AI instead of classical parser

Is that actually a good thing? (personal opinion wanted here). Because I’m sceptical.

And what does the AI do/deliver actually?


No idea, as the thing doesn’t even go live for another 18 hours:

It’s noteworthy, which is why I brought it to the attention of the community, but I don’t really have it in me to make value judgements about a nascent technology. Like most technology, it is full of potential, which could be used for good or harm.

As for what the AI actually does or delivers, I suppose we’ll soon find out, because right now it is all simply assertions made by Square Enix.



All I’m going to say is to take a look at the reviews (13% and falling):


Weird that ignoring the long history of text games would result in a bad text game. Surely the next person to ignore history will succeed…


Steam reviews are often gamed by vindictive assholes.

That said, this doesn’t seem to be making a good impression on anybody.


Yeah, the reviews I glanced at generally included actual transcripts of (frustrating) gameplay so I’m guessing they’re mostly legit.

It’s probably worth bearing in mind that Square Enix is kind of all in on hollow techbro BS - they recently unloaded a bunch of their Western studios, including Tomb Raider, so they could focus on NFTs. So the fact that this implementation is completely slapdash and all marketing, no substance, might not be as probative as one might think.


AI is still soooo much farther away from actual intelligence than the recent hoopla would have us believe.

Ouch. That’s top-tier stupid. I generally prefer older games, and I liked the original TR games, but I have to say the more recent Survivor trilogy is excellent.

NFT’s are for suckers.


I hadn’t paid attention to this one Discord server I’m on but then I realized they were talking about this very game.

A snippet from there:

S: I haven’t been this railroaded since playing Densha De Go!
C: I did look in the Steam forums for a command list, I totally forgot police brutality was a command
S: I remembered that part and was trying to get it to happen but couldnt find the right words
S: It’s crazy that this game has become the ultimate version of the problem they were attempting to solve
C: Yeah for real. The command is just hit him
S: Laura Bow’s parser from '89 is infinitely better than this game lol
C: If you do stumble on some Japanese reviews I’d love to hear if the parser’s any better

S: I’m having luck exclusively using commands I know from the NES game lol



Two thoughts about this:

  • Could it be that the tech demo refers exclusively to the “demonstration of Natural Language Processing”? That it is not about the parser and the understanding of text, but exclusively about the recognition of spoken language? If this would work locally, that would be pretty good!
  • Enix is not very well known for its IF. The game is from 1983 and apparently has not been revised. It was certainly a bit clumsy to choose this game as the basis for the demo. At least for a western audience; in Japan it might be seen differently.

I can see why you’d think that (and it’s nice to give them the benefit of the doubt), but NLP is an umbrella term that encompasses many things other than speech-to-text, including parsing typed text input that’s in a natural conversational style, and it’s clear from their press release that their innovation was supposed to cover everything except language generation. They break down all the different sub-fields of NLP and talk about how this game demonstrates them. In fact, the thing that they spotlight the most is the text parsing:

At the time of the game’s original release, most adventure games were played using a “command input” system, where the player was asked to type in text to decide the actions of their character. Free text input systems like these allowed players to feel a great deal of freedom. However, they did come with one common source of frustration: players knowing what action they wanted to perform but being unable to do so because they could not find the right wording.

Basically, this was being explicitly touted as a way to eliminate guess-the-verb problems, and it looks like it failed at that.

About your second point, I’m not sure whether you’re saying it was a poor choice for SE to do this because they were never a major player in parser IF or this game specifically was a poor choice because it hadn’t previously been remade (or both), but as for the first, Enix was well known for its IF in Japan in the era of commercial text adventures, and this game in particular was absolutely iconic to Japanese gamers. It’s frequently referenced in pop culture even now. As for the second… what commercial parser games have been remade/updated recently? Other than the recent graphical remake of Colossal Cave Adventure, I can’t think of much. So it’s not like there was an easy option to go for a parser game that had been adapted for modern player expectations in every regard except the parsing.

That said, I do wonder how much of the problem here is the parsing and how much is the game being underimplemented by modern standards. Parsing the player’s input correctly doesn’t help much if the game has no response for that topic/action. I was going to check it out for myself before commenting on this aspect, but apparently this game is 10GB (another issue with the viability of this technology as it currently stands!) so I’ll have to wait a bit for it to download and install.

On a side note, I see they were originally planning to get around the implementation problem through generated text, but axed that because they couldn’t guarantee the language model wouldn’t give offensive responses, but honestly, even if they could, I think language generation is risky for a mystery game. The language model could generate a response with details that sound significant, and the player could go off chasing a string of red herrings without the game ever giving any feedback to indicate that they were on the wrong track, because it can generate a response to any question they ask or action they take. To a certain extent, I think a mystery game needs “I don’t have anything to say about that” responses to indicate when the player is trying to pursue an unhelpful line of investigation.


This is the big issue with making smarter parsers. Infocom experimented with parsing adverbs in some of their games…and it added basically nothing to the experience, because for the most part the world model didn’t care if you did something “carefully” or “thoroughly”. The few cases where it did matter just ended up being frustrating guess-the-adverb problems.


This sounds like what Spirit AI tried to do. I wonder how they solved the problem of limited training data. Or perhaps the result is an indication that they didn’t.

they were originally planning to get around the implementation problem through generated text, but axed that because they couldn’t guarantee the language model wouldn’t give offensive responses

It seems to me there is a middle ground here where a language model generates lots and lots of plausible responses, which are then curated by humans, and the good ones are hard coded into the final game.


As I recall, we had enough training data to get decent indications out of player input. It wasn’t really trying to get Adventure-style commands out – just general flags like “player is greeting me”, “player is frustrated”, “player is asking me a question”. The hope was that this could be combined with keyword search (for specific topics) to get a workable model.

The hard part was what Daniel Stelzer mentions: coming up with an authoring model to use those player input indications.


From a quick gander at the transcript excerpts people were posting in the Steam reviews, it seems like this is a both/and rather than an either or; a majority of the stuff I saw was player input that included all the correct nouns and verbs for an implemented command, but the parser/LLM not fully understanding it due to word order, prepositions, unimplemented synonyms, etc.


That’s true, and I think it’s actually worse than that in that I don’t think many players actually want that kind of thing.

Like right now you could put together, using existing libraries, a JavaScript-based parser that could handle something like >RAKISHLY DIVEST YOURSELF OF THAT THREADBARE WORSTED MONSTROSITY as being synonymous with >DOFF SWEATER, but there are probably only a vanishingly small number of players who would want to play an entire game using syntax more like the former than the latter.


Overpromised and underdelivered AI based gaming reminds me of the good old days:


As a pre processor I think the idea has some potential for newcomers, hypothetically something like:

~> I want to get the cookies from the top shelf and if necessary I will stand on the stool to reach it
(Command simplified:
~>Stand on stool
~>Get cookies )

Okay, you stand on the stool and take the cookies.

In this way, the player learns how to play.


Well, the Steam review transcripts seem to indicate that there are one or two people out there who want that kind of thing.


I’m sure there are some, but I’d be willing to bet that even most of the players who think they want that, don’t.

Like I haven’t done any double-blind surveys or anything, but I imagine most IF players use >X LAMP where it’s possible, and comparetively few will resolutely stick to >EXAMINE LAMP just for the verisimilitude or whatever.


I don’t think those Steam reviewers are IF players in that sense. They most likely have no idea that X is short for EXAMINE, or even that you are supposed to EXAMINE things. From their perspective, the game tells them to type in what they want to do, and then utterly fails to understand anything they type.