FrinkleFrankle

Would you mind sharing, if you're open sourcing it?

It really depends his good it is. There are so many shows where stories just don't pay off well. I could see an AI developing a show with a complex web of throughlines kept logically consistent and fleshed out.

MCP is a tool more for security than anything else. If you give your agents access to an API key, there's a chance they can accidentally or maliciously leak that key. If the MCP server has access to the keys instead, it takes that possibility away. That's not always something you need to care about, but it is very important for some people's threat model.

I'd rather use the fancy models while absurd valuations are subsidising them and then pick up a couple grand worth of their old hardware in a few years when they're eol.

Fuck, that's smart. Thank you for the idea.

FYI, you can use brave/chrome policies to disable most of the annoying stuff in brave. It is an incredibly sleek browser when you do so.

https://support.brave.app/hc/en-us/articles/360039248271-Gro...

I've had a ZFS array running since ~2009. It's gone through upgrades and disk replacements, etc. Have not suffered a data loss in that time. ZFS I'd the goat.

I'd say anyone who chooses to kill a civilian, whether based on an order or not, is a war criminal. I really don't care if they thought they were there for a noble cause or not.

Any hope of ever expanding to Canada?

Sounds cool. Care to share it?

Windows 2000 was incredible. It was so sleek, fast and worked so much better than XP. I'm sure it still required a lot of tinkering compared to a modern OS, but I still miss it.

Sounds cool. Do you have a link or more info to share?

Brave has ad-blocking built in and policies can be used to disable any unwanted features. With Chrome going user-hostile, it's a pretty great option.

True. You'd probably go crazy as a brain disconnected from your body, regardless of what drugs they give you.. But It'd be an interesting final experience, I guess. I do hope they're getting pain killers along with the anaesthesia, though.

Would you mind sharing the relevant config?

New code will also use these tools from the get go, hopefully vastly reducing the vulnerabilities that make it to prod to begin with.

They need a complete reworking of the government. The fact is that bum-fuck states with a handful of citizens can use their senate seats to hold the country hostage. Nothing will ever get better until that is resolved.

Just because a calculator will only ever be used by a subset of the population to type 80085 and giggle, doesn't mean it can't also be used for complex calculations.

AI is a tool that can accelerate learning, or severely inhibit it. I do think the tooling is going to continue to make it easier and easier to get good output without knowing what you're doing, though.

Yeah, llms change the game for card creation. I'm trying to learn Rust (programming language) and I have Codex ingesting books/articles and generating sensible cards from them. It's able to consistently get the HTML right for syntax highlighting in examples too.

In the video, it was clearly children and other civilians. I can't find it at the moment.

Here's an article from Reuters about the civilian deaths. You can also pull up satellite images and see for yourself that the country is being levelled. That's not something you do if you're seeking specific individuals. There's just no excuse for killing civilians.

https://www.reuters.com/video/watch/idRW842708112024RP1/

You know, both sides can be bad. They're both led by bad people who do bad things and some good things. I've watched the Oct 10th attack videos. They're horrific. I've also watched the videos of civilian buildings in Palestine being have their roofs "knocked on" by a missile, followed shortly after by demolition by additional missiles.. And the Israeli solders dropping grenades on tents.. And the firsthand accounts of doctors talking of children and infants being shot through the head with sniper rounds.

Both country's governments are in the wrong and their civilians are suffering because of it.

It also needs to be able to ensure the signals are coming from a human that actually has authority to command it. Don't really want it taking hand signals from anyone.

That's kind of what learning to code is like, though. I assume you're using an llm because you don't know enough to do it entirely on your own. At least that's where I'm at and I've had similar experiences to you. I was trying to write a Rust program and I was able to get something in a working state, but wasn't confident it was secure.

I've found getting the llm to ingest high quality posts/books about the subject and use those to generate anki cards has helped a lot.

I've always struggled to learn from that sort of content on my own. That was leading me to miss some fundamental concepts.

I expect to restart my project several more times as I find out more of what I need to know to write good code.

Working with llms has made this so much easier. It surfaces ideas and concepts I had no idea about and makes it easy to convert them to an ingestible form for actual memorization. It makes cards with full syntax highlighting. It's delightful.

What are those sleeping earbuds?

If you want to do this another way, Tailscale funnel can send public traffic into your tailnet Traefik supports pulling the Tailscale cert from its socket.

For those that don't want to build their own addon, Cold turkey Blocker works quite well. It supports multiple browsers and can block apps too.

I'm not affiliated with them, but it has helped me when I really need to focus.

https://getcoldturkey.com/

Care to share your setup?

Brave on desktop is also fantastic. Especially if you use a policy config to remove annoyances and harden it further.

I'm using it to help me build what I want and learn how. It being incorrect and needing questioning isn't that bad, so long as you ARE questioning it. It has brought up so many concepts, parameters, etc that would be difficult to find and learn alone. Documentation can often be very difficult to parse. Llms make it easier.

Kagi has their own AI assistant that let's you choose any model from the major, and some not so major, providers. You can even hop between them I the same chat. It is also able to search for results using Kagi. This includes any lenses you could configure.

It's worked extremely well for me. Their higher subscription was less than ChatGPT + Kagi. I haven't used Gemini on its own interface yet to compare, though.