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.
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.
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.`
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.
“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).
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.
Nice! I'm using AnyDesk for both desktop and phone, and then can completely control my computer from my phone, not only vs code. Also for watching long processes.
From Cursor's privacy policy:
If you enable "Privacy Mode" in Cursor's settings, none of your code will ever be stored by us or any third-party (except for OpenAI which persists the prompts we send to them for 30 days for trust and safety, unless you're on the business plan).
If you choose to keep Privacy Mode off, we may save prompts / collect telemetry data to improve the product.
Maybe it's only in my head, but for me, programmers work 99% of the time with code, while developers also spin up servers, cicd pipelines, domain dns stuff, and more stuff that are not strictly source code.