atroche

you could help it along by providing clues about the domain in the prompt. including what various proper nouns might indicate (assuming they're not chosen completely at random, and encode at least some meaning).

and you might find the scores it gives back about its confidence are useful for escalating to a more expensive classifier.

but also, there's no requirement to use it as a zero-shot classifier, you can provide it as many examples as you like, and prioritise giving it examples it had previously gotten wrong. and with input caching it might be economical.

I'd be surprised if they or others don't start offering a fine tuning API for models like this, like openai does for some models (or used to, I haven't checked in a long time).

From the article:

> I proceed asking it to build a simulation of that topic in a low-poly, Rollercoaster Tycoon-like animation

Sounds like the Rollercoaster Tycoon part is just referring to the aesthetics/graphics, and the author is just suggesting building a top-down isometric 2D animated simulation (which I agree is a bit limiting, there are definitely some things where you'd want to be able to fly around a 3D space in first person, move time back and forth, manipulate parts of it).

That sounds amazing. Which IaC tools are you starting with? Do you pull metrics and logs from the AWS/GCP APIs?

This is one of the best WASM-based web UIs I've seen! What was the hardest part of getting your desktop build working via Emscripten?

This is awesome, keep up the good work! Have liked and subscribed =)

After this section…

> Ultima VII was in development from 1990 to 1992 (shipping in April ’92), and even though software 3D was taking off at the time, it hadn’t been designed as a 3D game (even though it used a 3D world) and that contributed to its issues.

> But software-rendered 3D games with isometric perspectives started coming out very soon after Ultima VII, and every time I saw one I thought, “This is what Ultima VII should have looked like.”

…there are clips from three games: Dungeon Keeper (June 1997), Myth II (Dec. 1998) and Grandia (Dec. 1997). Not sure if that really counts as coming out 'very soon' after Ultima VII!

One key, one base_url config, one billing account. If you like to mess around with many different models it's very convenient.

Yep, but a float is more useful than a bool for tracking progress, especially if you want to answer questions like "how soon can we expect (drivers/customer support staff/programmers) to lose their jobs?"

Hard to find the right float but worth trying I think.

Hah, I actually came to this comments thread to link to this. I had a similar experience with my SO!

There are costs to creating and enforcing regulation, and then more costs if it needs to be rolled back (say, if there are unforeseen downsides to it).

What was the thought process that led to this solution? Did day 24 remind you of some other problem you'd seen before?

Yep, have recently had some troubles with provisioning two relatively new products (Redpanda and Materialize), and both of them relied on Slack communities and it's really not an experience I enjoy or find helpful.

But was it being "propped up" two centuries ago?