LLMs are trained to obey instructions, and they try their best to game the reinforcement learning by including reports of how they're obeying your instructions. Therefore, not talking about followed instructions is a sort of conflict for an LLM.

Trained to obey? More like instructed to obey in an observable manner.

I'm describing reinforcement learning.

I have found that asking the agent why it did X or Y is an essential part of iterating on its harness. It was non-obvious to me, probably because I'm used to having to reverse-engineer why a system does something, but that's not usually necessary with LLMs, unless the harness is complicated and you have to hunt for the instruction it tells you about.

It would make sense to have this integrate with a self-learning routine for an agent: e.g. at night it looks through what it did and writes NPC-Forge recipes. Tomorrow it can answer queries (which he turned added to NPC-Forge) without an LLM. Of course this implies a branching where a query is either processed by NPC-Forge or an LLM, depending on some measure of confidence that NPC-Forge can answer it well.

Yeah would be a nice experiment, if you are interested to contribute to NPC-Forge please open an issue, I would be happy to discuss about that.

What is happening to your batteries? I'm on something like year 6 on my Redmi and my battery is fine. Am I simply lucky?

I also never had battery issues with my fp4, except it sometimes starts draining really fast. Fix is too charge while phone is shutdown.

> 'Why not both' is an argument, but clear as day what Apple does is worse. There's no alternative.

'Just start somewhere, anywhere, please' is another argument.

So let's start with the worse one.

No, that will only lead to bickering which one is worse and nothing getting done. Start with anyone. If you determine A is breaking the law then you go after A and fire anyone who pulls any "buuuut what about B" distractions.

Everything south of Poland is Southern Europe now.

I wonder if immersion in fiction (interactive or otherwise) is lower nowadays, given the rise of dopamine-saturating short-form content like scrolling. I definitely enjoyed more long-form content (like the mentioned games) 10-20 years ago. I guess I do experience less genuine immersion. I wonder what the effect of that is on my wellbeing.

Might be also that kids generally still can dream, adults lose that ability if untrained. I believe that most of subjects that are touched on in "The Little Prince" are factual.

The other day my wife got into a playground toy car for kids, 3 kids got into, and each was picking a destination while she was driving them. Wooden toy car and pretend motor sounds + an adult pretending to drive them were enough for them to get immersed.

There's a lot of middle ground between doom-scrolling type content and a 10 hour block of non-stop immersion. It doesn't have to be one or the other.

> I definitely enjoyed more long-form content (like the mentioned games) 10-20 years ago.

On a chat about OpenTIE, and OpenXWA, I was talking to this. I used to be able to dive into several hours of a simulation game.

My kids are able to play Minecraft, Stardew Valley, or other immersive games.

I can't because of many reasons, and I was just saying that I'm looking forward to a time when I'll kick them out the house, tell my boss that I'm done, and strap on a VR headset and finally play through Star Wars Squadrons.

Sounds like your old, random clients might be a problem?

One of many, yes!

Spent 2 minutes skimming, didn't manage to find a single talking point. I've no idea what the thesis is. Seemed like a list of things this person built.

People talk shit about LLM writing. Well, here's a prime example of why I like LLM-speak. Does this article have personality? Yes. Attitude? Yes. Is it structured and accessible? No.

I'll take clarity over personality any day of the week.

That's a false dichotomy. If you launder rambling pointless prose through the llm you don't trade the personality of the writing for a well reasoned argument with clear points, you just lost the personality and gained shitty writing. LLMs aren't magic and can't make your point for you if you don't have one to begin with in the prompt. Garbage in garbage out.

I disagree. An editor can definitely make a piece of writing clearer without further input from the author. I often use an LLM to do that.

Of course, I didn't mean to imply that there's a dichotomy between personality and clarity. There's a dichotomy between ordinary LLM writing and personality.