The rage bait farming on onchain #zaps is wild. There is no reasonable way to justify these imo 🤣

Gemini 3.5 Flash is now available! Use it for fast multimodal chat, coding, visual Q&A, data extraction, and long-context work with up to a 1M-token input window and 64k output tokens. For harder reasoning tasks, try Gemini 3.5 Flash Thinking. 👏 https://nano-gpt.com/subscription/k7AXDwBb #ai #llm #gemini

PSA: Repos for WasmBox & WasmBox Registry are now mirrored on nostr! > Flatpak-style launcher for sandboxed WebAssembly tools. Single binary, local-first, no accounts, no telemetry. > Built for agents and humans alike — every tool ships with a machine-readable skill file so agents can discover, understand, and invoke tools without guessing. CLI:

gitworkshop - Decentralized Git

Decentralized GitHub alternative over Nostr

Registry:

gitworkshop - Decentralized Git

Decentralized GitHub alternative over Nostr

#wasmbox #wasm #rust #nostr #git

# Markdown In, HTML Out *Why your specs are unread and what to do about it* A few weeks ago Thariq Shihipar from the Claude Code team gave a talk that named something I had been doing badly. The thesis fits in one sentence: **Markdown is the right format for instructing an LLM. It is the wrong format for whatever the LLM produces for you to read.** `CLAUDE.md`, `AGENTS.md`, `SKILL.md` are markdown for a reason. Terse. Easy to grep. Easy to keep token-cheap. The model reads them well. But the *output* you ask the model for, a plan, a PRD, an architecture writeup, a status doc, is read by a human, not a model. And past a hundred lines, nobody reads markdown. It is a wall of text. There are no anchors, no visual hierarchy beyond ATX headings, no way to collapse a section, no embedded mockup, no working example, no diagram, no diff highlight. Open one of your 1k-line specs and ask honestly when you last scrolled past line 200. The fix is to have the model emit HTML instead. > On the open-model side, nano-gpt is the cheapest way to try GLM, Qwen, Kimi, and MiniMax through one API key before committing to any of them. Pay per token, no monthly minimum. [Check it out!](https://nano-gpt.com/subscription/k7AXDwBb) ## What HTML buys you A single self-contained `.html` file rendered offline gives you: - visual hierarchy that scales past 100 lines - inline SVG diagrams that diff in git - collapsibles, tabs, copy buttons where they help - working examples instead of fenced code blocks - a shareable URL the moment you push to a static host - a real design surface that signals you cared enough to make it readable The same artifact serves you (the author), your team (review), your stakeholders (sales, regulators, investors), and your future agent (next session context). One file, four audiences. ## The pattern ``` project/ ├── src/ # code ├── dist/ # generated HTML artifacts │ ├── index.html # landing, links, summary │ ├── plan.html # scope, milestones, risks │ ├── architecture.html # components, data flow, threats │ ├── design.html # tokens, type, components │ └── status.html # blockers, next steps ├── AGENTS.md # token-compressed agent directives └── html.prompt # paste-ready agent spec for the artifact set ``` Markdown for the instructions. HTML for the outputs. The agent does the translation. ## html.prompt I packaged this as a paste-ready file you can drop in any project. It tells the agent what artifacts to build, how to constrain them, and what triggers regeneration. ```sh curl -O

gitworkshop - Decentralized Git

Decentralized GitHub alternative over Nostr

claude "read html.prompt, generate dist/ artifact set for this project" # or opencode "read html.prompt, generate dist/ artifact set for this project" ``` Constraints baked in: - single `.html` per artifact, no shared assets, no build step - embedded CSS, no CDN, no webfont, no analytics, no telemetry - renders offline, deploys as static site anywhere - `<!-- manual:keep -->` blocks preserved across regens - gaps marked `<mark>TODO</mark>`, never fabricated - inline SVG only for diagrams, no raster, no third-party logos - WCAG AA contrast, semantic HTML, dark default with light toggle Repo: [gitworkshop.dev/ngmi@zaps.lol/relay.ngit.dev/dotprompt](

gitworkshop - Decentralized Git

Decentralized GitHub alternative over Nostr

MIT. One file. Fork and adapt. ## Where this lands The `dist/` directory becomes the canonical spec of the project. It commits with the code. It deploys as a static site to GitHub Pages, Cloudflare, IPFS, or tangled.org. It is what you link to when someone asks for the PRD. For me this replaced three patterns at once: 1. Long markdown PRDs nobody reads past the TOC 2. Stale Notion pages that drift from the code 3. Figma mockups that exist outside the agent's context A single `html.prompt` plus a `dist/` is lighter than all three and lives in the repo where the code does. ## A note on which agent This works with any agent that reads files and writes files. Claude Code produces the cleanest HTML out of the box. Open models via OpenCode (GLM-4.6, Qwen3, Kimi) produce passable HTML if you point them at the embedded skeleton in `html.prompt` as a reference. For client-facing artifacts the quality delta matters and I route those through Claude. For internal status docs and architecture writeups any of them is fine. The prompt is the source. Edit it. Add artifacts. Tighten privacy rules. Shift the regen triggers. It is one file. ## Why this matters past the productivity angle Specs as living HTML artifacts collapse the gap between code, documentation, and presentation. The same artifact a developer reads in `dist/plan.html` is the one a regulator reads at `yourproject.org/plan`. The same artifact the agent loads as context next session is the one a potential customer sees in a pitch. You stop maintaining three derivatives of the same information. For anyone shipping AI-adjacent infrastructure, where compliance posture, threat model, and audit trail are part of the product, this is not a productivity hack. It is a way to make the spec the deliverable. --- Credit where it belongs. Thariq Shihipar's [talk]( is the source of the thesis. `html.prompt` is the operationalization I now use across every project. If you fork it or build something on top, drop me a line. — metaend

Agent prompt for generating living HTML spec artifacts. Drop in any project, run with Claude Code or OpenCode, get dist/ of single-file HTML docs. Built on Thariq Shihipar's HTML-as-output thesis: markdown wins for instructions (CLAUDE.md, AGENTS.md, SKILL.md) but loses for outputs past ~100 lines. HTML restores engagement. Visual, scrollable, shareable, deployable as static site.

gitworkshop - Decentralized Git

Decentralized GitHub alternative over Nostr

#ai #llm

Errr View quoted note →

Oof View quoted note →

#Heltec stationary #Meshtec node is built and setup! Spreading the messages 👋

Meh #nsite deployment doesn't seem to work via Shakespeare? https://476cwr90otsdvrpehtjcuof2r7inbkm6jbg1dvkr52fm0dzlwozero-surface.shakespeare.to/

Vibed a tool for Vercel's zero language zero-surface / capability instrument reads zero graph --json and surfaces the capability footprint of every module & function in a Zero package.

zero-surface · capability surface for Zero

#Vercel #zero

Vercel Labs Introduces Zero, a Systems Programming Language Designed So AI Agents Can Read, Repair, and Ship Native Programs

MarkTechPost

Vercel Labs Introduces Zero, a Systems Programming Language Designed So AI Agents Can Read, Repair, and Ship Native Programs

Zero is an experimental systems language from Vercel Labs that compiles to sub-10 KiB native binaries, emits JSON diagnostics

Used my nano-gpt subscription (paid with crypto) and #shakespeare to build a little promo page demo/poc! https://nano-gpt-promo.shakespeare.diy/

All the #zaps I received so far here on #nostr went to

Bitcoin Crowdfunding for New Ideas and Humanitarian Causes | Geyser

Geyser helps people launch new Bitcoin project ideas and fund humanitarian causes worldwide, accelerating adoption through transparent crowdfunding.

👋

👇🤣 View quoted note →

Cool! View quoted note →

Its horrible and avoidable, but no need to be so negative. Vitalik has his full onchain practice open, and so far no one went for him. At least not to public knowledge View quoted note →

Nano added a cool new privacy feature: PII redaction https://nano-gpt.com/subscription/kUGJhgF9 #privacy #ai #llm

👇👇👇 View quoted note →

Starknet Develops 'strkBTC' to Bring Shielded Transactions to #Bitcoin This but as #zaps https://news.bitcoin.com/starknet-develops-strkbtc-to-bring-shielded-transactions-to-bitcoin/

#cashu deez nuts View quoted note →