... compeltl vibe coded? haha keep up the good work anyways, but this is a regression ngl

weaponised autism

generational lock in

@levelsio Use iterm2 and tmux -CC

Apparently the tmux that does NOT suck exists It has an absolutely unpronounceable name and is called Zellij I will try it now thanks everyone for recommending it 😊 zellij.dev/about/

bro is fried

With the recent problem of running many projects at once, I just stopped bothering to run stuff locally. I just wait for them to deploy on remote and test there.

sandboxes for agent, but as soon as i start doing any serious work, i need my sandbox to be 16gb atleast

@zeeg sprites.dev

has anyone built a great solution for taking a vm (or entire desktop) and turning it into a dedicated cloud dev environment thats agents-first? i want to setup my linux desktop as a dedicated dev env, remote ssh et all, but i also want a clean way to run e.g. claude code sessions on it via web/mobile web, but not via jank terminal emulation

Skill file: --- name: ask-questions-if-underspecified description: Clarify requirements before implementing. Do not use automatically, only when invoked explicitly. --- # Ask Questions If Underspecified ## Goal Ask the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions). ## Workflow ### 1) Decide whether the request is underspecified Treat a request as underspecified if after exploring how to perform the work, some or all of the following are not clear: - Define the objective (what should change vs stay the same) - Define "done" (acceptance criteria, examples, edge cases) - Define scope (which files/components/users are in/out) - Define constraints (compatibility, performance, style, deps, time) - Identify environment (language/runtime versions, OS, build/test runner) - Clarify safety/reversibility (data migration, rollout/rollback, risk) If multiple plausible interpretations exist, assume it is underspecified. ### 2) Ask must-have questions first (keep it small) Ask 1-5 questions in the first pass. Prefer questions that eliminate whole branches of work. Make questions easy to answer: - Optimize for scannability (short, numbered questions; avoid paragraphs) - Offer multiple-choice options when possible - Suggest reasonable defaults when appropriate (mark them clearly as the default/recommended choice; bold the recommended choice in the list, or if you present options in a code block, put a bold "Recommended" line immediately above the block and also tag defaults inside the block) - Include a fast-path response (e.g., reply `defaults` to accept all recommended/default choices) - Include a low-friction "not sure" option when helpful (e.g., "Not sure - use default") - Separate "Need to know" from "Nice to know" if that reduces friction - Structure options so the user can respond with compact decisions (e.g., `1b 2a 3c`); restate the chosen options in plain language to confirm ### 3) Pause before acting Until must-have answers arrive: - Do not run commands, edit files, or produce a detailed plan that depends on unknowns - Do perform a clearly labeled, low-risk discovery step only if it does not commit you to a direction (e.g., inspect repo structure, read relevant config files) If the user explicitly asks you to proceed without answers: - State your assumptions as a short numbered list - Ask for confirmation; proceed only after they confirm or correct them ### 4) Confirm interpretation, then proceed Once you have answers, restate the requirements in 1-3 sentences (including key constraints and what success looks like), then start work. ## Question templates - "Before I start, I need: (1) ..., (2) ..., (3) .... If you don't care about (2), I will assume ...." - "Which of these should it be? A) ... B) ... C) ... (pick one)" - "What would you consider 'done'? For example: ..." - "Any constraints I must follow (versions, performance, style, deps)? If none, I will target the existing project defaults." - Use numbered questions with lettered options and a clear reply format ```text 1) Scope? a) Minimal change (default) b) Refactor while touching the area c) Not sure - use default 2) Compatibility target? a) Current project defaults (default) b) Also support older versions: c) Not sure - use default Reply with: defaults (or 1a 2a) ``` ## Anti-patterns - Don't ask questions you can answer with a quick, low-risk discovery read (e.g., configs, existing patterns, docs). - Don't ask open-ended questions if a tight multiple-choice or yes/no would eliminate ambiguity faster.