标签：#r

Who the F*** Am I? Hi, I'm Daniel Flores. A software developer with, I believe, seven years of professional experience. It's been a wild ride — at least the past three years. I was one of the first to actually try GitHub Copilot during its preview, probably around 2021 or 2022. I was completely amazed by it, but it was definitely very, very rough around the edges. Nobody knows me, though. I never intended to become a public figure or one of those guys who "knows where AI should go." That's not me, and that's okay. I've been watching this new paradigm evolve — and devolve — from the sidelines. What I Think About LLMs and "AI" I've been watching videos about this topic for years. Evolution simulators, learning algorithms, a model trained to play hide and seek — I was completely baffled when I realized that video came from OpenAI itself. I'm not an expert in how to build models or LLMs. I have no PhD. I've just been doing my own thing for years, watching which tools get adopted and which ones suck. And I have to say this: the industry doesn't know what the hell is happening. Neither do I. Nobody knows, and that's what I hate the most. LLMs are extremely useful. They can save you a lot of hours of work. But that's only half the story. So What's the Issue? Almost everyone — paid AI shills, mostly — is telling you: "YOU'RE GETTING BEHIND IF YOU DON'T USE THESE TOOLS!!" They're trying to push the entire industry into a fear-of-missing-out state. Let me share my personal experience about this completely inconsequential fear. If you're already experienced enough — if you already know what an LLM is and can prompt it to do or refactor something — you're not missing out. That's all there is to it. I'm going to explain what I mean. The exact same issues I had with the old GitHub Copilot — I don't even know what model it ran, probably a customized GPT — are still true today with the latest frontier models. They all hallucinate. They all seem to kind of understand what they're do

Most explanations of BIP39 and Shamir's Secret Sharing (SSS) stop at "here's what they do." I wanted to understand how they actually work under the hood, and more importantly, how they'd combine in a real system — specifically, censorship-resistant recovery of Bitcoin keys through a network of trusted guardians, where no single person, device, or institution should ever hold enough to reconstruct someone's keys alone. Here's what I worked through. The problem guardian-based recovery solves A Bitcoin wallet's security model has an uncomfortable tradeoff: hold your own keys and a single point of failure (device loss, death, coercion) can be catastrophic; hand custody to an institution and you've reintroduced the exact counterparty risk self-custody was meant to remove. Guardian-based recovery is the middle path — trusted parties each hold a fragment of the recovery material, with no single fragment being useful on its own. Two primitives make this practical, and they operate at different layers of the problem: BIP39 and SSS. BIP39: encoding entropy as something a human can reliably transcribe BIP39 doesn't generate a key — it encodes existing entropy into a human-transcribable form with built-in error detection. The process: Generate entropy: a cryptographically secure random bit string of 128, 160, 192, 224, or 256 bits. Compute SHA-256 of that entropy and take the first ENT/32 bits as a checksum (4 bits for 128-bit entropy, up to 8 bits for 256-bit entropy). Append the checksum to the entropy. The combined length is always divisible by 11. Split into 11-bit chunks (2^11 = 2048, matching the wordlist size) and map each chunk to a word. The checksum is the detail that matters most once you think about this as part of a real recovery flow: it means a single-word transcription error is very likely caught immediately during validation, rather than silently producing a different — but still structurally valid — seed. That's the difference between "recovery failed, check y

I built PunFiction: 1-Star Travel Reviews , a free daily web puzzle where you guess world landmarks by deciphering unhinged travel reviews from confused travelers. Tech Stack: Vanilla JS, CSS, HTML, GitHub Pages, MongoDB Atlas The Concept The internet can feel like it's literally overflowing with consumer complaints. I decided to take that negative energy and turn it into a 2-minute daily browser game for your morning coffee break. The Game Loop: Read an absurd 1-star review of a famous world landmark. Decipher the rhyming pun clues to guess the destination. Solving the puzzle unlocks an illustrated cartoon postcard and a sassy reply from the landmark 'manager'. The Tech Stack I wanted PunFiction to feel lightweight and lightning fast. Vanilla JavaScript: No React, Vue, or Svelte. Pure DOM manipulation and client-side logic. Zero Dependencies: No npm install spiral, no build-step headaches, and zero third-party scripts. No Accounts: Daily state, win streaks, and game progress live in localStorage. MongoDB Atlas: Light backend for aggregate puzzle stats (success rates, guess counts, no PII stored). Hosted on GitHub Pages: Static asset delivery via CDN. Give It a Spin If you like wordplay, geography, or just laughing at terrible tourist complaints, give today's daily puzzle a shot: 👉 Play PunFiction: 1-Star Travel Reviews I’d love to hear your thoughts on the UX, the game feel, or your take on building lightweight web games. Drop your feedback (or your worst pun) in the comments!

Most agent projects do not fail because the first model call is difficult. They become difficult when the prototype needs memory, tools, evaluation, a user interface, documentation that coding agents can navigate, and a repeatable review process. That is the problem the open-source AgentsKit ecosystem is trying to solve for JavaScript teams. It is a set of independent projects with shared contracts, rather than one application that must own the whole stack. The six public pieces 1. AgentsKit: the composable foundation AgentsKit provides focused JavaScript and TypeScript packages for runtimes, adapters, tools, skills, memory, RAG, evaluation, observability, sandboxing, and UI bindings. Its core has zero runtime dependencies and a CI-enforced 10 KB gzipped budget. Six formal contracts keep adapters, tools, memory, retrievers, skills, and runtimes substitutable. You can run a first local agent without an API key: npm install @agentskit/core @agentskit/runtime tsx Then connect OpenAI, Anthropic, Gemini, Ollama, or another adapter without changing the rest of the runtime composition. 2. AgentsKit Chat: one interaction model, seven renderers AgentsKit Chat defines an interactive agent experience once and renders it through React, React Native, Ink, Vue, Svelte, Solid, or Angular. It also supports deterministic local answers before an optional backend call. That matters for documentation and support interfaces where exact project facts should not require an LLM. pnpm dlx @agentskit/chat-cli@0.4.0 init my-chat --renderer react --yes 3. Registry: reusable source, not another dependency The AgentsKit Registry distributes ready-to-use agents in a shadcn-style model: the CLI copies the source into your project, so you can inspect and modify it. npx agentskit add research npx agentskit add code-review The public catalog currently includes research, code-review, and knowledge-promotion agents, and is open to contributions. 4. Agents Playbook: engineering rules that can execute Ag

Two substantial slices of gene/phen trait implementation just landed on submain . This shifts the needle significantly—contract checking and the capability for phen methods to actually get called at runtime are in the door. Previously, we only had the basic declarations and coherence working but now methods can type-check, Self can resolve per receiver, and calls execute. The submain branch now sits 15 commits ahead of main , holding the matrix at 321/0. Contract Checking and Self Resolution (Slice 2) Let's zero in on commit fcd3193 , which makes waves with 594 insertions across 23 files. The big takeaway is Pass 0 contract conformance. The collect_gene_phen_registry() function now actively validates every phen against its gene. Consider everything from arity to positional parameter types (post- Self substitution), return types, and even checks for both missing and extra methods. If there's a mismatch, it doesn’t just shout—each one is a precise diagnostic identifying gene, method, position, and expected-vs-actual types. It's pinpoint troubleshooting. The decision to resolve Self at the concrete level before analysis was deliberate. Self in phen signatures and bodies changes to the actual receiver type within the AST thanks to substitute_self_type() . This function even navigates through intricate structures like Array , Handle , and Result wrappers. There was an alternative: treating Self as a floating type parameter. But honestly, it doesn't cut it because types_compatible would unify any type param with anything. Sticking to the design docs, our path— Self is concrete, not a floating parametric. How about ownership? It's strict. There's no room for unauthorized methods beyond the gene's contract. And we're talking multiple enforcement points: from Pass 0 checks to the phen_methods field on Analyzer triggered during per-file analysis, down to cross-gene-method name collisions caught by Pass 0. Every path specified is locked down, as envisioned by the design docs.

Most “WordPress to Next.js” tutorials show you how to fetch posts from the WP REST API and render them in the App Router. That’s the easy 20%. The 80% that actually decides whether your organic traffic survives is everything around the content: your URLs, your redirects, your metadata, your sitemap, and your images. Get those wrong and you’ll watch impressions fall off a cliff two weeks after launch, right when everyone assumes the migration “went fine.” This guide is the checklist I wish every team ran before flipping DNS. It’s framework-accurate for the Next.js App Router, and it works whether your new backend is headless WordPress, a headless CMS, or flat files. The one rule that saves rankings Every decision in a migration comes back to a single principle: Nothing about how Google already sees your pages should change, except the parts you deliberately improve. Google ranks specific URLs based on their content, their metadata, and the links pointing to them. A migration is dangerous precisely because it’s tempting to change all three at once: new URLs, a “cleaner” content structure, redesigned templates. Do that and you’ve thrown away the signals every ranking is built on. The safe path is boring: same URLs, same content, same meta, just a faster, modern frontend underneath. Step 1: Inventory everything before you touch anything You cannot preserve what you haven’t captured. Before writing a line of Next.js, you need a complete, structured snapshot of the live site: every published URL, its rendered content, its SEO metadata, its images, and its internal links. This inventory becomes the source of truth for your redirect map, your generateMetadata , and your sitemap. This is the step most guides wave away with “export your content from WordPress.” In reality it’s where migrations break, because the default WordPress export (WXR) gives you raw post content, not the rendered HTML your page builder actually outputs, and it drops most of the SEO fields you need. If

Most agent tutorials stop at tools: give the model a function schema, hope it calls the right one. That works for get_time and hash_string . It falls apart when the model skips a knowledge search and opens a ticket, or when eighty APIs all land in one context window. Solon AI keeps tools as the execution unit, then adds Talent as the product unit: tools plus SOP plus activation rules. Think of it this way: Tool ≈ a function Talent ≈ a class that owns those functions, their playbook, and when they appear This post is a practical map of when to stay on tools, when to wrap them in a talent, and how registration actually works in Solon v4.0.3. The product failure behind “just add more tools” Bare tools only answer two questions for the model: what can I call? what args does it need? They do not answer: should this capability even be visible right now? what order must I follow before a dangerous call? which tools belong to the same business domain? That gap shows up as: premature side effects (ticket created before diagnosis) context blow-up (full tool tables on every turn) weak SOP compliance (model freestyles across domains) Talent is Solon’s answer: a reusable package of awareness + instruction + tools , with automatic coloring so tools keep their domain identity. Tool vs Talent in one table From the official comparison: Dimension Tool ( FunctionTool ) Talent ( Talent ) Unit Single function / method Instruction + tool set + state Abstraction Physical: how Logical: when and under which SOP Context awareness Passive isSupported(Prompt) can activate or hide Injected content Tool schema (JSON) System prompt fragment + tool list Constraint strength Weak — model freestyles from description Strong — SOP via getInstruction Registration defaultToolAdd / toolAdd defaultTalentAdd / talentAdd They are not rivals. A talent contains tools. Registering a talent also registers its tools; you do not need a second defaultToolAdd for the same set. Lifecycle: what actually runs at reques

Open source web terminal multiplexer for AI agents Discussion | Link

The Range Rover GT will debut as an EV with a hybrid version to follow.

It’s “the most car-like Range Rover ever created,” but will this all-electric grand tourer spoil Jaguar’s Type 01 party?

Hey HN, I built Superserve, a compute layer that lets AI agents live inside isolated Firecracker microVMs with no session time limits. The problem I kept running into: most sandbox providers kill your agent after 24 hours. If you're running something autonomous that needs to work for days — refactoring a codebase, running tests in a loop — you're constantly fighting timeouts and rebuilding state. Superserve lets you snapshot a running VM at any point, fork it into parallel branches, and resume e