Reverse-Engineering Claude Web's MicroVM: Uncovering Anthropic's Hidden Antspace | Hacker News Reader

Reverse-Engineering Claude Web's MicroVM: Uncovering Anthropic's Hidden Antspace

aprilnea.me

110 pointsrzk23 comments

Actual title: ' Anthropic's Hidden Vercel Competitor "Antspace"'

It's for Claude Code, not Claude web. And it's been posted here 3 times already.

One thing that I didn't understand from this article was how you use this deployment platform.

Can you tell Claude code for web to build and deploy a web app using it? If so, does that end up with a public URL somewhere? Does that deployment continue working after your Claude code for web session ends?

The way I interpret this is:

After some inactivity it goes into some dormant mode. Where it will only consume some storage. The next time someone tries to access this artifact it just restores a snapshot from last working state.

I guess the public url part is working similar to how OpenAI and their Sites are. E.g: their personally only available to you, until you change the sharing options.

I’m guessing this is what the mobile apps use when spinning up a vm for code (not chat).

The interesting benchmark is not merely whether each agent receives a VM. It is whether a compromised task can cross capability, credential, network, or persistence boundaries.

"No systemd. No sshd. No cron. No logging daemon."

You can delete that sentence. Why would someone assume sshd or cron in an environment like this?

Omit needless words.

It's "load bearing".

It's perhaps the most pernicious Claudism. Or just the one that gets my goat the most. Saying what something isn't, usually twice, before saying what it is. What a fucking waste of words.

Got it. No bullshit, no ceremony: just straight to the point.

Reasoning trace: > The user seems to be frustrated with my stylistic choices for prose...

I don’t get no respect. I don’t get no respect at all.

I say to the guy, “That looks load-bearing.”

He looks at me like I just insulted his mother. “What the hell does that even mean?”

This is the same guy who asked me to rebuild Twitter. No bugs. By Friday.

sounds like a douche

I'm not defending claudeslop, but TBF, anaphora and its lesser-known sibling: epistrophe far predate the English language, let alone something new like LLMs.

Repetition at the start or end (i.e. Anaphora/Epistrophe) are not used lightly in prose or verse, they serve a rhetorical purpose - usually add rhythm or strengthen the theme.

The type of repetition Claude uses is what Fowler[1] called "elegant variations" and discouraged in modern style guides for a good reason - people find it really annoying.

[1] Henry not Martin

"I'm not defending claudeslop, but <defends slop>". People obviously know this. The problem is that using a dramatic rhetorical flourish every third sentence for completely un-dramatic things is fucking tiring. And so are the people defending this shit. "Oh, humans use em-dashes too, so actually there's literally no difference between a human using one or two and Claude using 400 em-dashes in one article". A human using things correctly and a language model using them incorrectly are not the same fucking thing.

I believe that what the previous commment is trying to say is that even when we identify phrases highly attributable to llm output we can never be certain. Which is the nefarious thing about broad use of computer generated text. I noticed comments here on hacker news containing conspicous mistakes which llms hardly ever do anymore and was wondering whether it was people purposefully adding mistakes to identify as noslop or whether llms got worse or if it was bots trying to fool me. My misspelling of conspicuous was left in on purpose in this case. All i can say is "trust me bro, I am not ai".

> The problem is that using a dramatic rhetorical flourish every third sentence for completely un-dramatic things is fucking tiring.

100% this. It's exhausting reading this stuff, and those dramatic flourishes are a big part of why.

The issue is the frequently repeated, formulaic use.

That's the most annoying one, and the two negated things more often than not end up being something no one would have ever considered in the first place.

The article, while interesting, is clearly Claudeslop.

Clearly the author is not a native english speaker (from the other blog posts) i found skimming it interesting nonetheless, i hate slop as much as the next guy but appreciate the language barrier braking qualities of llms.

“It is difficult to get [an AI] to [omit words, which are counted as tokens], when [it’s company’s] paycheck depends on [it] not [omitting words].”

"This is not just an AI coding assistant. It's"...

Claude writing about claude. Painful to read.

Reply on news.ycombinator.com