I've got something similar but I call them threads. I work with a number of different contexts and my context discipline is bad so I needed a way to hand off work planned on one context but needs to be executed from another. I wanted a little bit of order to the chaos, so my threads skill will add and search issues created in my local forgejo repo. Gives me a convenient way to explicitly save session state to be picked up later.

I've got a separate script which parses the jsonl files that claude creates for sessions and indexes them in a local database for longer term searchability. A number of times I've found myself needing some detail I knew existed in some conversation history, but CC is pretty bad and slow at searching through the flat files for relevant content. This makes that process much faster and more consistent. Again, this is due to my lack of discipline with contexts. I'll be working with my recipe planner context and have a random idea that I just iterate with right there. Later I'll never remember that idea started from the recipe context. With this setup I don't have to.

I got the same results you did. I think this is testing our monitors more so than our eyes. Given the forum we're on, I expect far better than average display devices being used which could help explain why basically everyone is doing far, far better than "average" according to the site.

Politics has always been a lame excuse. If there's an article shitting on California's politics, it doesn't get flagged and there is no talk about "no politics on HN". Just tons of "California Bad" posts. If there's an article praising something political in Austin, TX. Same thing. No complaints about politics. Lots of posts about "California Bad". It's almost like the problem isn't politics. But the "politics" a certain segment of HN doesn't like.

I've been having CC identify LLMisms in generated text. It does a decent job, but has no idea that em-dashes are sus.

https://claude.ai/share/8fa5de6a-e79d-414c-834f-9bc9aa87c9bc

I can not stand that I'm expected to adjust my use of em-dashes because LLMs use them (incorrectly, typically). It brings up all these feelings from my younger punk / indie days when normies would get into a band we were into, and then we were expected to not like that band anymore. Since then I've tried to abide by what I call the Farting Billion Principle. People shouldn't have to change their ways everytime a billionaire farts.

This is no different than making changes in any micro-services environment. You have to be careful. You've got existing contracts with other services and typically you don't just change things like that. If your environment is large enough to actually need micro-services, that means the lines of communication between the owner of the service and the consumers of the service have exploded to the point any change is basically impossible. So when you "rename" a field. You add a new field and maintain the old one to allow consumers of your service to transition (prompted by deprecated warnings) gracefully. You monitor when your old value is no longer referenced and then you remove it.

It's also telling that none of your tests caught the issue. Why don't you have consumer like tests of your services? If after every change, you're testing your micro-service against what your consumers are actually sending you failures like this show up quite easily. This isn't a failure of vibe coding. This is a failure of properly architecting and testing your micro-services. It happens all the time when companies just try to blindly follow what Netflix engineers are doing without understanding the nuance and tradeoffs.

And then blew up the deficit and started our massive accumulation of debt. A pattern gleefully followed by every single Republican administration since. Every single Democratic administration since has reduced the deficit the "spend and give tax breaks" Republicans have run up. But it's a losing battle clearly.

Carter reduced the deficit as well until the recession hit in 1979 and tax revenues decreased.

I was quite happy with Ubiquity for a while, but their cloud push and constantly moving and hiding features in their UI is driving me mad. Power isn't the issue since I got the UDM-SE. Mikrotik came up as the next router I'll be buying. I just want consistent CLI configuration at this point. Stop moving my cheese and forcing features I don't want.

A buddy of mine recently got a suspicious request which I'm pretty sure is how these NK workers are getting jobs. In this case, the dev is allegedly from Japan. But I don't think the NK folk are out there proudly stating they are from NK.

"Thank you for your reply. You’ll only need to spend about 1–2 hours maximum in a day for our collaboration.

We need a person who has experience in software development. so I tried to find a collaborator on github and also found your profile on it.

I will explain why I'm looking for a collaborator.

The reason is that the job market between the US and Japan is significantly different - often 2 to 3 times in rates. Because of this, I focused on working with US clients. I usually work at night and sleep during the day due to the time zone difference. However, even though I adjust my schedule, US clients often hesitate to hire me because they're uncomfortable with the time zone difference or concerned about communication due to our non-native English.

To solve this, I tried to collaborate with an US developer who communicates with clients, while I focus on the development work. You wouldn't need to develop anything yourself unless you want. You don’t need to develop any code or communicate with the client. All you need to do is attend the meetings on video calls. You’ll only need to spend about 1–2 hours maximum in a day for our collaboration.

In return for your participation, I’d like to propose the following arrangement: for the first job we secure, we’ll split the total income 50/50 after taxes. Starting from the second job, you’ll receive 30% and I’ll receive 70% of the total income.

I'm not looking for a random US person - I'm specifically looking for someone with solid development experience. Even though I don't require any coding from the collaborator, without development experience they can't handle client communication properly or understand project requirements.

That's why I found your profile on GitHub and decided to reach out to you.

Could we have a meeting to discuss more in more detail? I have a clear strategy to get a success and looking forward to your reply"

You're wrong. These laws aren't very long. You should read them instead of just passing around incorrect assumptions.

Mine is radically off as well. Says I've got a GeForce 980 or equivalent with 4GB instead of a 5090. I'm guessing the detection only really works on Chromium based browsers.