Thought is a derivative of sensory processing. LLM does not have a physical body to interact with the world, nor does it develop itself and learn anything by experiencing the world, it has no subjective experience or subjective feeling, it has no qualia, it's symbols are not grounded in physical reality and it's "thoughts" is a mere simulacrum. Anyone personifying an LLM is just derealised by convincing outputs, not realising that manipulating symbols according to rules does not imply understanding

having to click somewhere is not a shortcut, seriosly who the hell switches the desktops with mouse scrolling or clicking? there is a real shortcut for that

Digital Vitamins | Senior JS developer | Electron.js + React.js | Remote (EU) | Full-time

Digital Vitamins is building a secure messaging application on top of Electron.js and React.js. Looking for developers with relevant experience. Send your CV to ilya.lopukhin at 1rstwap.com

Thinking that Apple would urgently reconsider anything because of some angry blog post is rather naive. Until this s tangibly affecting Apple's finances the probability they are giving a single shite is approaching zero. Pixel phones and GrapheneOS stonks up.

Hello OP, I think using an ai agent to fetch the JSON is a bit of an overkill

Here is a node.js script for you which will fetch the data and save it to the file:

  import fs from 'fs'
  import puppeteer from 'puppeteer-extra'
  import StealthPlugin from 'puppeteer-extra-plugin-stealth'
  puppeteer.use(StealthPlugin())

  const browser = await puppeteer.launch();
  const page = await browser.newPage();

  async function fetchCoords(x, y, z = 8, station = 0) {
    await  page.goto(`https://www.marinetraffic.com/getData/get_data_json_4/z:${z}/X:${x}/Y:${y}/station:${station}`);

    const jsonRaw = await page.evaluate(() => document.body.innerText);

    const json = JSON.parse(jsonRaw)

    return json
  }

  const data8353 = await fetchCoords(83, 53)

  const data8453 = await fetchCoords(84, 53)

  const data8354 = await fetchCoords(83, 54)

  const data8454 = await fetchCoords(84, 54)

  const fullData = { ...data8353, ...data8453, ...data8354, ...data8454 }

  fs.writeFileSync('data.json', JSON.stringify(fullData, null, 2))

  console.log('done!')

  process.exit(0)

Just like this, no need to spend a cent on expensive APIs or tokens

Take your upvote, love the old school hn spirit.

Reminds me of when I was speaking at a conference back in the mid 2010's with a presentation titled "Join the dark side of APIs" or something akin to that, where I showed many of the newly popularized "single page apps (SPAs)" relied on undocumented and public APIs, often without any authorization. Immediately followed by a talk by a business type guy on API copyright or something or other.

If I had to pick one thing I like about software devs as a group, it's this: you find a problem, you solve it, you share the solution.

What is the AI agent doing in this interaction? This is a public API exposed to any browser...

Well, not to every every browser, there is some cloudflare bs preventing simple curling and you actually need a stealth-mode puppeteer to go around it.

>Text field.

>"Ask Meta AI..." placeholder.

>Colourful blue Send button.

>Eager to try, entering question... hitting Send.

>Log in or create an account to access.

>15 seconds of loading time

>Continue with Facebook or Instagram

Typical meta move, throwing a dark pattern at you from the beginning instead of just letting you try it

Won't even bother to continue, somehow OpenAI got this right.

Executable signing is also designed to make easy money from selling certificates

File. In Unix everything is a file.

honestly if local LLMs become easier to implement in the future due to dedicated hardware, the Unix-like thing I'm working on might actually get this

Am I missing something but I can't see full article? All I see is like a 100 words preview, is this the whole thing?

i believe the post is a [video] and the 100 words are an AI summary

At least the cost of building slopware has drastically decreased.