I really did swallow a bit and looked at the ceiling reading this (at a public place).

I'm building "workboxes" to work on my startup. It helps me develop features insanely fast. A workbox is a simple worktree-in-a-sandbox per feature. I have a simple front end where I can launch new workboxes: I input a prompt (a documented grilling session) and it creates a branch, a PR, and starts an opencode coding session on an e2b sandbox based on a custom template with the app's monorepo. Each workbox has a public https endpoint so I can manually test the web app after the coding session is complete. At any point I can either approve the PR, send a follow-up prompt, or connect to the opencode session for more control.

I think my next step is to perform the grilling session inside the front end, currently I perform it in my terminal and then paste in the front end.

Is it similar to how Claude Code Web works? It generates a cloud container and clones your repo, and works on a whatever you want (preferebly something specific), and then it generates a branch and a PR.

I guess. I never worked with Claude Code Web, but it sounds like it serves the same purpose.

The challenge I dealt with is actually running all services on the same machine - 4 services, each needs their own port, 2 of them need docker. Then injecting their sandbox urls into env vars for communication. All to have a fully working app with all services running - I just go to the public web app url and test.

Nonetheless, I'll look into CC Web, thanks for the mention.

In the links you provided, swc is the same entity.

From the article: `Reporters and networks are prohibited from publishing the precise location of Iranian missile impacts, or even filming or photographing the extent of the damage in a way that could give away the location — restrictions designed, in the words of the army’s chief censor Col. Netanel Kula, “to prevent assistance to the enemy during wartime.”` ... `In an unclassified document published on March 5, Kula instructed journalists to submit anything related to the following topics to the censor for review prior to publication: operational matters, intelligence, defensive preparedness, impact sites in Israel, armament management (including munitions and interceptor stockpiles, aircraft and air defense systems readiness, and the employment and use of unique and classified weaponry), and operational vulnerabilities in defense and offense.`

This happened to me too - the solution is to temporarily set the page view as desktop view through the browser settings.

While agents act on behalf of the user, they won't see nor click any ads; they won't sign-up to any newsletter; they won't buy the website owner a coffee. They don't act as humans just because humans triggered them. They simply take what they need and walk away.

Do you have an ad-blocker? If so, should website owners be able to disable your ad-blocker via a setting they send to you? It's their content, after all.

As a frugal person it's frustrating when websites block me for using an ad blocker, but I also don't think publishers should be required to send me data

They may, and do, refuse to send you the page. That is a more realistic parallel.

Without advertising the web would be largely unsupportable financially without per site subscriptions.

Without advertising, the web would be a far healthier place today, free of click-bait and ad-infested, low effort, low quality content. Bad business models wouldn't've survived the light of day.

fair point.

where's the front page CF callout for google search agent? they wouldn't dare. i don't remember the shaming for ad and newsletter pop up blockers.

that being said, agree with you that sites are not being used the way they were intended. i think this is part of the evolution of the web. it all began with no monetization, then swung far too much into it to the point of abuse. and now legitimate content creators are stuck in the middle.

what i disagree on is that CF has the right to, again allegedly, shame perplexity on false information. especially when OAI is solving captchas and google is also "misusing" websites.

i wish i had an answer to how we can evolve the web sustainably. my main gripe is the shaming and virtue signaling.

As far as I know Google's bot respects robots.txt and doesn't try to evade detection?

Funnily enough this would also mean some humans are not human, like me. I exhibit that behavior exactly as well. Maybe I'm an agent acting on behalf of myself, whatever that means.

Yep, also true of something like curl -s $url | llm --system 'summarize this article'

It's also true that you could dismantle a building with a hammer, which accomplishes the same as dynamite. So why not just sell dynamite at the local hardware store along with hammers?

And Cloudflare is the police entity to enforce this, right?

If your emacs config is (1) specific for each repo and (2) needs to be shared with other developers, it makes sense to add it to the repo.

Why would you need to share this? Isn't it an individual developer's preferences?

If it is, there's no reason to share it. If there are some org wide prefs needed to be "enforced", then there is a reason.

“The fundamental weakness of Western civilization is empathy". This is so depressing to read from one of the most influencial leaders in the world. I think empathy is a basic condition for a healthy society, and it lifts the average of human happiness.

I tried to write "Hello" on the demo page on my mobile phone, but it rendered "elloH". After hitting the H, the caret went back to the start of the line and then acted normal (stayed after each of the other letters).

Edit: video - https://we.tl/t-hAWomZ9DvT

The screenshot on your homepage looks very similar to plausible's https://plausible.io/ which is also open-source analytics software. Is it based on it? What are the differences?

Edit: Just noticed the feature comparison in the readme.

Also Plausible is almost stock TailwindUI elements + including the default color, so many sites look like that.