… What?

Did you forget your /s tag

If that’s all you want to do, one of the cheaper Ubiquiti managed gateways would probably work and not break the bank.

If you want to tinker even harder, an open source router running https://openwrt.org/ (or even their own device) may be a good option.

the difference between unqualified and exceptionally unqualified means very little, neither of them can accomplish their basic tasks.

This is exactly how most developers are being asked to use it, it’s literally how most of the IDE integrations work.

The vast majority of people are unqualified individuals.

If the AI is writing ALL the code for an entire application it would be a problem, but as an assistant to a programmer, if it spits out a single line or even a small function, you can read it over very quickly to validate it before moving on to the next component.

Why?

You aren’t going to find a useful AI system for personal use in Finance, you simply don’t have the scale needed to benefit from it. You don’t make enough transactions per month that looking over it yourself is going to be any slower than reading the AI summary.

The question as with most process optimization and data analysis is, what’s the actual result you’re hoping for? If you want it to be able to summarize WALMART, WAL-MART and WMART so you can see those numbers added together, you already know you spent a lot at Walmart. Whare are you going to actually do with that information?

Saving money doesn’t really need an AI, there really aren’t many ways to cut budgets down short of paying attention to the most obvious spending problems (Too much housing, too much vehicle, too much food (especially eating out), and too much entertainment(too many subscription platforms))

It’s usually a far better investment of time to improve your earning power (upskill, change jobs, add hours, etc.)

Cutting $40 per month from your budget by not going to the movies every week just isn’t going to have the impact you need in your life.

Our ERP system that is used for Vacation entry doesn’t have that, it wants start date, end date, hours, and vacation type code. We have a small number of employees who work on stat holidays, so defaulting to all users needing that wouldn’t even work.

The LLM fix is cheap as shit compared to buying an entirely new system. It costs less than half a cent per submission. The power use for a single query is nothing, and this request isn’t some crazy agentic thing that’s using a million tokens or anything, more like 500-1000 tokens combined input and output.

Normally I’d agree, and we used some of that in the original form (like maximum hours, checking for negative submissions, etc.) but requests don’t always follow simple logic and more complex logic just led to failures every time a user did something other than take a standard full day off.

Some employees work 7 hours, while others are 7.5, some have flex days and hours that change that, sometimes requests are only for part days, sometimes they may use multiple leave types to cover one off period.

I spent a few hours writing and testing the prompt against previous submissions to fine tune it.

So far it’s detected every submission error in the two weeks it’s been running, with only one false positive.

I just implemented an LLM in a vacation request process precisely because the employees are stupid as fuck.

We were getting like 10% of requests coming in with the wrong number of hours requested because people can’t fucking count properly, or understand that you do not need to use vacation hours for statutory holidays. This is despite the form having a calculator and also showing in bright red any stat holidays inside the dates of the request.

Now the LLM checks if the dates, hours, and note from the employee add up to something reasonable. If not it goes to a human to review. We just had a human reviewing every single request before this, because it was causing so many issues, an hour or two each week.

Longevity has been a bit of a strange argument to me, I already re-use my old laptops. My two previous devices are in active use by my kids. My devices usually get 10+ total years each.

Fuck me that price… I know it’s a great company, but the framework-premium is like $1000-1500 on that hardware

AMD 370 w/ the 5070, 2TB drive and 64GB of ram is like $5000 CDN

You can get a similar specs from Lenovo or Asus for under $3500

I’d still like to get one, but… I can’t justify that. It’s literally $1000 for just the Nvidia 5070 graphics module, and it’s still only 8gb of VRAM. That’s more expensive than a desktop 5070($800ish) with 12GB of VRAM and you can get a desktop 5070ti for only $1100 which has 16gb of VRAM.

I really like framework, but I can’t put that much money extra towards one or it’s literally going to be coming out of my food budget.

I’m due for an upgrade to my 3060 laptop, but… I just can’t do it.

Even if you could shave off 50% at idle, you’re talking about like $0.10 per day in power savings. Is it really worth spending any time on that?

Now that’s some grade A uplifting news.

What a hero

I don’t disagree with you that LLMs don’t reason. I disagree that all Humans can or do reason.

I’ve met far too many people I wouldn’t trust to give me a reasoned response.

Some people simply lack that capacity entirely, some just don’t care enough to spend the effort on it, while others are trying to deceive me intentionally.

I’d really like to see a time relevance rule.

Uplifting news from months or years ago isn’t what I’m looking for, I want to see the good happening in the world right now.

Would it be okay for me to post Ozzie Osbourne news from two months ago?

No, because freshness of news does matter.