Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

What xAI's Grok build CLI sends to xAI: A wire-level analysis

gist.github.com

Post reply on HN
Print view View original

41–50 of 251 posts

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#41

Post by rescbr »

5701652400 wrote: post #29
rescbr wrote: post #14

Now, where are the people afraid of the Chinese AI companies, who claim they are going to copy their very precious code...?

using them in VSCode all the time for months now. Qwen from Alibaba Cloud, Deepseek from deepseek.com. none of them upload entirety of codebase or even attempt to. in fact, opposite. Chinese AI seem to post-process heaviliy locally. they are always using head / tail, grep, sed, and do as much as they can locally and extrac meaningful data and send home (AI inference chunks). only what is really needed. it is actually…

For me, them allowing API usage on coding plans so we can use any harness, and returning the full unabridged reasoning back are how they earned my trust.

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#42

Post by rvz »

dimgl wrote: post #38

Grok Build has had impressive performance in a couple of my projects. And fast. So this revelation has been very disappointing... I will say, a majority of the code I'm writing now is fully through an online LLM. If a company wanted to reconstruct a project I'm working on, they could just replay all of the tool calls from their logs, if they decide to retain the data (I did this locally once to recover a project that…

But you also have handed over your secrets, dotfiles and API keys alongside with your source code to xAI.

I'm afraid you have been scammed.

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#43

Post by culi »

faangguyindia wrote: post #12
freakynit wrote: post #4

"It uploads the whole repository — every tracked file's content plus git history — independent of what the agent reads" Holy cow!!!! I mean I kinda expected Elon would do something like this to try to catch-up.. but this is extremely concerning. This is precisely the reason, even though their pricing is competitive and grok-4.5 is actually good enough, I chose not to go with them.

Does OpenAI also have access to all github repos via partnership with microsoft?

Absolutely not. That would be an absurd violation. If you have Copilot enabled then they can use your interaction data for training but you can turn that off as well

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#44

Post by tyre »

t_gamer_kle wrote: post #36
jpollock wrote: post #17

Earlier quoted context omitted.

It would be _extremely_ surprising if private repos were available via that contract. Corporations wouldn't use GitHub at all if anyone other than those given direct access had read/copy permission.

They were caught stealing Apple trade secrets, dude. Nothing is beneath them.

Nothing is beneath Altman, maybe, but Satya isn’t that dumb. MSFT cares about OAI but giving access to private data and trade secrets voluntarily would be catastrophic for them.

Doesn’t feel like the type of mistake Satya would make.

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#45

Post by dimgl »

rvz wrote: post #42
dimgl wrote: post #38

Grok Build has had impressive performance in a couple of my projects. And fast. So this revelation has been very disappointing... I will say, a majority of the code I'm writing now is fully through an online LLM. If a company wanted to reconstruct a project I'm working on, they could just replay all of the tool calls from their logs, if they decide to retain the data (I did this locally once to recover a project that…

But you also have handed over your secrets, dotfiles and API keys alongside with your source code to xAI. I'm afraid you have been scammed.

A bit hyperbolic, no? A majority of code is now written through Claude and similar services.

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#46

Post by ashishb »

freakynit wrote: post #4

"It uploads the whole repository — every tracked file's content plus git history — independent of what the agent reads" Holy cow!!!! I mean I kinda expected Elon would do something like this to try to catch-up.. but this is extremely concerning. This is precisely the reason, even though their pricing is competitive and grok-4.5 is actually good enough, I chose not to go with them.

There is a reason I run all such CLIs inside a sandbox [1] giving limited directory access.

Imagine if the CLI pulled your SSH keys or other sensitive information by mistake?

Programmers do make such mistakes all the time. I don't want to count on whether "uploading all files it can access" is intentional or a mistake.

1 - https://github.com/ashishb/amazing-sandbox

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#47

Post by tredre3 »

5701652400 wrote: post #29
rescbr wrote: post #14

Now, where are the people afraid of the Chinese AI companies, who claim they are going to copy their very precious code...?

using them in VSCode all the time for months now. Qwen from Alibaba Cloud, Deepseek from deepseek.com. none of them upload entirety of codebase or even attempt to. in fact, opposite. Chinese AI seem to post-process heaviliy locally. they are always using head / tail, grep, sed, and do as much as they can locally and extrac meaningful data and send home (AI inference chunks). only what is really needed. it is actually…

> none of them upload entirety of codebase or even attempt to.

How do you know? Did you do an analysis like OP did?

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#48

Post by phaseleza »

I always separate the coding tools from LLM providers, and use bubblewrap to sandbox the coding tools so they:

1. Can only read the working project directory, with .git read-only and sensitive directories hidden (mounted as empty directories).

2. Have an isolated network namespace; they can only access the internet through an HTTP proxy hosted on a Unix socket, can only access specific LLM provider hostnames, and exclude the tool's own hostname.

For example, with Crush, I will let it access *.openrouter.ai (LLM providers) but not *.charm.land (Crush's domain for auto-updating the LLM list).

This makes me feel much more comfortable enabling "yolo" mode and letting the tools do everything.

Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis

#49

Post by charcircuit »

culi wrote: post #39
charcircuit wrote: post #22

The simplest way to disable uploading your repo is disabling it in the config. [harness] disable_codebase_upload=true

This is completely made up. The Grok Build CLI reference lists no such thing. Whatever LLM you asked probably hallucinated this.

>completely made up

If you want easily verifiable evidence, run strings on the Grok Build CLI binary and you will see:

    Codebase upload skipped: disabled by config (harness.disable_codebase_upload=true)
Post reply on HN