Hacker Newsnew | past | comments | ask | show | jobs | submit | pinkgolem's commentslogin

I mean, i struggle with spelling/wording and ask the LLM to proofread a lot.

I often send out the LLM version, but still check if it contains the original thoughts correctly.

It's not a bad way to extend your vocabulary & catch spelling mistakes


> I often send out the LLM version, but still check if it contains the original thoughts correctly.

Please don’t do this. You probably aren’t aware of how bad this can land. It’s not just about containing your original thoughts, it’s about the verbosity, repetitiveness, and absurdity of it all.

Grammarly is a much better tool for these kinds of purposes, and it actually guides and teaches you to improve your writing along the way.


The irony that this response has a very common LLMism...


Grammarly the honeypot?


You seem to be referring to something specific I’m not aware of, could you elaborate?

A Google search didn’t reveal anything specific other than them using famous author names for expert review.


It's the nature of the product itself. It's a key logger software. That's literally what it does -- take every input on your computer and route it to their servers.


Right, I was just confused by your use of the word honeypot.

“keylogger mode” is optional, and to my understanding, you always see a visual indicator in the text area.

it doesn’t take every input as far as I know, and security firms don’t consider it a threat.

but point taken, it’s not for people with privacy concerns.


It installs itself as an accessibility tool, which requires special user permissions. With these permissions, it sees literally every keystroke you make (except, in some cases on some OSs, system password prompts). The visual indicator is just their UI.

Regarding "honeypot" -- that's also what a honeypot is. They provide a service you want, then collect data. We have to take their word that they're only using this data to train their AI (which, btw, they are upfront about -- they log everything and feed it into their training. it's in their TOS).


Isn’t a honeypot some decoy website / service / whatever that presents itself as legit, and then once you register / interact with it you’re caught in whatever they want to do?

Eg FBI putting up fake “buy drugs online” sites and logging your info once you place the (fake) order.


It is deception, but it doesn't have to be decoy or fraudulent. It could actually provide the service or deliver goods. The point is that the operator isn't running it for the reason they say they are, but rather to gather info or whatever. Specifically in cyber defense a honeypot is sometimes a fake server that serves as an intrusion detection alarm, but that's actually the odd one out when you look at how the term is used more broadly.


Verbosity and repetitiveness? Which tools are you using?

Tell it that you want a succinct professional email and it will do that. Give it examples of your own writing and it will match that style. If there's something you don't like, tell it to rewrite the part differently.

Theses are literally the things language models are best at.


> Tell it that you want a succinct professional email and it will do that. Give it examples of your own writing and it will match that style.

This is not what the parent I replied to indicated, nor what people usually do.


There's no reason to assume that their output is as bad as whatever you have come to expect.


You don't need a fake extended vocabulary. Just communicate directly and honestly. Underlining spelling errors as you type has been a standard feature of email software for nearly three decades.


Nah man, it has been career limiting before and I have gotten bad feedback for it my whole life...

I keep the LLM close to the original text content wise, but feedback was/is fantastic


> I often send out the LLM version

The problem is that you lose your voice and adopt one that your audience knows all too well (and knows it isn’t yours). It makes your audience feel like you aren’t listening to them (even though you are!), because they feel like they’re talking to an LLM.


I'm pretty sure most non-native speakers (one here) do the same. I'm not talking about three-paragraph-long Slack thread, but even a single message where I feel otherwise unable to convey what I need _the way_ I want.


As someone with oncall yesterday it was a fun experience, but you noticed quickly that everything .de was down and then it was just a waiting game.

We had a short discussion about migrating to .com, but decided risk != reward as no one would know the new tld

I assume there are a couple people working for denic who had a stressfull night..


Do you have a writeup what problems you ran into?


We do, let me check with my team and post it here.

There were many issues. On top of my mind was, after a DR drill where in a VM was booted, node did not join the cluster. Apart from that bunch of issues due to etcd, longhorn.

Another major one was the CNI stopped work for a particular node. Garbage collection for images was another, we labelled the images, it would still remove then from the node.

Bunch of these kind of issues when our requirement is fairly straightforward. Therefore we are working towards a strip down version.

There is lot of operation complexity in general and most of us can do without.


I've found a lot of issues come through somewhat naive networking setup - which is encouraged by the "just yolo it" installation instruction in the documentation. If you want to start understanding what's going on you'll end up in very weird corners very quickly. Also, if you don't want the API endpoints available to the world the documentation is not much help.

I've found things more stable if you can give a dedicated interface just for internal k3s communication. It can be a bridge interface on top of a vlan interface - but not the vlan interface itself, or some things will break in very interesting ways. Also, even when using IPv6, just stick with internal IPs and nat everything - touching internal IP ranges is no fun. Plus, if there's a chance you'd ever want to use dual stack, set it up with internal v6 addresses, and just don't use the v6 addresses for now. There's also a lot of unintuitive behaviour around dual stack networking - and lots of areas where documentation is just plain wrong.

I'm scripting our stuff with ansible - one of the more useful things was the realisation that in some areas changes which shouldn't break anything can lead to cluster communication being interrupted, which is a very interesting thing to deal with, especially when you can't pin it to that change that didn't touch anything close to that, and therefore should not be responsible. I've learned, and sprinkled checks to make sure all members can still reach each other in there now, so that at least when I break it on changes I directly know why.


Thats might be true.

In enterprise setup when you are dpeloying on customer, airgapped, no access to internet and repositories, you generally dont have control over the infrastructure. It can be as hostile as you can think of.


Meanwhile our architecture team that surely supported 0 real life k8s went with no vendor, on premises deployments, claiming it was as easy as booting a VM, after 2y, there is 2 apps running and supposedly all future apps will be deployed on that cluster.

I cannot wait for the end of this month to leave that place.


Anything real world tech is hard.

We are hiring, btw.


At least in Germany in B2B contracts that might be possible.

For b2c, no chance


I think the example is still valid, orgs will not change if the still get what they want from you


I joined a startup 3 years ago as employe 6. everyone was using windows but I was used to working with macos so I got a mac.

Took a year till everyone was using a Mac.


Most places I've worked I've had the autonomy to re-install my machine to whatever OS I worked with, so was always Debian Linux.

Then I joined some mega-corp, with it's structures and set systems, so opted for a Macbook.

Worst mistake of my life, OSX is horrid, I'd rather use Windows.


Lack of knowledge about something can certainly make it seem horrid. It just means you have a lot to learn. There is a reason so many of us engineers with decades of experience in Windows, MacOS (and OSX), and Linux use a Macbook Pro as our daily driver.


That is a really really shitty comment. Because their choice is different to yours they have a lack of knowledge?

FYI I had a top class developer working for me about 5 years ago, who saw me using WSL and VScode... they had a Windows machine and several macs due to the nature if their work. A week later they were on Windows every day, only using apple for apple builds.

The answer is, we don't all do the same kind of work. There is a reason so many engineers working in your field use mac. Guessing you are a Web developer?


It's funny you say this because the more I learned about mac the more I understood its limitations in being as good an operating system as e.g. Arch.

I know a lot of engineers. Some daily osx, some daily Linux. I'm not seeing any particular correlation in knowledge or skill - except perhaps slightly in the osx people's disfavor.


Maybe you can install homebrew and open source apps to make it more Linux like, but you'll still be stuck with Mac OS's shonky window and task management UI unfortunately.


Install SizeUp. I paid $10 10 years ago and have been using it ever since. Far better window management than any Linux distro I've used. (and better than windows but that's not saying much)

edit: 13 years ago


I like Divvy because it supports more than just halves and quarters — I use a 7×6 grid so my browser can be wider than my editor and terminal: https://mizage.com/divvy/

Pairs well with Stay to make windows automatically return to their assigned layout when plugging/unplugging my external display: https://cordlessdog.com/stay/


Tbh, my one server paperless deployment has a higher uptime then most services.

If your scaling need is not that high, you can get very far with a single server


In single threaded workloads, still impressive


Nah locally is fine, if you have a good 6ghz coverage, but that means a hotspot in every second room


I don’t have WiFi 6E, just 6 (5ghz). If the input latency is imperceptible for productivity work, and the resolution matches my laptop resolution without pixelation, then why the heck am I not streaming my powerhouse main pc?

Weekend project.


>Take off with the assurance your will will be done

* Whatever the ai things is your will, will be done in a way the ai things is correct...


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: