Introducing frame.md, a spec built for videos & motion
design.md kept your brand consistent across screens
but when applied to videos, agents translated it back into webpages and decks
frame.md teaches your agents how to make branded video
turn your design.md into frame.md ↓
new herdr update!
agent session restore is now enabled by default for supported integrations.
after a herdr restart or update, supported agents can automatically resume their native sessions right where they left off.
also introducing release channels. a small thread:
Introducing Impeccable 3.5, the best way to design in production: iterate on real UI with your AI agent, in the codebase you actually ship.
Turns out many popular design skills, including Impeccable and Anthropic's frontend-design, weren't actually very good at...design (the workflow was valuable, but the output didn't magically make LLMs like GPT great designers). We measured it across thousands of generations: 74% of pages used the cream AI-default background, 76% reached for extreme letter-spacing, 90%+ failed the contrast floor.
So we started fixing slop systematically, specific to each model. The skill now compiles rules for the exact defects each model makes, instead of shipping one generic file to everyone. The biggest jump is in GPT-5.5 and Codex.
Also new:
◆ It now knows the difference between a new project and an existing one. Existing codebase, it reads your design system and preserves your identity. Greenfield, it seeds a fresh palette from 129 hand-curated anchors so every cold start doesn't drift to the same safe colors.
◆ Live Mode is now in beta, and works at two scales. Type a direction into the new Steer bar, or speak it, and the agent reads the whole page and edits it in place. Or pick a single element, steer it with a sub-command, live-edit any copy, and accept the variant straight back to source. Insert mode scaffolds brand-new elements between the ones already there. Recovery survives HMR, hidden heroes, and dev-tool overlays.
◆ A rebuilt anti-pattern detector. Torn off jsdom and onto a real CSS cascade resolver: roughly 20x faster, dependency-free, and now small enough to run inline inside the skill, not just the CLI and extension. 14 new rules, 41 total.
◆ The skill keeps itself current, checking once a day and offering to update. Plus /impeccable init and a bare /impeccable that reads your repo and tells you the next move.
Free, open source. Claude Code, Codex, Cursor, and more.
impeccable.style
you don't need accounts, credits, docker envs, or your ide cosplaying as a terminal.
you need one binary that speaks ssh.
herdr --remote you@host
your terminal is not a saas. try herdr!
diffshub[dot]com
Take any public diff from GitHub and virtualize it nearly instantly, no matter how large, with DiffsHub. Built to show off our brand new CodeView component.
To try it out, replace `github` with `diffshub` in your address bar.
Introducing Hallmark!
An open source design skill to make beautiful UIs and landing pages by default.
Works in Claude Code, Cursor, and Codex.
npx skills add nutlope/hallmark
‼️🚨 BREAKING: GitHub has been compromised by TeamPCP. GitHub has confirmed the internal breach. A poisoned VS Code extension on an employee device exfiltrated ~3,800 internal repositories.
TeamPCP is already selling the data on a cybercrime forum.
1/
Keep running claude -p on your Claude Code subscription after June 15.
A 200-line bash wrapper pipes your prompt into the Claude Code session you already have open. The call rides your subscription, not the new Agent SDK credit bucket.
Looks like claude -p. Runs on the plan you already pay for.
How it works 👇
Karpathy threw a grenade at every senior engineer who still treats LLMs as a toy.
his actual words: the worst thing an expert can do right now is reject them.
most experts read it as a threat, but it's advice.
his framing:
> the gap between "AI tools are bad" and "AI tools are useful when used right" is professional discipline, not capability
> agents have cognitive deficits. they fail in ways nothing in the training set anticipated
> the experts who reject LLMs lose to experts who learn to wrangle them
> "models have so many cognitive deficits. but you can route around them"
routing around the deficits is what CLAUDE.md was invented for.
Karpathy himself wrote 4 rules. across 30 codebases they took my Claude error rate from 41% down to 11%. solid drop.
but his rules pre-date the slop era going public. I bolted on 8 more, tuned to the failure modes that surfaced after January. got it down to 3%.
a CLAUDE.md does not raise Claude's IQ. it lowers his slop floor. that is the entire game.
open the article underneath.
the model is not the bottleneck. your config is.
For 100% agent-written frontends, I keep coming back to this:
Maybe we don't start with a frontend framework
Maybe we start with an index.html, browser primitives, Web Components for reusable UI and a strict convention for how agents route, render, mutate state and handle data
This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc.
More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage:
1) raw text (hard/effortful to read)
2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default
3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default
...4,5,6,...
n) interactive neural videos/simulations
Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral x.com/zan2434/status…
There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen.
TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.
A flow I just tried and LOVED:
1. /grill-with-docs, talking about a new bit of UI
2. Asks me a question I can't answer unless I prototype
3. /prototype
4. Iterate on the prototype, burning tokens freely until we get a good spot
5. /rewind to the question, and select 'summarize' (Claude Code feature), saying 'summarize what we learned from prototyping'
6. Continue the grilling session, retaining the prototype
Smoooooooth
3K Followers 10K Followingonly private elite here !! I will mainly talk about crypt market, stocks market,price action analysis etc. ONLY FOR A FEW PEOPLE MAIN ACCOUNT @dangambardello
266 Followers 3K Followingreading = knowledge。
Fitness + Golf = Health & Perfect Body。
I like delicious food and beautiful scenery, and hope to travel to every corner of the world。
249 Followers 2K FollowingBefore doing anything, you must have the right direction, and acting blindly will only lead to failure. The right direction is the premise of success. Without o
9K Followers 299 FollowingSecurity researcher and reverse engineer. Interested in Windows kernel development, low-level programming, static program analysis and cryptography.
139K Followers 186 FollowingThe build tool for the web. It's pronounced /vit/ like Veet! | brought to you by @voidzerodev and the community - join us on Discord: https://t.co/Cs7aMLlLwD
69K Followers 18 FollowingExploring what AI actually is. Building @shapeworkspace, prev @standardnotes. Talking at https://t.co/814DpgwSzr and https://t.co/vlHyF3gEjn.
97K Followers 987 FollowingDirector of Developer Experience @togethercompute. Building open source AI apps (https://t.co/f8hbvXOFaN, https://t.co/SmHisRTtnp, https://t.co/H3xCBJvVMu, https://t.co/sed83e9OUA).
534K Followers 2K FollowingPolyagentmorous ClawFather. Came back from retirement to mess with AI and help a lobster take over the world.
@OpenClaw🦞 + @OpenAI
5K Followers 2K FollowingHusband to an amazing wife, father to 2 wonderful kids.
All in on AI: https://t.co/zimxWCA6ky
Founder of https://t.co/kYTwOP48Rt
1.1M Followers 172 FollowingNobel Laureate. Co-Founder & CEO @GoogleDeepMind - working on AGI. Solving disease @IsomorphicLabs. Trying to understand the fundamental nature of reality.
256K Followers 178 FollowingCo-founder of Thinking Machines Lab @thinkymachines; Ex-VP, AI Safety & robotics, applied research @OpenAI; Author of Lil'Log
460K Followers 1K FollowingML/AI research engineer. Ex stats professor.
Author of "Build a Large Language Model From Scratch" (https://t.co/O8LAAMRzzW) & reasoning (https://t.co/5TueQKx2Fk)
1.6M Followers 1K FollowingCo-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCs
1.2M Followers 788 FollowingProfessor at NYU & Executive Chairman at AMI Labs.
Ex-Chief AI Scientist at Meta.
Researcher in AI, Machine Learning, Robotics, etc.
ACM Turing Award Laureate.
6K Followers 18 FollowingOwn your AI. Agents that remember, execute code in isolated VMs, and stay reachable from anywhere -- all on your Mac. Any model. No cloud required. Open source.