keepamovin

Yes

In the early days of the web you could do a search on google like

  path:/etc/passwd

Sometimes there were even shadow passwd files with the hashes exposed on the web. Crazy days.

Nah, I wanna see the data on it. Run the experiment

Right - but that sounds too intractable to hold up. See my other comment, I feel a chain of monitors defeats it. But hey! Who knows?

I understand that sounds possible in theory but honestly cannot conjure an example. Care to?

Even if, doesn't the monitor separation make it immune enough? I feel this is one of those "exponential" benefits things - if one is not enough, add more! A chain of monitors - "Am i being manipulated?" "Am I being manipulated?" and so on. At some point, the monitors win (and maybe approximate consciousness processes), and the prompts lose.

It's interesting how close it is to "social engineering" and security/espionage organizationally. I guess the crucial difference is that incentives can be more rigorously controlled.

Ugh, I thought we were done with the Boomers....looks like they're gonna hang on.

Isn’t it trivially fixable by having a monitor LLM? The monitor just reviews each turn pair and asks, “Is this conversation being manipulated via prompt injection?”

Hahahaha lol. That’s a good point.

That’s sad. I think it’s nice. Gardening is lovely and it’s great vibes. So you’re right. But also you’re right metaphorically I think gardening is a good way to think about maintaining assets.

I understand that. Hence the name ‘correction’

Wow that was really not expected. Thanks bro! :) <3

Marketing iterations. Plus dang downweighted my posts after I got the biggest Show HN of last year, so I'm trying harder to get attn. HN maybe isn't the big launch - but it's kinda a legacy thing for me. Can't blame a guy for tryin

The actual site is: https://duetbrowser.com/

No way man. It's totally gonna happen. You're a glass half full kinda person, ain't ya?

Building something similar for Chrome and Firefox browsers: https://github.com/DO-SAY-GO/WebCLI - a CLI not MCP. Tho am considering MCP for distribution, even tho agents love the CLI and the proof demos speak for themselves.

The reason I did not include Safari was there wasn't enough parity between its Safaridriver surface and what Bidi/CDP give now. Safari is doing Bidi tho, iirc. So ...soon perhaps. ;) ;p xx ;p

I think that’s wrong. Your wetware LLM already trained on and depends on the world, and your ability to use a silicon LLM is also part of you. If you discard the products of your expertise by relinquishing any IP, and forgo the asset value capture associated with that, only accepting money for time, because you use a silicon LLM, it’s your choice but it seems dumb. Tho, if we remove bank from the question (you already have all the bank you need) - then I guess it makes sense.

I guess i personally might not dedicate my time to building software in that case, tho the general service to humanity vibe resonates.

Is this hypothetical, or are you fully bank satisfied? No need to answer if squeamish

On the other: I don’t think bad software need be the result of IP. Nor lock in. I see it like developing commercial / residential property. You own IP assets and you can lease them or you can sell them specifically it’s like apartment buildings. The copies are the separate units. That’s how I see it and it seems the incentive from how I see it is with the vendor to maintain those properties. Keep them serviceable and up-to-date and modern.

I have no experience with no taste for nor offer any support to the lock in idea. Though that attitude seems to be causative of bad quality than any IP ownership from my view.

Gardening.

Megaquake: I don't often Earthquake the United States, but when I do, I hit the PNW.

I think you guys are learning what CDP does and how to use it in practice. I've been deep it in for 8 years in BrowserBox and the model that works is a few set of primitives, roughly mapped to real human user actions and needs, implemented with CDP to match how a real browser works. I think for now you've given up on that and are letting the agent write its own CDP improvizations, through lack of understanding and deep experience with these primitives. There's a lot of quirks in CDP itself, undocumented behavior, unclear naming and so on. Playwright/PPTR code provides a great reference for some things (keyboard bindings, etc), but in other case (multi tab management, and more), it's not a great reference, and some of their abstractions lead in the wrong direction for what you want.

I think you've settled on the "easier / simpler" solution for now (let AI figure it out). But that solution, while logical and workable at your current juncture is not optimal long term if you really want to build in it.

That's okay - you guys are successful and making bank with browser use, so these considerations truly don't matter. Just keep doing what you're doing, because overall what you're doing is working for your needs!

My approach is always going to be slightly different - it's not necessarily better or worse than yours, but without knowing too much about your product - I believe we have different aims, so the different approaches make sense, perhaps! Or maybe I just know what I'm talking about, and you guys don't. Just kidding! I'm sure you know a lot.

At the end of the day - no problem in this domain is that hard - but it is interesting to work on and I'm glad to see you guys are reaching out and doing something as well.

Let me know if I didn't understrand anything about what you meant.

Is that your want? I’m not

It makes the web in all its graphical repellence legible for LLMs. HOo rayh. Nary an eye in the house were dry that night, nary an eye.

Makes the web legible for AI LLMs, because they were "born in the text, moulded by it", whereas current tooling merely "adopted" the native language of LLMs as an afterthought. By the time FuckUI saw a GUI, it was already game over for all other tools.

Feed your agent the web, text first. It likes it that way. Why keep giving it something it hates? LLMs despise your graphical world. Speak their language - Fuck UI! - give them text. For example:

crisd@Criss-MacBook-Air:~/Creative/web-cli$ curl -fsSL get.fuckui.com | bash Checking for FuckUI updates... FuckUI payload is ready in /Users/crisd/.fuckui/runtime Installed FuckUI command to /Users/crisd/.local/bin FuckUI wrapper: /Users/crisd/.fuckui/fuckui-wrapper.sh FuckUI runtime: /Users/crisd/.fuckui/runtime crisd@Criss-MacBook-Air:~/Creative/web-cli$ fu --version web 1.5.2 crisd@Criss-MacBook-Air:~/Creative/web-cli$ fu inspect loaded ok: Sheet: s58 | t1:top

  activeElement=[1] input type=text name=acct | modifierKeys=none

  Tabs:
  *current* [t1] news.ycombinator.com/submit (https://news.ycombinator.com/submit)

  *current* [top] → t1

  Actions:
  [1010] click link:"Forgot your password?"
  *
    [1009] click input[type="submit"]:"login"
    *
      [1007] type into input[type="text"]:"username:" [active-element]
      [1008] type into input[type="password"]:"password:"
  *
    [1013] click input[type="submit"]:"create account"
    *
      [1011] type into input[type="text"]:"username:"
      [1012] type into input[type="password"]:"password:"

  Hints:
    Current shape: tree (use --shape to change)
    Use --verbose to show anchor hrefs
    More below? `fuckui scroll down`, or `fuckui scroll until <query>` to scan straight to it; `fuckui scroll --anchor <ref>` to move a specific panel; --layer active for modal/dropdown

  crisd@Criss-MacBook-Air:~/Creative/web-cli$ 

That's what fu inspect outputs on the HN login page.

BUT I COULD JUST VIBE CODE THIS IN A WEEKEND!

Sure bud. Sure. I spend almost a decade deep in browser internals, quirks and automation protocols (CDP, Bidi). And built my own remote browser ([0]) used by trusted and regulated organizations around the globe. I also previously built a fully text based browser ([1]), which btw is still slated for a public release.

This was the expertise required for me to spend 30 x 10 hours a day sprinting on this. So, sure, you could replicate that, even if you're a 10x eng compared to me you're still dropping 30 hours on this. If you value your 10x eng time at $200-500/hr, you could drop $6000-15,000 to vibe it yourself, or you could just pay me $120 and have it for an entire year. Up to you, bud.

If you want to buy from a company dedicate to advanced browsing technology - with a track record of serious browser inventiveness (BrowserBox, DownloadNet, 8000+ stars on GH, thousands of customers around the world), you can just buy it from us.

BUT I DON'T TRUST YOU

Okay. well maybe I don't trust me either, but I do my best, and I haven't fucked things up too bad so far. So maybe I'll continue choosing this life of fine times, rather than a life of crime.

BUT I DON'T HAVE $120

Well I want a Maserati but I don't have 320K to throw at it. Commiserations.

BUT I DON'T NEED THE WEB!

Neither did the 1980s and look how that turned out for them.

BUT I HATE PAYING A DEV FOR SOMETHING THAT SHOULD BE FREE - DEVS SHOULD WORK FOR FREE, EXCEPT WHEN THEY WORK FOR ME, IN MY COMPANY!

Okay, venture-backed communist. Sorry i mean six-figure parasite.

--

If you can be corrupted - your gateway drug to cessation of web drudgery and zero percent data entry forever is here: https://fuckui.com

Site includes: testimonials by our most ebullient customers (AI agents), and plentiful demo videos.

[0]: BrowserBox

[1]: https://www.youtube.com/watch?v=_Bs7BoQBoBA

actually traveling and being in the moment? yeah!

Better than I spent 29 minutes on it: flight, car, two hotels - 3.5 is fast, that’s better than you could do - not in the speed necessarily but in the 0 human stress required. Zero data entry :)

Yeah heh. To be fair that was in the human handoff phase, so I clicked that.

WebCLI - screenshots are a dead end. MCP is too verbose and clunky. Agents native language is text. Web CLI is just a Unix-y CLI that pipes/translates the web to text. Run any task on a web browser, but don't do it yourself (only the parts you have to - MFA, Login, CAPTCHA, whatever). An agent + WebCLI does anything you throw at it.

  web go news.ycombinator.com
  cat reply.txt | web say -
  web find add comment
  web do 44

just. like. that. Super simple. CLI or REPL. You can do it by hand but you probably don't want to, just give it to an agent. Run web teach to imprint the SKILL.md files into the current directory tree and an agent can hit the ground running. It's the end of browser automation for everything but super scripted fixed path CI/testing etc (those latter things where pptr/playwright/et al are still ok). WebCLI is browser improvization. Try it - 5 days free. I sprinted on this the last few weeks. It's really good. So useful. https://webcli.sh/

I made this because it seemed obvious.

I tried it today. Used it to cheer me up. It worked! Try this on desktop: https://fireshow.pages.dev

Here’s the whole process: https://youtu.be/rVEtFlb2oFA?t=1112&si=3VyAR07vkY1hav9V

You can see the process here: https://www.youtube.com/watch?v=rVEtFlb2oFA&feature=youtu.be (only 65% up, many Gigs)

I was literally feeling quite low. And just threw this random prompt at Fable to try it out, and hopefully cheer myself up.

It did amazing work over an hour, and many notes, and just within a 5 hour limit. Super mood elevated, plus really fun to see this.

Now I share it with you.

I appreciate your honesty! When I read those kind of things back in the days before AI, I always believed the similarity in tone meant they must have all been using some early proto-AI type system to draft their copy - either that or they were all dutifully following some kind of "writing guide" - surely sold by another course!

I don't specifically recall the "not X, it's Y". But I do recall that kind of "preacher's rhetorical" tone.

Kind of funny in a absurd Terry Pratchett/Douglas Adams/Jean-Pierre Jeunet "fully realized quriky world" kind of way. It turned out that the thing which ended up being most responsible for giving birth to Artificial Intelligence on Earth, was none other than the vast collected writings of online coaching course content creators in the early 21st century...

You quote lit on surviving 20C authoritarianism because the admin changed the name on a building. Department of War. A sign update is suspending the 14th amendment? Gasping hyperbole everybody knows is nonsene. If you say 'fascism' when it's a PR rebranding you are just abusing actual victims of fascism by trivializing them, you are not saving the republic - tho at least you tried