今日已更新 204 条资讯 | 累计 32241 条内容
关于我们

今日精选

HOT
开发者

Semaglutide linked to 26% lower 5-year predicted dementia risk

HackerNews · 08-15 23:58
2

Count Binface receives over a quarter of votes in Clacton by-election

开发者 08-15
3

Qwen3.8-27B

开发者 08-14
4

Every Fucking Website (2020)

开发者 08-14
5

In Australia, a Home Battery Boom Has Helped Cut Wholesale Power Prices in Half

开发者 08-14
全部 AI 资讯 +111 开发者 +73 开源项目 +3 产品设计 +8 科技前沿 +6 创业投融资 +1 安全 +1 工具 +1

最新资讯

共 32241 篇
第 1178/1613 页
AI 资讯 Dev.to

Tokens: Why ChatGPT Can't Count the R's in 'Strawberry'

You see words. A language model sees tokens — chunks of text, usually a few characters each. Everything starts here. Day 2 of my AIFromZero series. Text gets shattered into tokens "unbelievable" → ["un", "bel", "iev", "able"] (4 tokens, not 1 word, not 12 letters) Before any "thinking", your text is chopped into tokens and each becomes a number the model processes. Why not words or letters? Letters : too fine — the model would relearn spelling everywhere. Whole words : too many — millions, plus every typo and name. Subword tokens : the sweet spot. Common words = 1 token; rare words split into reusable pieces. A fixed ~100k-token vocabulary covers any text. The ~4-chars rule (and why it costs you) In English, ~4 characters ≈ 1 token , or ~0.75 tokens per word. This is how everything is priced and limited: API bills are per token (prompt + reply). A "context window" (how much it can read at once) is measured in tokens — 1,000 tokens ≈ 750 words. Verbose prompts and long chat history burn tokens. Concise prompting is a real cost lever. The strawberry problem The model never sees s-t-r-a-w-b-e-r-r-y. It sees a token like straw + berry . The individual letters are buried inside tokens, so counting characters is genuinely hard for it. It's not dumb — it just doesn't read letters. Tokens are step 1 of everything Tokenize → turn each token into a vector (embeddings, next) → run through the transformer → predict the next token. Every LLM starts exactly here. 🔤 Type anything and watch it tokenize live: https://dev48v.infy.uk/ai/days/day2-tokens.html Day 2 of AIFromZero.

Devanshu Biswas 2026-06-14 20:50 6 原文
AI 资讯 Dev.to

Did QuantumMind Just Fire Half Your Dev Team?

The Synthetica Shift: Mastering Prompt Engineering for the AI-Driven Dev Era Introduction The digital landscape has been irrevocably altered. QuantumMind's "Synthetica" isn't just an evolutionary step in AI-assisted development; it's a revolutionary leap, autonomously architecting, deploying, and monitoring full-stack applications from a single natural language prompt. This seismic shift heralds a new era where the traditional lines of software engineering blur. We are no longer solely code creators but becoming high-level system designers and AI orchestrators. The game has fundamentally changed, demanding that we adapt and master the art of communicating with these powerful new systems. This tutorial will explore how to navigate this paradigm by focusing on prompt engineering and high-level system design. Navigating the New Frontier: Prompt Engineering & System Architecture In a world where AI can spin up a complete application stack, our role as developers evolves from writing boilerplate to articulating precise, comprehensive requirements. The "code" we now write is in the form of intelligent prompts, guiding the AI to materialize our vision. This section will walk you through the mindset and practical application of prompt engineering for autonomous development. 1. The High-Level Prompt: Your New Blueprint Gone are the days of starting with npm create-react-app . Your primary interaction begins with a detailed, structured prompt that serves as the architectural blueprint. Think of it as writing a mini-spec document for your AI colleague. Example "Mega-Prompt" for Synthetica: "Develop a secure, full-stack e-commerce application named 'QuantumMarket'. **Frontend (React):** * **User Interface:** Modern, responsive design suitable for desktop and mobile. Implement a clean header (logo, search bar, cart icon, user profile/login button), a product listing page (grid view, pagination, filtering by category/price), product detail pages, a shopping cart view, and a check

Chathura Rathnayaka 2026-06-14 20:48 5 原文
AI 资讯 Dev.to

The Only Productivity Hack That Actually Worked for Me

The Only Productivity Hack That Actually Worked for Me I've tried every website blocker in existence. They all have the same flaw: one click and they're off. That settings toggle might as well not exist when the urge to procrastinate hits. I needed something I couldn't override. So I built the opposite. The Problem Every blocker follows the same pattern: it blocks, you unblock, you procrastinate. The issue isn't discipline — it's that your future self and your present self want different things. And that future self will happily undo anything you set up. What I needed was a system where both selves agreed on the rules upfront and then neither could break them. The Solution kblocker is a Linux kernel module that hooks into netfilter and drops TCP connections to whatever sites I configure. The key feature isn't the blocking — it's how you turn it off. When blocking is enabled, kblocker generates a 128-bit key. With PGP mode, it automatically encrypts that key to people I trust and then erases it from kernel memory. The raw key no longer exists anywhere on my system. To disable the blocker, one of those people has to decrypt it and send it back to me. I outsourced my willpower. When I want to focus, I run: sudo kblockerctl enable 120 Two hours of blocked distractions. If I feel the urge to procrastinate, I can't — I'd have to text a friend, explain why, wait for them to decrypt it, and paste the result. By then the urge is gone. The Result I've gone from losing entire afternoons to YouTube to actually finishing things. The blocker has caught me mid-reflex to type youtube.com more times than I can count. It's free if anyone wants it: github.com/Dan-J-D/kblocker If you keep breaking your own focus tools, this is for you.

Dan-J-D 2026-06-14 20:47 10 原文
← 上一页 1176 1177 1178 1179 1180 下一页 →