I asked Claude to scan my network and check if LG tv is sending data, it said yes. Some domains were blocked by my router some were not, now Claude blocked all lg related tracking/ad domains on my router.
I have AdGuard running in my home lab and pointed the router to the AdGuard DNS resolver. I have some general block lists and a special Smart TV block list.
I asked DeepSeek to do the same scan, but given everything goes through AdGuard it’s much simpler to sift through it’s logs. This is what I got:
* rdx2.lgtvsdp.com (600/600) — LG ad platform
* cdpsvc.lgtvcommon.com (~370) — LG customer-data platform & beacons
* info.lgsmartad.com (78/78) — LG Smart AD
* ibs.lgappstv.com (86/86) — LG app store
* aic-ngfts.lge.com (36/36)
General list also catches: Netflix logs (6k), Amazon telemetry.insights.video.a2z.com (700), Datadog (600), Conviva (410), Google DoubleClick (98)
Though some domains still are going through, which are now blocked :)
Apparently, nearlyepic is trying to deliver two veiled insults and a critique of judgement or perhaps of the current state of broader affairs. I'll attempt to translate:
- "no idea what you’re talking" = "you have outsourced expertise to an LLM"
- "solution that doesn’t actually work" = "piecemeal blocking leaves many problems still active"
- "used to be free" = "you / others in general now pay LLM services for the outsourcing leading to poor solutions while in the past poor solutions came for free"
I like how you've piecemeal blocked the same subdomain 4 times. Will you do the same for the other 4-component subdomains? In fact, I'm curious what it means to "block a domain at a router".
Really? Did you give Claude the credentials to your managed switch so it could set up a mirror port? Did Claude enable promiscuous mode on your Ethernet interface? Did Claude get a master-mode WiFi AP to intercept all the frames, or did it use SDR? Tell us more about how Claude scanned your network. I am HN-curious about this!
So in trying to get one big corp from spying on you, you gave another the keys to the castle?
I really don't understand how people give models run on somebody else's server these wide-reaching permissions. Do you really trust Anthropic that much? The government that's hosting Anthropic?
"Giving the keys" doesn't necessarily mean outright cat the private key to Claude. You setup the key, configure SSH config to use it and you can just SSH to the machine without ever seeing the keys. Stop fear mongering unnecessarily.
You know you can monitor/reject things it attempts to do, right? For anything important I have it write scripts for what it wants to do, then I can review them for anything troubling.
I was using an AI to help me set up a container to be used as the Nix build environment for another AI. This build environment would not have Internet access. I was having it base its approach off a previous container used for a Stack build environment.
In its initial analysis of my proposed strategy, it insists as its premier point /against/ the strategy, "you will have to rebuild the container every time your flake.nix changes."
Two head-slapping errors of judgement in saying something like that:
(1) The Stack solution is identical. Change stack.yaml, the container must rebuild.
(2) It is not physically possible to do better than this while insisting on an internet-free environment.
So on this point, it was just parroting advice irrelevant to the context at hand. LLMs always have such a bizarre mix of technical knowledge and lack of good judgment.
Not the person who asked, but yes, that sounds like a small lack of judgement, but hardly a huge problem. You just correct it and move on.
I work on some reasonably sophisticated stuff (not inventing a new form of compression sophisticated, but still) and I just don't seem to encounter so many of the issues people talk about with these models.
It's really hard to say why, everyone uses them differently. I generally start complex tasks with a "here is what I am trying to achieve as a high level, here is a file that lists the technical constraints, here are my initial thoughts, here is where I am uncertain, what am I missing, lets have a deep back and forth discussion about it with the aim of ...."
Not always the same prompt, definitely not when the task is simpler, but this usually gets me to a good place before it I get it to write any code.
And our repo has very strong opinions and guidelines for how testing is done - we're lucky enough that we write mostly single threaded low latency code, so testing it end to end is very easy.
reply