ksaun

I'm hesitant to respond, because I haven't shipped yet and I haven't shown any evidence. But I am close enough to completion that I am certain Claude's work will be sufficient to ship.

I'm making a fairly simple game, a single player 2D roguelite strategy game. More context here: https://news.ycombinator.com/item?id=48886151

From an implementation perspective, it is about 80% complete, where by "complete", I mean "adequately polished such that I could ship it." (I'm not interested in providing evidence of my claim at this time, and you are welcome to not believe me.) Most of the remaining 20% are optional game modes I could choose to cut (and may, for gameplay reasons).

I do not contend that the code is excellent. But to whatever extent the code is "slop", that has not meaningfully inhibited the ongoing development or caused noticeable issues with the player experience.

The game is not especially ambitious, but it's something I would have been unable to create without genAI. The version of me that could have made it without genAI would have taken > 10x as long to get as far as I've gotten.

Re: superpowers/brainstorming: in an attempt to be more helpful, below are a couple examples of prompts I used. (I've been surprised at how infrequently people talking about genAI share their prompt text.)

I've found it's fine to start /brainstorming in a new session; Claude has been usually good at gathering up enough relevant context to directly dive in. I use high or xhigh for brainstorming; sometimes I ask Claudes opinion regarding level of effort (or whether using Fable would matter). In both cases below, I had more details in mind than I included in the prompt text; I try to provide enough context and direction to drive the discussion. I think I started the first one in a new session, with Opus, in parallel to another Opus whose work sparked my interest in this feature. The second prompt was during a Fable session that I felt had been going very well. It was working on a tutorial and I thought continuing the session with it having that additional context might be beneficial.

**

/brainstorming We're currently fixing up the Disrupted Memory panel, which leads into a Signal Lock match. Through that process, we decided we want to let opponents effectively have "items" like the player can. These would be authored specifically by opponent (i.e., Null has <item1> <item2> etc.). For passive items, the opponent would simply get the effect during the match. For Active items, the opponent would need to have their logic/strategy modified so that they can decide when to use it. I'm imagining the Signal Lock screen/UI shows/represents the opponent's abilities in a way that's symmetrical to what we're doing for the player's. It seems possible that we'll need other/new visual effects for when opponent active abilities are activated, to more clearly indicate what's happening. The design objective here is to help the opponents differ more significantly from each other, adding to the sense of them having personality, increasing difficulty, and influencing the player's own strategy. Please help me delve into the specific items for each opponent and then implement all aspects of this feature.

**

/brainstorming A tangent that's related to the tutorial: We want to make Mara more of a "character" in the game. "Mara" being the tool, or the AI agent within the tool. We use Mara more actively than we have been. For example, instead of just static system log messages, Mara "talks" to the player: when first starting the game, Mara says something like "Hi! It's been 2423 days since I was last activated. You could not be Erik, so I assume you are a new analyst interested in accessing digitized memories. Since you are presumably new here, would you like me to give you an overview of how all of this works?" etc. Going this route would involve a few things: 1) In elevating Mara's presence, we'd probably want to define her voice differently, probably give it a little more personality. 2) We'd want to adjust the tutorial as if it is being delivered by Mara. Both using this new personality and maybe adjusting some other details to make it feel more like what the tool itself would want to explain. 3) We'd want to audit the system log and see what messages it contains would be better presented by a Mara message (either instead of or both). 4) We'd want to revist the Ask Mara content of the Console, maybe adding more questions or modifying some of the answers. 5) We'd reposition Signal Lock's place in the fiction. (E.g., "Restoring disrupted memories is very complex and poorly suited for human consumption. I understand that many humans excel at card games, so I've translated the process into a card game.") 6) A writing pass on all of the text that's supposed to be in Mara's voice to better fit the new voice. 7) Probably we'd want other places/opportunities for Mara to say something to the player. 8) We should re-envision the UI a bit -- maybe we stop the map from reaching all the way to the bottom, and repurpose the screen to the right of the system log for Mara (like the Tutorial does). Maybe we want to allow the player to "talk" with Mara, at least in some situations. Like... Mara might ask the player a question and the player can answer and there's reactivity to these choices later. I see two routes we could take: a) fix up the things in the list above (1-7) and let that help us to see how to better leverage Mara and then revisit 8 and iterate; b) Design out 8 and implement this, then figure out how to cascade the implications of 8 through the rest of the game (i.e., 1-7 + more?).

While I, too, find myself recoiling at many of Claude's word and phrase choices, I've chosen to grit my teeth and have just tried adapting to it. I want Claude to remain focused on the work I give it; I fear that influencing its communication with me would consume valuable context and give me lower quality results.

[Edit: Part of what led me to this conclusion: I do prohibit Claude from using em-dashes in any player-facing text and I've been surprised at how often I see it mention "no em-dashes" in its self-talk while it works. This led me to wonder how much each preference might dilute its attention.]

[Edit 2: I haven't experimented with hooks before and maybe the technique discussed in this article does not have the tradeoff I'm concerned about?]

Overall, I've been very pleased, though I have seen inconsistency like you mention.

First, some background: At the start, I used Sonnet, but after a couple weeks, I'd switched to mostly Opus. I've used Fable when available. For any significant new feature or work, I use /brainstorming (superpowers plug-in). For Vestiges, I haven't written any design documentation per se. I'll start off a /brainstorming with a hefty prompt, maybe 5-15 lines. Throughout the brainstorming steps, I'll think of additional ideas/details about the feature, etc. I'll just add the change/addition to my answer to whatever question it had asked and it seems to handle that fine.

Sometimes I catch things in the subsequent design review process and it handles new guidance well there, too. Typically, I've left some details underspecified and Claude fills in the gaps -- often quite well, but I have to pay attention. The details that it decides later in the process (the implementation steps) are often solid, but when they're not, it's easy to iteratively fix later. Most of the time when Claude asks for clarity on a detail, its recommended option is what I wanted.

It's been rare for Claude to do something that just didn't work (but it has happened occasionally). I have found that it's not good at imagining the player's perspective; it doesn't consider the player's cognitive load for UX considerations, for example. That seems to be consistent with your observation about what they can and cannot verify. A recent instance was when I added a tutorial (which was much more scripted than regular gameplay, providing a more specific experience); I ultimately had to get very directly involved to get to the quality I wanted.

Vestiges doesn't have any gameplay involving timing like Pong does. I could imagine that sort of gameplay being harder for it to get right.

(I hope that covers some of what you were seeking!)

(Early on, one requirement I gave it was not to use em-dashes for anything player-facing. It's kind of amusing (and a bit sad) at how often I see in its session self-talk something like "No em-dashes!" alongside much more important comments. It's really taken that constraint to heart! :) (Alas, I liked to use em-dashes myself, too; I'm resisting giving up semi-colons and parentheses, though!)

Fortunately, I personally enjoy writing. Currently, I wouldn't be able to claim that Claude didn't contribute to the writing, but nothing in Vestiges should sound like genAI. (Which is actually a little funny to me since one of the characters is an AI. But the genAI writing style grates on many, including myself, and I'd imagine that 20+ years into the future, such issues will have been solved.)

That's useful context, thanks. I might be in a grey area on that front. Vestiges has no genAI-created images, textures, etc. Pretty much all of the (non-text) visuals are generated at runtime using Godot's 2D vector drawing capabilities.

(I've considered trying to find an artist to work with to have professional 2D art.)

Yes, the minigame is like Pazaak. I've prototyped two more radical variants that might also make the cut.

Thanks! I've been hesitant about Steam because of the strong anti-genAI sentiments there. (And the initial fee to set-up a game's page.) You are right, though, and I probably should just push past my reservations.

(When I began this effort, I was just enjoying feeling productive again and didn't have any real plan to release. But I've been pleased enough with how it's been coming along that I've started seriously thinking about it.)

I was an experienced game designer and producer (mostly RTS and narrative RPG). Some years ago, my career was derailed by major health developments. Since then, I haven't been able to work as I once did. I didn't expect I'd be able to meaningfully contribute to a game again.

Earlier this year, a colleague encouraged me to experiment with Claude Code. So now I have a little game project. :) Being unfamiliar with genAI, I chose something modest so that I'd more likely be able to push it to a fairly polished state.

Tentatively called Vestiges, it's a single player 2D roguelite strategy game with meta progression, some narrative, and a card minigame (the latter inspired by work I did on Star Wars: Knights of the Old Republic II). It's set in the near future. You are using software (the game) to navigate a person's digitized mind, reading their memories.

I hope to have a playable demo within the next month or so.

That capitalization convention is included in the Associated Press Stylebook (https://en.wikipedia.org/wiki/AP_Stylebook); the author's use of that convention is not evidence of any broader "allegiance." (Maybe some feel that adhering to the AP's guidelines is enough evidence of bias, but I think it is imprecise to judge the author specifically for following that convention.)

(I am not expressing any opinion on the broader topic(s). I only wanted to call out that the author's writing conventions may have less significance than OP implies.)

If you don't mind disclosing, for what type(s) of games is your game engine intended?

(Also: I agree with your assessment. I'm not working on an engine, but I am working on a game, mostly/initially just for my own edification. It's fun to feel empowered to create again! (My personal circumstances had obstructed me until genAI's recent progress.))

To be fair, pixelready said "average person," not "average American."

Sincere question: Do you have thoughts as to how we can invest our $ if our goal is to support the "good economy" instead of attempting to ride the wave of the rich getting richer?

I would like to be part of the solution instead of contributing to the problem, but it is challenging to identify companies in which to invest without supporting the status quo.

I am not "rich," but wish I could better vote with what assets I do have.

Specifically, the episode "Forks," in season 2. IMO, this episode can be enjoyed by someone otherwise unfamiliar with the show.

I don't know about SSI, but this isn't accurate for SSDI.

For SSDI, if your earned income is more than $1110 in a month (for 2024), then you consume one of your 9 trial work months. That $1110 threshold is regardless of your SSDI payment amount and it is adjusted annually. The trial work months are to allow disabled persons to attempt to return to the workforce without risking losing their social security benefits if it proves unsustainable for them.

(The specifics are a little more complicated than what I've described.)

Besides just not using these services, wouldn't it also be necessary to divest any investments in any of these companies (even if through mutual/index funds, etc.)?

I agree it is hard to not feel defeatist.

Well, I have a similar difficulty in analyzing myself. So you are not alone.

But I also struggle hypothesizing others' reasons for behavior. I can readily empathize with others, but often can't transfer from the emotional response to the underlying reasons/logic.

Diet and exercise are extremely effective in treating type 1 diabetes. But some exogenous insulin (and other medications) are usually still required.

I think you are misinformed about Type 1 diabetes. Maybe you are thinking of some other condition?

In Type 1 diabetes, the pancreas stops producing any insulin. Insulin must be administered regularly (always, not usually) or the person will die. "Other medications" aren't required.

One's diet and exercise are relevant to Type 1 diabetes treatment, but are not a treatment method.

Source: my daughter has Type 1 diabetes

The entire system is too complicated, and the CGM too variable in accuracy, for such calibration to work in the way I think you are suggesting.

Each time the CGM is applied, the situation is different because of the exact position and various other factors. And the CGM is not 100% consistent.

You do/can calibrate the CGM as needed. For example, when the CGM first activates, standard practice is to check with a fingerprick to see how accurate the CGM is this time and (sometimes) calibrate. (As noted in other comments, the CGM and fingerprick are not detecting exactly the same thing.)

And the next time you apply the CGM (we use a Dexcom G6, which is changed every 10 days), any previous calibration is irrelevant. There's a lot of variability and many factors that can affect results (exact location, scar tissue from previous CGM application, recent exercise, a recent hot shower, etc.)

(I didn't explain that well, but hopefully you get the idea.)

Suppose you lose your job while your house is badly underwater. You are unable to make mortgage payments and selling your house would leave you saddled with part of your mortgage still.

Thanks. :) Gosh, no. (Too much additional work for the benefit, for us.) We've used Unity, but we expect to transition to Unreal in the future as Unity's direction in recent years unfortunately has been ominous.

(FWIW, the studio with which I'm affiliated (https://digimancygames.com) is focused on narrative-driven CRPGs in the vein of games like PS:T and Disco Elysium. We have assembled three of the Disco Elysium writers and other talent in this space. We have an internal project, but are seeking publishing partners or investors.)

I believe your recollection to be accurate.

The lead designer (Chris Avellone), who I think was the primary author of this document, is often playful and energetic/hyperbolic with his language, yet is extremely focused and professional in his approach to the actual game design. (I.e., this exact type of disconnect between the energy/tone of this document and the energy/tone of the game is consistent with what I know of him. The self depreciation, noted in the comment below by ricardobayes, is also on brand for him.)

Source: I've worked with Chris very directly on three games and indirectly on several others. We've talked about this document in passing before (though I didn't know him until a few years later).

Yes, it is a very selfish act.

Imagine how must pain they must be in to act in this way, to dismiss or not realize how much harm they will cause.

Imagine how much pain they must be in to demonstrate such extreme selfishness. To behave in a way that seems so out of character, so different from how they'd treated their loved ones prior to that act.

And consider how selfless they must have been to have held off as long as they did. To have endured the immense pain and struggled to resist the escape of suicide, until that time when they were finally overcome and capitulated.

It depends on the specifics of her situation. If the 30% is the chance of it being curative (as opposed to just dealing with the currently known tumors), then even if the treatment "failed," it might still allow her to live several additional years and/or be in better health for her time remaining.

"there will probably be incredible opportunity down the road to combat this,"

I am curious to hear more about what you mean by this.

I crave living in a high trust society. I've attempted to act as though I do (though not with complete success), but reality often rebuffs me. I am discouraged by the high (and seemingly increasing) "capacity to benefit from dishonesty," especially as I feel powerless to meaningfully affect this trend/condition.

It sounds like you see ways in which society can shift to be higher trust. Can you elaborate?

I don't think the type of reparations discussed in the article are an attempt to punish. I don't see any mention of one's ancestors' offenses (or lack thereof) being considered. It's about compensating those who are believed to have suffered.

I was amused by the cleverness of your summary. :) But while what you wrote seems to literally be true, I don't think it's an accurate portrayal of what the article (if not its title) describes. I might have overlooked something, but

1. CA would be taking the money from everyone. (I.e., it isn't intending to punish and doesn't single out who is taxed. For example, a poor person who receives the reparations benefits more than a rich person who does, since the latter would have paid for more of the reparations through their own taxes.)

2. The people who would receive the money are descendants of slaves; while not former slaves themselves, this $ could be thought of as a representation of the inheritance they should have received. (But how they determine these people seems flimsy -- the article mentions people who "claim" enslaved ancestors and it's unclear how such claims may or may not be validated.)

Regarding CA not having been a slave state, the article mentions the harm caused by prejudicial policies in CA, but then it's unclear why affected people who don't have enslaved ancestry wouldn't also be compensated.

Anyway, after (and despite) writing out the above, I think your summary is actually fairly apt (and humorous). But I kind of wish it were less provocative.

(FWIW, I think the course of action discussed in the article is problematic and I have conflicted opinions about the concept of reparations. I think it is a complex topic.)

I think if more people tried to make less potentially inflammatory statements, it would be easier to have productive discussions about contentious topics. This could serve to reduce tribalism, which I feel would be a good thing.

(The article's title is a much stronger example of the inflammatory language that I think should be minimized.)

[Edit: grammatical and formatting fixes; criticism of the article's title added.]

> The collections agency had also put a black mark on my credit history.

This doesn't seem to be true.

Maybe the situation has changed over the past couple decades. (I don't recall which of the three credit reporting agencies this was with.) It was true for me back then. :)

In my case, the collector didn't initiate contact. I learned of the situation because I checked my credit report and then it was I who contacted them. I didn't know who they were or why they thought I owed them money. They tried to convince me to pay them, saying they'd remove the mark from my credit report after I did so.

I had believed the medical service (a couple years in the past at that time) had been completely covered by insurance and didn't know that anyone thought money was owed. I don't know where the original miscommunication/mistake had occurred. I only know that the collector dinged my credit report and that I had documentation showing that my insurance had addressed the original claim (paying the medical provider), which enabled me to challenge the collection agency's assertion.

(Thank you for the additional information and context you've added about collection agencies. I knew little about them outside of my direct experience with this one.)

20+ years ago, I was in a situation that, at this high level anyway, was similar to what you're describing. The collections agency had also put a black mark on my credit history. I don't recall the details, but to whatever extent I did contact the medical provider or the insurance company, they claimed to be unable to help me. (I no longer owed them money, afterall.) The amount I supposedly owed was some hundreds of dollars, not thousands.

After repeatedly failing to have any success communicating with the collections agency, I sent a letter to the Better Business Bureau about the situation. The collector stopped contacting me and my credit history was restored. I never spoke with a lawyer about it and don't know if my approach to addressing the problem was typical.

From my experience, I would suggest that you take the fight to the collector. They are the ones to whom you currently supposedly owe money. (I did not attempt to sue anyone, though, and maybe that detail, or others, would change the answer for your specific situation.)