tiku

Just don't set it to your home directory lol.

To be fair, it is really simple to build your own proxy. I built a custom authentication layer with logging and limits for Dify MCP with just 2 prompts in Kimi. Later built it out with database limts etc.

Why not use crypto. Each identification is a transaction from your wallet to the other party. After the session or once per day send back the token. We are so stupid relying on apple/google.

Netherlands also.

So by this logic my auto complete function before Ai also wrote 50% of my code and is not made by me, because I didn't type it.

What should matter is intent, the human that gives the orders.

I'm reporting every spamm mail that I get through Gmail from Gmail accounts but it doesn't seem to help!

I believe it doesn't matter, other companies will copy or improve it. The same happend with clawdbot, the amount of clones in a month was insane.

Went with Kimi and z.ai a while back, no regrets yet. When I started using it the limit was far away but Anthropic moves the goalposts, tried to get my money back but they rejected it. Lesson learned, never buy a full year.

Yeah for dev purposes perhaps. Production would be another story.

Im using z.ai when I hit my Claude limit after a few questions..drops in easily in Claude code.

I hate that my M5 with 24 gb has so much trouble with these models. Not getting any good speeds, even with simple models.

A lot of trial and error. I've built graphical tools with GD in PHP, the difficult part for me what that the coordinates where inverted.. I only knew how to draw lines and pixels, but I got the job done.

I remember the LinkedIn app that got all your contacts from your phone and tried to add them to your network. I had random people from internet-deals (local craigslist) that where popping up. So strange that this was allowed.

Thanks, I was already distracted after the first sentence, hoping there would be a good explanation.

I still hate Claude for turning down limits. I use z.ai in Claude code now, haven't hit the limit yet.

Perhaps time to dig out a channel to cut across the land there? To add some second path.

Personally I'm so disappointed about the state of local AI. Only old models run "decent" but decent is way to slow to be usable.

Depends on your measurements. If you measure with 1 cm it is longer than if measure with 10 cm.

Meanwhile the Netherlands is selling the DigiD system to foreign companies and today it came out that we are also are going to outsource of of our key tax systems to an American company.

Ive made different solution for my Laravel projects, saving them to the db encrypted. So the only thing living in the .env is db settings. 1 unencrypted record in the settings table with the key.

Won't stop any seasoned hacker but it will stop the automated scripts (for now) to easily get the other keys.

So true. It is a exoskeleton for all my tedious tasks. I don't want to make a html template. I just want to type, make that template like on that page but this and this data.

Only unique data will be worth something.

When orchestrating you need to have a damn good plan / requirements. And then I'm typing or thinking a lot beforehand. And at the end it's never 100% what you want.

That is why I'm going back to per function/small scope ai questions.

Does that just use 2 agents at the same time or something like that?

So us normal pro accounts have slow mode. Thanks anthropic.

I'm currently testing Kimi2.5 with cli, works great and fast. Even comes with a web interface so you can communicate with you kimi-cli instance (remote even if you use vpn).

Napster.. so what happens if peerweb.lol goes down?

Run it from a VM, use a hotspot named the same as your home connection. Lots of options!

Now find the tools used by the Egyptians or the people before that lived there and made the tool markings..

So now I can stop slouching and biting my nails. 2026 is here!

I've built a react invoicing tool, I can't help but think that it probably ripped of a bunch of code. I've added my own touch now but it seems like it was wat faster with generation.but then again, it's hardly rocket science.