Rendered at 22:56:08 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
zaep 2 hours ago [-]
Working in satellite simulation, where we end up with complex harnesses (cabling) and where I don't really know the nitty-gritty of how the sausage is made by the engineers creating them, I was really curious for a moment; but alas, it's an AI thing.
FWIW, my quick impression is that takes reasonable concepts and tries to formalize them into a framework; I can see potential benefits, I've certainly asked in a claude code session for it to have a look at pipeline so and so and figure out the issue, but I'm not really convinced by this at first glance either. Both setup-cost and token cost seem like downsides.
vibe42 6 hours ago [-]
Something I've had good progress with using local models and simple open-source harnesses is to repeat, in a new context, simple verification prompts.
I'd run the following 5-10 times with one model, then again with a 2nd model.
"Verify the correctness and completeness of all security configs/rules in SETUP.md. Consider if anything is missing, and if anything is not needed. Do not modify any files; only write potential findings to report.txt"
"Verify all findings and claims in report.txt."
Replace "SETUP.md" with whatever you're working on.
It's both terrifying and incredible watching what the models get correct and what they get completely wrong.
However, after enough runs they tend to settle on a state they claim does not need any more edits. And that result is generally useful with much fewer errors/hallucinations compared to a single run.
mrshu 2 minutes ago [-]
I have also had positive experience with doing this multiple times via multiple model families, and then to recursively have the fixes reviewed too.
It's called review-anvil and does find significant amount of problems that might pop up:
Don't you think "consider if anything is missing" leads them into adding something with sycophancy RL training and "if anything is not needed" making it remove something?
Or does "verify all claims in report" counteract that?
mindwok 2 hours ago [-]
This is AI slop written primarily with the intent to promote the authors, not to actually educate. So sick of this kind of content.
sieabahlpark 1 hours ago [-]
[dead]
mustaphah 5 hours ago [-]
Couldn't tolerate the content; it's too structured; I'm open to something more chaotic.
manbash 4 hours ago [-]
The content is clearly AI-generated, which is really ironic.
myself248 4 hours ago [-]
I would love a resource to get more into the details of bend radius and vibrational modes in harnesses, specifically as they're used on different types of vehicles. Marine wiring endures very different motion than road-vehicle wiring, for instance.
mordechai9000 3 hours ago [-]
I wonder about failure modes and fault identification. I've heard stories of things like screws or brackets wearing through the insulation and causing an intermittent fault that defies diagnosis. One of those things I think about when I am procrastinating.
anonymousiam 4 hours ago [-]
My first impression, based upon the title was that this was about Wire Harness Engineering, which is a thing. Apparently it's not about that at all, and is (surprise!) AI related.
FWIW, my quick impression is that takes reasonable concepts and tries to formalize them into a framework; I can see potential benefits, I've certainly asked in a claude code session for it to have a look at pipeline so and so and figure out the issue, but I'm not really convinced by this at first glance either. Both setup-cost and token cost seem like downsides.
I'd run the following 5-10 times with one model, then again with a 2nd model.
"Verify the correctness and completeness of all security configs/rules in SETUP.md. Consider if anything is missing, and if anything is not needed. Do not modify any files; only write potential findings to report.txt"
"Verify all findings and claims in report.txt."
Replace "SETUP.md" with whatever you're working on.
It's both terrifying and incredible watching what the models get correct and what they get completely wrong.
However, after enough runs they tend to settle on a state they claim does not need any more edits. And that result is generally useful with much fewer errors/hallucinations compared to a single run.
It's called review-anvil and does find significant amount of problems that might pop up:
https://github.com/mrshu/agent-skills/#review-anvil
Or does "verify all claims in report" counteract that?
Why not just look through the actual Claude code codebase and use your own AI to deconstruct it
https://github.com/codeaashu/claude-code
[0] https://vitepress.dev/