Hacker News new | ask | show | jobs
by giancarlostoro 1 hour ago
> It's harder than you'd imagine. Hell, my CLAUDE.md says not to push changes without asking me, and it still tries.

Is it a system memory? Because I rarely if ever have issues like this, and I have Claude under strict rules to never commit or push anything unless I explicitly instruct it to do so.

> They tried that, several times.

Tried what exactly? Telling it to only agree with MAGA via the system prompt? or some Tay level hallucinations? I wouldn't be surprised if they're trying to make Grok less strict on what it says but running into the "holy crap it turned into a 4chan poster" wall.

1 comments

> Is it a system memory?

As I said, it's in my CLAUDE.md. That just gets progressively lost when context gets larger.

> Tried what exactly?

To make it align more with Musk's beliefs via the prompt.

(The answer to your question is literally in my post; I quoted the parent poster's "all they would have to do is add a one liner to the system prompt for Grok")

> As I said, it's in my CLAUDE.md. That just gets progressively lost when context gets larger.

I rarely have this problem, but you could do a /loop every 30 minutes or so to have Claude reread the CLAUDE.md file might do the trick? or however long it 'forgets' I believe there's an MCP for "after" it finishes a task or compacts too, but I don't recall the name.

Sure, I could. (I have a fairly complex workflow with subagents at this point, which helps reduce it; I mainly get bitten by it when I go back to a direct `claude` CLI prompt for something.)

But that solves "my LLM is doing things I don't want it to do". It doesn't solve "Grok's owner wants it forced into agreeing with him" scenarios.

Have you tried something like beads? Curious if it would help with your setup too. This is also kind of why I built "GuardRails" I got tired of Beads auto-approving tickets or closing them.

https://github.com/Giancarlos/guardrails

I have a custom Mac app that runs a workflow with plan/build/review/test/document subagents in Ralph loops, manages MCPs, etc. that I'm extremely happy with so far.

Beads was a bit of an inspiration for parts, as was Chainlink (https://github.com/dollspace-gay/chainlink).