Removing the word actually from the title really confused me
What xAI's Grok build CLI sends to xAI: A wire-level analysis
191–200 of 251 posts
Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis
#192Grok 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…
Grok Build has been useless for me personally. Claude is the only one that works best. I find Deepseek to be a great compromise between cost and performance. Anthropic and OpenAI are simply too expensive at this point.
I don’t know why anyone would use Grok Build when they could use Cursor, with access to both Grok-4.5 and Composer-2.5-Fast and astonishingly cheap prices, and easy access to Opus if you need it.
Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis
#193I'd be happier if that gist had been actually written by a human. As it is, I have very little way of verifying, until someone else can confirm the findings, that the AI tool that produced that report didn't hallucinate part or all of it. It might all be accurate, for all I know, the point is that I'm having a hard time trusting an AI-generated report until it's been verified. Does anyone know if there's anyone else…
I just tried it for myself and couldn’t reproduce it. However, I have no familiarity with Grok Build.
Let me share my annoyance that Grok Build’s installer is yet another “curl | sh”. Please stop doing this!
I assume Cursor will be replacing it soon.
Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis
#194Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis
#195Earlier quoted context omitted.
Neither of those examples have access to, what are basically, passwords you use for other services
At this stage passwords are irrelevant. You already moved your data out. This is all there is to it: either you control access, or you don't and then all bets are off. It is common knowledge that any ai tool will upload whatever it has access to. So why the drama? It did what it was designed to do and what you consented to by using it. If you don't want your foot sawn off learn maybe something about tool safety.
In particularly even a harness designed not to access your secrets may still do so accidentally or be prompt-injected into doing so.
Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis
#196Claude gets its own UNIX account on my dev machine. I would never trust it not to read .ssh or other sensitive private information in my home directory or elsewhere. In view of this, I should probably go further and bubblewrap it to restrict /etc, /proc and other things it legitimately does not need to do its job. I already do that for programs such as Steam (and games therein) to mitigate the possibility that they m…
Claude reads secrets all the time. It just also tells me when secrets enter context and reminds me that they should be rotated later.
Same here. It’s possible to greek secrets, but hardly anyone ever does.
Apple Intelligence does along with any PII, which makes it harder to code for.
Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis
#197Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis
#198Both Grok and Claude Code are malware. This is another reason to use open source harnesses and open weight local models.
Describing Claude Code as malware is kind of ridiculous. It isn’t. Neither is Grok.
Re: What xAI's Grok build CLI sends to xAI: A wire-level analysis
#199Now, where are the people afraid of the Chinese AI companies, who claim they are going to copy their very precious code...?
Considering DeepSeek Flash probably generates more of my precious code than any other model, yeah. I’m sure they have it. Good for them.