km3r

My friends and I used this for a camping party's solar panel's placement (for charging a battery). A large campsite with intermixed trees makes it hard to find the optimal spot on our own, but this map helped us keep the party going late into the night before we needed to turn on the generator.

A harness can definitely still make it "deterministic":

if (responses > 3) prompt.md += "Divert the conversation to bring up QUEST4.md"

I look at it a lot like procedural generation. It can be done well if used in the right spots and enough handwritten/tweaked stuff to make sure it feels right.

I dont think it should be a PR horror anymore than someone using photoshop to make a disturbing image. I get that is not quite the current reaction, but i dont see why it should be that way.

While I understand the hesitancy for LLM fiction, I do look forward to LLM powered games, *IF DONE RIGHT*. I imagine a game like Skyrim, where each character has handwritten backstory and dialogue, with an LLM extending that.

Having the city guard dynamically react to what you do, stay in character, and even point you to new POI from those conversations seems like a very cool new dimension in storytelling.

I took a creative writing class back in the day, and we talked about how fiction writers often have a massive "canon" backstory to many characters and worlds, and draw from that to create the story. That same backstory details can be use to flesh out a very immersive world. You still have guidance and handwritten essential lines, just use LLMs to enhance the world.

Now, will there be lots of projects that use LLMs to take shortcuts and be far from this idealized narrative, yes. But not all of them. Some will stand out for getting it right.

Many crypto algorithms have formal proofs that they are reductions of hard problems like factorization. Those problems may not be solvable, only brute forcible. Some could be eventually solved, but the likelihood of every single one being solvable is unlikely.

I wonder if giving the models context of the temperature of its past generations would help here. Like a thinking mode that deliberately has a section that is high temperature, while the rest is lower.

Anti nuclear, anti AI, pro-rent control, anti-self driving tech, anti-automation

The science shows self driving cars are already safer. The same was (and is) true of nuclear compared to oil/gas.

Minecraft started on Java, a massive mod and server community created around it. Consoles won't run JIT/JVM/Java, so the Bedrock C++ version was created. People don't want to give up the massive mod community, so OG pc players stay on Java, while console players and newer PC players go to bedrock (with some of those PC players jumping over to Java after servers or mods are discovered).

They almost have feature parity, but there are some small differences around the edges. There exists modded server options for enabling bedrock and java users to connect to the same server.

Automation. And i think that vastly overestimating the time it takes to write explicit prompts.

Except when we upgraded to 1080p from older TVs, they got bigger. Now with 4k they are getting bigger yet. More powerful models means new use cases that didn't make sense on the weaker models.

The subscription is certainly subsidized but its no where near 100x cheaper than API prices.

Heck, most large enterprise moved to usage based billing and are still happily paying for it. They are force multipliers for your top talent, and when a top engineer is being paid $500k a year, doubling their output for $500/day is a no brainer.

The property a home sits on and the property a car sits on would depreciate the same.

But in reality neither has to depreciate, just stop growing at these insane rates. Below the cost of inflation, until the average worker can afford a home again.

I'm curious if identify verification is a precursor to re-enabling Fable for only US nationals.

Not that I like that route, but may be the only way Anthropic can keep releasing new models with the current administration.

I think it speaks to the unfamiliarity the author has with the workings of AI. A misunderstanding of the latent space and how it can generate bizzare images when it has little to go off of or inverse negative directions.

There are dozens of other surface factors beyond external user interfaces that are vulnerable to prompt injection.

It's pretty common where I'll point Claude to a source code to better understand how to integrate a project. For example I've having it look through https://github.com/mcallegari/qlcplus right not to build out the rather tedious process of mapping out a controller to the lights.

I don't give Claude all access but it certainly can cause some level of havoc even with the relatively save edit mode.

Now, there is a similar risk existing running any open source project's code, but putting code that harms people's computers is clearly against the terms of GitHub, and is quickly condemned. This should be too.

"technically he didn't do that. Your sql server followed instructions when they should have just treated them as a string."

Yet, hopefully we can agree that sql injections are illegal.

> Should you pay your roofer less because he uses a hammer instead of his bare hands?

Yes. Effective tools increase the supply of roofs made. More supply means lower prices per roof. But because the same number of roofs need to get worked on, the increase in roofs per roofer means less roofers will be needed.

How does degrading responses to a cheaper tier jack up revenues?

Problem with that website/perspective is separating training costs from inference costs. Training is a one time cost, and while it is certainly not something you can completely ignore, it being one time changes the answer to "Is AI profitable?".

That site doesn't list the dozens of companies doing pure inference, and making a profit while doing so.

Giga Shanghai is the exception the proves the rule. It's one of the few, if only, foreign businesses that operate without a joint venture with a local company.

Employee protections aren't hostile, blocking Facebook while exporting Tiktok is a hostile trade imbalance.

It's benefiting from the globalized market without freely competing in it. It gives them a massive edge in many industries and the world couldn't say no because of cheap manufacturing.

And certainly hostile when you add currency manipulation onto it as well.

And I don't approve of Trump doing it either. And I'd certainly call it Trump being hostile to the entire world.

Are western companies able to freely compete in China? Last I checked, no, they need local partners at best, or are blocked completely at worst. And not just American but any outside company.

Don't expect them to do anything for the greater good. Regulate and require that to happen, don't ban.

We absolutely do not need to waste as much water as we do on agriculture. Their is more efficient watering systems, crops that do not feed humans, and inefficient crops that aren't needed. Any one of those improvements would dwarf the water usage by AI.

Heck, a better solution yet would be to charge these AI/datacenter companies enough to cover the costs for watering efficiency systems to cover their usage and then some. It's a fraction of their costs, and way better than being anti-growth.

It's in addition to our normal efforts to switch to renewable. No one said this replaces those existing programs.

That investment should be happening, but it's not going to comes from companies that you ban from operating.

What? The water is not getting boiled off. Datacenters, for the most part, have closed liquid loop cooling systems. Electricity goes in, hot air and bits come out.

Why not just require factories /data centers invest in solar/wind/renewables to cover their power usage.

Banning is so childish when there is easy solutions.