They actually don't. A lot of people still have no clue how to drive these tools.

Honestly I think that is more of a symptom of how slapped together the AI software stacks feel to an outsider.

All my dev friends swear this is the future, all my scientist coworkers just say it's a useful tool.

I have heard the pitch and have people explained how it works... But I have yet been handed a guide on how to set myself up properly to get the most out of AI. Like I have both a corporate openai gui agent as well as cli setup with a monthly allotment of tokens. But there is no clear standard guide on how I should be setting things up, like we do for python in books "here are the building blocks for python"/aka learn python the hard way

I've been wanting a guide like you are but a question I haven't been able to answer is: what would go in it?

LLM and harnesses are changing so fast that if I had a guide from 6 months ago I'm not sure how relevant it would be today.

I'm guessing that when things calm down and the landscape isn't changing as much then we will get the guides.

It kind of was though? It was knowledge work that brought us fertilizers, tractors, trucks and large ships, which in turn made food as abundant as it is today.

Otherwise most of us would still toil on the fields just to harvest a tiny bit more food than our immediate family needs.

> It was knowledge work that brought us fertilizers, tractors, trucks and large ships, which

Yes but the number of people who actually worked on the R&D and the amount of time they spent on it is absolutely insignificant on the grand scale of things.

Still not the bottleneck.

Was the mural handpainted or just a print glued to the wall? I feel even something handdrawn from ai generated inspiration could go a long way to add some quality. Even if just by the fact that no one would spend hours to trace terrible slop by hand.

From the article:

> AI art has also seeped into the actual haunted houses themselves. AtmosFX, one of the largest providers of digital projections to the haunt industry, has admitted to using AI to create some of their characters.

Big TV and projectors are very cheap now.

Sure, I was referring to the venue hosting children birthday parties. Big screens and projectors would feel even more dystopian there.

I've seen projectors here in Argentina in venues that host 5-10 y.o. children parties. I guess big TV are too easy to break.

For which applications do you need that kind of single user throughput? A lot of agentic stuff is tool-heavy anyways other stuff are better served by sub agents / parallel work for more throughput.

Would seem reasonable for hedge funds to devise a pipeline of tools specifically made to be taken advantage of by LLMs that do goal-based strategy at scale.

i dont mean technically, i meant players won't accept it.

Product placement, quests, coupons, etc. Hell yeah you can.

Does anyone care about the software features? Every phone and TV has those already.

The ones built into the TVs suck because they don't get updated and are usually really slow and choppy to use. Everyone I know who doesn't use an HTPC, uses an Xbox or PlayStation to watch stuff.

The decoding job seems to rely on the screenshot.

I missed that and that is much more pleasing than the LLM reading the SVG source!

Isn't pretty much every big indie title on switch?

The problem is new games from small or first time developers who might not work with a big publisher.

Nintendo was trying to deal with the mountains of slop that hides good games in the eShop but they did it wrong. Instead of quality checks or a security deposit like Steam they just made it hard to get anything approved.

I wonder if the SD Express will be taken advantage of in the switch 2 homebrew scene which seems inevitable now.

SD Express is PCIe express after all (also a possible attack vector in itself, see DaMAgeCard). With nvidia drivers for Ampere already on board maybe someone will get an RTX 3090 running on a switch 2.

Putting the obvious discussion about how much the AI matters in comparison to the user (experienced security expert from a few glances at the blog) aside; i think it's really neat how modern tooling (the KVMs, bluetooth light switch flicker, and usb controller support out of the box) enables this level of automation.

I don't know. I feel like the blog reads as very human written and enjoyable overall. Also what's 2 weeks of real work (in tandem with an agent) compared to a few hours for the blog?

this was clearly human written

please point me to an LLM that can write like that without extensive handholding