I've been learning Go for about 4-6 months. So far I've been really enjoying the language. I'll suggest to you to work through the go tour in the beginning, then gobyexample is a great reference resource. I've also heard good things about the book "100 Go mistakes" which is for advanced users.
Obviously, Go has its own quirks but if you can enjoy them and make the language work for you, it's really fun!
tldr pages are a great idea, but the execution is a total fail. Looking at the rsync entry, it fails to provide the most blatantly common requirements:
I just needed two commands: one to mirror a folder from one drive to another, updating only the changes (excluding all of the hidden MacOS cruft). And another command to do a deep validation of the copy. These have to be two of the most commonly used commands right???
In the end, I felt that messing around with precious data without being 100% certain of what I am doing just wasn't worth it so I got a GUI app that was intuitive.
Why is such a wave so big? Because the coast is extremely shallow suddenly. Normally 1m-50cm, but when a big wave comes, all the water in front of the wave is sucked into it back, which makes it about 10-20cm deep. And it is sucked back really fast, because it is not deep. So if you miss such a wave and fall down, you end up there in the impact zone, which is also the shredding zone. There are either rocks or coral reefs, both extremely unhealthy when being shredded along, even if you still have your board. Normally not. And then you are sucked back into the next wave impact zone with high speed, which is un-nicer, because then you are not just shredded along, but also hit big from above into the ground. Where you usually break some arm or leg, or just hit your head into the rock and then drown. The few people who survive this do have professional help by the jet skiers, who try to catch you before the next impact.
Your only chance is to get your board from the leach as soon as you get up, and paddle as fast as possible to the side, across the stream to survive the next impact.
It's not interesting at all, pure danger. Like running across a highway without looking.
That seems a bit like deck-chairs on the Titanic. The hard part isn't icon design, the hard part is (A) ensuring a clear list exists of what the NPC is supposed to ensure the user knows and (B) determining whether those goals were received successfully.
For example, imagine a mystery/puzzle game where the NPC needs to inform the user of a clue for the next puzzle, but the LLM-layer botches it, either by generating dialogue that phrases it wrong, or by failing to fit it into the first response, so that the user must always do a few "extra" interactions anyway "just in case."
I suppose you could... Feed the output into another document of "Did this NPC answer correctly" and feed it to another LLM... but down that path lies [more] madness.
You prompt the LLM to point out that the clue will be added as is to the conversation, but for the LLM to include a marker instead of the actual text to ensure that actual critical details are included unchanged.
EDIT: Also, having the LLM botch a clue occasionally could be a feature. E.g. a bumbling character that you might need to "interrogate" a bit before you actually get the clue in a way that makes sense, and can't be sure it's entirely correct. That could make some characters more realistic.
No, this is the Einstein/student model that has been proposed for improving LLM output quality.
Basically you have your big clever LLM generating the outputs, and then you have your small dumb LLM reading them and going “did I understand that? Did it make sense?” - basically emulating the user before the response actually gets to the user. If it’s good, on it goes to the user, if not, the student queries Einstein with feedback to have another crack.
Repeating the last line of dialogue is not just a way to indicate that there's no more dialog, it often also works as a remainder, giving you the most important kernel of information ("You should go to [place] and talk with [npc]"), in case you come some time later and forgot what you were supposed to do. You can indicate there's no more dialog in many ways, but you'd lose that secondary feature. Same thing if the NPC just keeps babbling generated drivel.
So true.
In such an LLM-driven game though, I would imagine the player would just ask the NPC: "I forgot what to do" or even "Can you explain it in other terms?" (if the quest description isn't clear enough).
