itsdavesanders

Myself and a couple friends bought this device a few weeks ago and with the firmware being released, its an amazing device.

I love the idea of cheaper Chinese music hardware with the ability for open source firmware and apps to be loaded into them. I hope the success of this sees a sampler from M-Wave - I'd love a Chinese 404 or MPC...

This is why I spent a lot of time building a design system first, that I can then re-use in my projects. My system is built out of properly CSS tokenized and organized Vue components, and the agent has instructions that it cannot create HTML that isn't made of components - and that if it needs a different UX (which I will have designed with it), then it needs to be built as a component.

What's nice is that you can then write linters for rando CSS and component violations most of the time.

Even then, you sometimes still have to beat it down when it goes rogue - but it does tend to bring my daily frustration down a bit. (Along with a process during design to preview these layouts before they get to a coding agent.)

And once you have a design system that suits your needs, its easy to add in as skills/scripts to any new project. I keep a github repo with all of these bits and bobs, with an agents.md that teaches the agent how to use the repo.

But in short: if the LLM keeps screwing it up, build tools and define it once - stop trying to prompt your way out of it every time.

Yeah. That difference is profit.

Someone ripping a copy of The Odyssey for watching in their own home is a loss of profit for the company's lawyers, and must be punished to the fullest extent of the law.

A company ripping off all of humanity to create profit for their company's lawyers is perfectly fine.

There's nothing magic here. Its money deciding the rules. Like it always has.

And "The A-Team"

Yes but you can’t watch Netflix on a Moleskin.

If all you’re doing is writing then it’s not worth it, but for me the iPad is a fantastic piece of kit that can consume media, create media, and of all types, writing to fully mastered music albums.

And throughout those two decades they also canned a ton of projects, including maybe some good ones.

I’d say they are batting .250 like everyone else.

- AI works 24 hours a day

- AI isn't bound by need for rest, vacations, sick days, or labor laws

- AI doesn't bounce from company to company, taking your business knowledge with it (actually this isn't technically true based on the practices of AI companies, but that's not a technical requirement)

- AI doesn't join a union and stop work in demand for higher pay or workers rights

This is what CEOS and capitalists are thinking. For capital, the best outcome is to not have any labor at all. And if you can do that when your competitors can't, then you have a huge market advantage. (Slop notwithstanding)

I'm not saying this is a "good thing" but this is what drives the market. Less labor revenue in the long term and money printing machines.

This is exactly why unions are needed. To negotiate for extra benefits and share of the effort for their labor.

I'd like to see some software that can be used to connect and hack them (which has been already proven possible), erase any data, then fill their memory with tons and tons of out of place images. Take real traffic images, flip them in different orientations to slow down future training, throw in nonsense, etc. Leaving them in place and making them unreliable is a better solution - they can always put up another camera.

A Little Brother solution: they want data, give them so much bad data the rest of their data becomes worthless. But it only works on a mass scale.

I have to say this is one of my favorite things about local Qwen and Qwen code, it seems a heck of a lot faster that Claude and feels better to work with.

Problem is it is nowhere near as smart, so what speed I get in conversation gets killed by iteration.

Its pretty easy with a system like Readwise. Yes, that's ANOTHER system, but its one system to quickly just add articles like these to an inbox and read them another time, in plain text.

Of course, it doesn't work 100% and certain sites are hostile to it and do stupid javascript tricks "for the views".

Mostly, I use it to put it on a reading list later, and to get around really, really abusive ad driven sites.

Remember, Open Weight doesn't necc. mean local. They are probably running on a larger version online, closer to Claude specs. (lol and probably distilled from Claude)

at my mcdonalds you're lucky if they even get the bun on at all...

This is how I feel about AI coding in general. I see business users getting excited about building 60% of an application themselves - but have zero clue that the remaining 40% will take 5x as long, and oh, by the way, you now have to maintain it for the next decade - and what happens when you leave and no one can figure out why payroll doesn't work anymore?

Coding has always been the easy bit.

I didn’t take it that way at all. I took it as “I was blinded from the actual solution because my vision was artificially narrow due to my past experiences with this person.” They didn’t ask for help, their partner intervened for them with a completely different and more direct approach.

I have a kid going thru this right now. It’s very disheartening and frustrating to see, because even with coaching and help, they don’t see the help and suggestions as solutions because they simply can’t see it. And as a parent you don’t want to have to intervene, you want them to learn how to dig their way out of it. But it’s tough to get them to dig when they don’t believe in shovels.

Probably because it’s not a “US league?”

I might consider F1 in that case as it has gained in popularity a lot, and technically it’s owned by a U.S. company, but I’d never think of it as a U.S. league.

It looks like it’s a HN-like for stocks / market opinions.

Claude can use use tools to do that, and some different code indexer MCPs work, but that depends on the LLM doing the coding to make the right searches to find the code. If you are in a project where your helper functions or shared libs are scattered everywhere it’s a lot harder.

Just like with humans it definitely works better if you follow good naming conventions and file patterns. And even then I tend to make sure to just include the important files in the context or clue the LLM in during the prompt.

It also depends on what language you use. A LOT. During the day I use LLMs with dotnet and it’s pretty rough compared to when I’m using rails on my side projects. Dotnet requires a lot more prompting and hand holding, both due to its complexity but also due to how much more verbose it is.

Once AI is fully writing software autonomously and humans don’t need to see that code anymore, then why not just have AI write iteratively more efficient assembly? (Meaning make the software work then turn it over to an optimization agent that can drive out all inefficiencies until perfection.)

Those efficiencies will eventually be driven into all parts of the system. AI will be able to run the most efficient code on the most efficiently designed processors, that can be designed with the knowledge that only AI is going to use them. And then we can remove ALL the weird abstractions and accommodations we had to make for human brains.

I’m not saying it will happen tomorrow but language choice is just a temporary concern.

I keep seeing this argument pop up about “should Obama be prosecuted” like it’s some sort of “gotcha liberal!”

And as a liberal I think “hell YES he should be prosecuted!” The government shouldn’t just go around killing citizens without due process. I don’t care what letter is by their name.

I worked with a Navy Vet in the 1990s that would play Harpoon and reported that it was pretty much just like sitting in the sub looking at his displays. I don’t know how true that was, but I remember them marketing it as something that the Navy used in training.

I loaded it up once and decided that I really wasn’t into games I had to study for.

I think the counter point to that is that we have think tanks and political organizations who have rich donors with which to hire high power law firms, who find the regulation they want to axe, and then search the country for a case with standing and then pursue those cases until the regulation dies.

You are right that it won’t be the little guys doing this, but they might be represented by very powerful organizations who take down laws professionally and are doing so for their own benefit. And with the way politics has entered everything, who knows which things will be targeted next, or what new cruelties they care to inflict.

At the same time, again due to the current political climate, it doesn’t do us any good to have all the rules thrash back and forth with each new administration. This is what we get as we get more and more polarized and laws aren’t being written with compromise. Congress and elections need serious reform.

And imagine how our allies feel. If you can’t count on the U.S. for more than about 3 years at a time, then you quickly move away from them and insure you aren’t so tied to them that a foreign election suddenly makes you vulnerable. Which then makes everyone weaker as a whole and easier to pick off.

Which is why U.S. foreign adversaries have been actively sowing chaos for a decade.

IS it cheaper? Better, maybe, depending on the restaurant. But I can’t see how it’s cheaper when you have to hire and insure drivers, manage shifts, deal with delivery areas, fuel costs, more accounting, etc etc.

Also I live in a pretty good sized city of about 350k in our metro area, and before these delivery services only the national pizza places delivered. When I moved here from a larger city I was shocked there wasn’t a single Chinese delivery place. So I’m thinking that the costs and management were just too high.

The right model might be the Waiter on the Way model, which hires regular drivers but can offer the service turnkey. But there needs to be more of those, and there doesn’t seem to be for some reason.

I find it strange that they would write "The hollowing out of US manufacturing has led to social and political division and left us in a precarious place geopolitically." And then suggest the answer to that is robotics and ML, which does nothing but exacerbate the social and political divisions - unless government and enterprise make the hard choices to provide a real safety net. And then, if we do that, it doesn't matter if the US is excelling in manufacturing as a source of revenue or not - providing revenue to fund these programs is coming in from somewhere, the source is far less important.