FireCrack

I've tried, casually, quite a bit of this. With generally poor results. Often this ends up similar what I have seen as classic RL problems with seeking reward in sparse environments. Unless you give the agent an a-priori goal outside the world it tends to not do anything interesting. Theoretically there ought to be ways around this such as herarchical approaches, but those tend to scale in complexity faster than my limited resources can keep up.

It's very neat though.

Edit: I really should watch the video before commenting. Looks like it goes into lots of these problems itself, and they got much further than me.

I feel like it's 50/50 between people doing that, and people that have spent a lot of time tuning a system they are pointing at focused and well specified problems.

Absolutely true. But the OPs statement is not without merit. While there is a lot of professional software for which GUI is the correct choice, there is also a lot of "GUI slop" which is just a GUI to look good on marketing and to be easier to onboard new users at the expense of long term effectiveness.

The thing is, for a guided interceptor, the speed ratio between the interceptor and it's target has an extremely strong effect on how difficult the intercept is. In practical situations increasing speed is the best way to increase intercept chance.

The premise is a bit of a stretch to begin with, and the idea that people would not believe a fable transcript circa 2020 (as long as explained as 5 year future tech) is absurd. But even if I take that "AI can do all cognitive and physical work, at human level or better, and cheaper than humans" is true, the article seems to silently layer on "and can run autonomously, indefinitely", then "can also operate independently of any instructions", and finally layers on "has emotions, has moral values, is a conscious being"

What's left is tautology.

For the purposes of chess the domain knowledge is the game rules. And from this pov there is really not much to describe, knowing en-passant exists is the peak of domain knowledge.

The other things you describe, such as endgame tables, are really more related to the domain of chess-computing, a subdomain of algorithms, and likely something you exceed your friend's knowledge in.

Getting to a high rank in chess isn't about better domain knowledge, is about application and experience.

IDK if it's just me, but I also find Claude, whether it be the model or the harness, is a lot more "forgiving" of poor prompts than many of the open models