I agree, I think this is AI, especially based on 1 and 2. It's hard to put your finger on, and I don't know if we can know for sure. It reminds me of the writing style you see on LinkedIn i.e. seemingly optimised for engagement.

If they're not already, I wonder if LLMs will get better at disguising this (avoiding the tells, inserting mistakes etc.)

I also wonder if there comes a point where we as a culture imitate this style.

TBH, I don't like AI-generated content much too, X and many other platforms were also flooded with those, which I tend to ignore. I guess I also fall into the rabbit hole myself with the aid of AI nowadays.

Perhaps consider a public domain film for the demo?

https://en.wikipedia.org/wiki/List_of_films_in_the_public_do...

And inverted the Y-Axis too, which I still do today thanks to this game, I think.

I agree. I'm intrigued by the self-hosted option. But it is unclear whether the iOS and Android clients will stick around to consume the saved data.

Yeah, the app is really what makes this a win.

Cool project, best of luck! Agree with the other commenter that some kind of error handling or warning re: outside-of-EU availability.

Nice. As a side note, I find that Claude 3.5 Sonnet is pretty good at drawing similar ASCII diagrams from prompts.

It being dysfunctional is a convenient stick for this crowd to beat it with, but I wouldn't discount the issues. The U.S.'s allies aren't exactly thrilled with it.

> The U.S.'s allies aren't exactly thrilled with it.

Since Russia invaded Ukraine and the European countries prioritized defense, the F-35 seems to win every competitive bid.

Not any other realistic stealth options. China has the J-20 and Russia sort of has the SU-57 but that has seen limited production.

So it's far better than anything anyone else has built.

That doesn't mean anyone is thrilled with it.

Is it dysfunctional though? There have been issues with it (landing gear and helmets come to mind), but they don't seem to be out of the ordinary for fighter jet development. As for allies, they keep ordering F-35s (or at least trying to) so it seems like they're at least fine with it.

I’m curious. Scraping seems to come up a lot lately. What is everyone scraping? And why?

To add to others’ points, we can do two, more things:

1. Pretain models with any legal, scraped content. That includes updating existing models with recent data.

2. Have our own private collection of pages we’ve looked at. Then, we can search them with a local engine.

With people making LLMs act as agents in the world, the line between "scraping" and "ordinary web usage" is becoming very blurred.

Context for LLMs, and use cases uniquely enabled by LLMs, mostly I think.

There might be some truth to this, but under Ballmer's leadership, Microsoft's inflexibility re: the use of competing hardware came with its own problems. Since Nadella relaxed this policy, it's unclear to me whether you could say HW quality is worse. In any case, the significance of this policy may be overstated one way or the other.

Out of interest, what kind of cost ranges are you seeing users spend on the OpenAI API using Plandex? (if only anecdotally)

There's a pretty huge range. It's a function of how much you load into context and how long the task is. So if you dump an entire directory with 100k tokens into context and then proceed to do a task that requires 20 steps, that will cost you a lot. Maybe >$10. But a small task where you're just making a few changes and only have a few small files in context (say 5k tokens) won't cost much at all, maybe like $0.10.

I haven't done too much digging into exactly how much people who are using Plandex Cloud are spending, but I'd say the range is quite wide even among people who are using the tool frequently. Some are doing small tasks here and there and not spending much--maybe they're on track for $5-10 per month, while I'd guess some other heavy users are on track to spend hundreds per month.