I joke to myself that the G in ARC-AGI is "graphical". I think what's held back models on ARC-AGI is their terrible spatial reasoning, and I'm guessing that's what the recent models have cracked.

Looking forward to ARC-AGI 3, which focuses on trial and error and exploring a set of constraints via games.

Lots of muralists document the art/business on youtube! Two I like: Kiptoe and SmoeNova

- I had a really hard time building a greenhouse, because I hadn't realized it'd be bigger than 1 square like all the previous buildings, and it just wouldn't build despite having materials etc. Maybe a footprint outline while hovering a build option?

- There were a lot of instructions from Dr. Kimura right off the bat. Hard for me to remember all that, and I was hoping talking to the doc again would replay those hints.

- My population seems to be stuck at 2.. I have landing pads and habitats and plenty of food etc, but don't really know what I should be doing next.

- that menus continue beyond the first couple lines was not obvious to me. Possibly because I'm on laptop, so the existing hint was way far to the right

But seriously, other tasks I've encountered recently that I wish I could delegate to an AI:

- Posting my junk to Craigslist, determining a fair price, negotiating a buyer (pickup only!)

- Scheduling showings to find an apartment, wherein the listing agents are spread over multiple platforms, proprietary websites, or phone contacts

- Job applications -- not forging a resume, but compiling candidate positions with reasoning, and the tedious part were you have to re-enter your whole resume into their proprietary application pipeline app

What strikes me as basic similarities across these types of things, is that they are essentially data-entry jobs which interact with third-party interfaces, with CRM-like follow up requirements, and require "good judgement" (reading reviews, identifying scams, etc).

In your example, yes, the factory owner can take their $100/hr of profit. But among the various factories, some owner might take $25 of that profit and instead undercut their competition to grow their order book. Other factories respond in kind, and the consumer is getting cheaper products.

I'm curious if this will implicitly drive a shift in the usage of packages / libraries broadly, and if others think this is a good or bad thing. Maybe it cuts down the surface of upstream supply-chain attacks?

Indeed, there's been quite a few studies [1] that find just including any old image of a brain with stuff highlighted will cause a paper to be perceived as more scientifically credible.

[1] https://pubmed.ncbi.nlm.nih.gov/17803985/

Biggest drawback though is that it's over-optimized for matrix math, that it forces you to think about everything as matrices, even if that's not how your data naturally lies. The first thing they teach about performant Matlab code is that simple for-loops will tank performance. And you feel it pretty quickly, I saw a case once of some image processing, with a 1000x speedup from Matlab-optimized syntax.

Other things issues I've run into are string handling (painful), and generally OOP is unnatural. Would love to see something with the convenient math syntax of Matlab, but with broader ease of use of something like JS.

Though you're right that the prices didn't skyrocket, as that would have been considered price gouging during an emergency, which would have been PR suicide at a minimum if not actually illegal.

For all their discussion of high temperature operation, it seems the only advantage at the end of the day is to eliminate water consumption in cooling. I question if that's really so valuable?