Kamal is basically self hosting though right? So you have to take care of keeping the underlying os patched etc. With heroku you only needed to think about git push.. ?
I've been working on https://www.minichessgames.com which I built with my 6 year old (she was the product owner ;). It's a site with a bunch of small puzzles (e.g. imagine a chess board with rocks thrown onto it, then move a single piece to a goal square). Lots of fun building it out. And radioactive pooping knights [1] is _amazing_ if I do say so myself ;).
It's just a basic minmax. The main mistake it makes is that if it can find an assured path to getting you it doesn't care how many moves in the future it is (even if it could win this turn).
That said, the audience is 6 year olds so I don't really want it to play perfectly!
Yup, I'm going to build out the reverse play when I find time in the next few weeks hopefully! I'll try to remember to comment here :)
Quite probably you did just run up against a bug in it! I'd have to see the position though.
Great question on the maximal theoretical length. Being pedantic I'd imagine infinite if I just move a knight back and forth and you move a king back and forth. (Though I disallow repeat moves for interests sake)
I mean the maximal length if both players play perfectly.
If the Kings advance in the 1)"b", 2) "d" or "e", 3) "g" column in a synchronized way, they form an horizontal wall of 3 ranks that will trap the Knight at the bottom of the board. This takes 5 * 3 to go from "7" to "2" plus 1 movements to take the Knight, so in 5 * 3 +1 = 16 they should win, and the maximal amount of movements for the Knight is also 16.
This use a little of hand waving, so I may be missing some corner case or brilliant strategy for the Knight. I also may be missing some obvious strategy for the Kings to win earlier. So add a few question marks here and there in the provious paragraph.
> I'm going to build out the reverse play when I find time in the next few weeks hopefully!
Interesting thought. I feel currently AI is most useful to those who have a decent understanding of the subject material and can critique any output. To wholesale trust the output of AI and remove any human in the loop, well, it needs to be really correct all the time.
Exams are a different beast and really a subset of a range of common problems.
Still, I'm very curious what happens when people who have just cheated their way through college, or these kinds of professional exams, meet the real world? Will they all get fired a few months down the track?
Still, I'm very curious what happens when people who have just cheated their way through college, or these kinds of professional exams, meet the real world? Will they all get fired a few months down the track?
They will continue to use AI to do their jobs. Eventually, the people who pay their salaries will ask themselves why they continue to pay them.
To wholesale trust the output of AI and remove any human in the loop, well, it needs to be really correct all the time.
It's not now, but it will be. Accounting is what you might call an exact science, one where creativity isn't rewarded and where hallucinations by one model can be detected and corrected by others. There is no need for humans to do this type of work.
well, lets take that as true (no more humans doing accounting). Doesn't that mean that there'll be a knowledge gap there? What happens when new rules come along (laws change all the time which will affect accounting practices). How will an AI (at least the current batch) learn what needs to change when there's no prior art for it to lean on?
I mean sure, if we ever get AGI then all bets are off, but, as far as I know we're not there, and LLMs are unlikely to evolve into AGI. They're not thinking right? It doesn't actually _understand_ anything right? I mean, I'm quite probably wrong here, but, as far as I can tell it's really just very fancy backwards autocomplete.
(Shrug) Thinking, unthinking, meh. If you can perform near the top level at the International Math Olympiad you're not going to have much trouble with the tax code.
What will likely happen is that future tax codes will be written specifically with rules oriented towards automation. We won't have to train general-purpose LLMs by shoving trainloads of IRS documents, Congressional records, and tax court cases at them, as happens now. I think we'll see lots of specialized models ramp up at some point, for efficiency's sake if not just for accuracy and traceability.
>> I'm very curious what happens when people who have just cheated their way through college, or these kinds of professional exams, meet the real world
Certification questions, as well as interview questions usually quite far from the real world. The best strategy is to fake everything to pass through and then learn at work.
Basically fake it until you make it. The hardest part of swe job is to land it.
Well done :) the "ai" for this game is really basic, it just tries to find any free move and take it. The other games do a basic minmax to look ahead a bit.
reply