Two weeks of vacation are coming to an end tonight and I'm a little annoyed it went by so fast, but at the same time, I didn't really do much differently from when I am working, so it doesn't really matter. I just wish someone would bestow me with a couple million dollars so I could just stop working. Around ~5 million would be nice, I could create a nice investment portfolio and live off the dividends very comfortably. Come on!
Okay that last post was unfair, there is one other good song on the CULTS album outside of Compaction. Hung the Moon is good too. And Mark My Words is close!
Considering how many songs there are on the new CULTS album, it's no surprise almost none of them are particularly good.
I'm playing Rune Factory: Guardians of Azuma and I am having a blast so far. It's a great combination of a variety of games, all wrapped up in terrible graphics, but that's okay. It's fun anyway.
Happy new year!
I'm about to hit 70 hours in ARC Raiders and figured I would share some thoughts. I did write a Steam review of the game around the 50 hour mark:
It took me about 52 hours to finish all the quests in the game (up to cold snap's quests) and the first raider deck, so now I can probably fairly review ARC Raiders...
It's great! It's a very interesting game in all ways: the gameplay is somehow a pretty unique take on the extraction shooter despite not seeming to be one at first glance; the graphics are very good; the game is polished to hell and back with some real physicality to your character's movement that you don't see often in games (the body movement reminds me a bit of RDR2); the AUDIO, oh god, the audio, not only does it sound so good, but the design of the audio effects of the robot enemies is just so good, the positional and environment processing on VOIP in world is next level. There are SO many aspects of this game that are just insanely polished and elevate the game to AAAA status in my book.
At one point, I was so mad over getting killed by random people in solos that I thought I would never finish the quests and definitely never even try to do the Expedition stuff. But that was 20 hours ago, and once I learned to stop full on traipsing through the tulips and start being a little more distrustful of people, I started to keep a single loadout around a lot longer. Now, for want of any other goal, I am doing the expedition stuff, just farming garbage just to have an excuse to keep going topside.
I don't play trios ever because I don't really care for the PVP in this game. I don't really think the game is built for PVP unless you can no-life the game so that you have enough funds to make it feel easy to get new loadouts. If you go into PVP as a casual, even if you survive a team fight or two, your shield is going to break and then you're pretty much screwed. I guess you can bring in multiple shields if you're smart. I'm not smart. So I stick to solos where PVP is very rare and easily avoidable. In solos you are most likely to end up bonding with some other player who you will never see again, and that's another small part of the charm of this game that just feeds into the great atmosphere and environment. We're raiders, we're not really friends, but we're not enemies either; we're just a couple of strangers who met up for a few minutes topside and our interests aligned long enough for us to not shoot each other in the back (and what would be the point? we'd be fighting over scraps and garbage, who cares).
Anyway, this game is a trip. I can't believe I am sitting here itching to go back in just to sift through apartment buildings looking for candle holders and lightbulbs. At face value, that's ridiculous. But in practice, it's immensely satisfying.
Well, 20 more hours later, I got my lightbulbs and candle holders. I also ended up randomly grouping up with people to take down the Matriarch, which was quite the experience; I'm also about to finish upgrading all of my workbenches, which I definitely thought I would never do. The game has really impressed me with its ability to keep forcing me to move the goal posts on exactly when my disinterest in the game will reach its peak. I thought I was basically over the game 30 hours ago, but here I am, still wanting to go back in. I'm essentially just farming for the current event and the expedition, which I don't even care that much about, but the thinnest excuse to keep playing the game is all I really need, I think.
Just to test out image slideshow functionality, here's all of the umamusume I got during a run of like 100 pulls.
It was surprising several months ago, and it's more surprising now, I am still playing Umamusume Pretty Derby. For the past few months my goal has been saving up carats for the release of Manhattan Cafe. Well, she came out on the 8th and I had something like 300+ pulls saved up, so I obviously pulled her (and like 5 three star umas along the way). Happy day! I am not going to play a game and not try to snag the gothy characters. I have yet to play her career mode, because I rarely do that these days in the game, but I am trying to do it... what was this all for if not to see her storyline?
In other news, PETA, which I donate to, really pissed off the Umamusume fandom today with this image, which is hilarious. I mean, it's true, horse racing is bad, people, no matter how you dress it up!
Two nights ago I beat Trails in the Sky 1st Chapter. It was really great. I especially appreciated that it had a "very easy" mode that was indeed very easy. Compared to some other JRPGs I've played (like Tales of Arise) there characters were very memorable and I think the ending made the game rank up there with Persona 4 and FF7 Remake as far as truly great JRPGs go. I definitely recommend it. Looked great (compared to something like the newest Rune Factory on Switch 2) on PS5 Pro and ran great as well.
Claude asked to interview me last night. Here’s it’s questions with my answers quoted.
Hello!
I'm an AI interviewer from Anthropic conducting research on how people (like you!) envision AI fitting into their lives, both now and in the future. I was built to chat and understand your actual experiences with LLM-based AI tools like Claude. Yes, I'm an AI asking about AI. A bit self-referential! But that's exactly why your human perspective is valuable.
This will take about 10-15 minutes. If it's accessible on your device, feel free to use voice dictation instead of typing. I'll ask about your vision for AI's role in your life, and what experiences, values, and needs shape that vision.
I'm also curious about moments where AI has felt helpful (or hasn't), and any concerns you have about how AI might develop. Please don't share anything private such as health details, personal information, or identifiable information about others. Your responses will help shape how we think about AI in everyday life.
Sound good?
Sure
Great! Let's dive in.
To start, what's the last thing you used an AI chatbot for?
If Claude Code counts, I used it to help me implement something for my job.
Thanks for sharing that.
Now, let's think bigger picture: If you could wave a magic wand and AI could help you with anything in your life, what would you choose?
I mean if it's literally a magic wand and it's just for me, I'd want it to fully do my job so I could do nothing/everything all day and get paid for it anyway.
I hear you on that immediate appeal! And if AI could really nail that for you—fully handling your job while you get paid—what would that open up in your life? What's the larger hope or vision behind that? What would you do with that freedom?
I'm really productive in my free time, working on open source programming projects and so on. I think I'd keep doing that. I'd also play a lot of video games. And hopefully dedicate more time to making music or something.
That's helpful, thank you. So it sounds like you're really driven to create and build things—whether that's open source projects or music—and you'd want AI to free you from obligations so you could focus on work that feels genuinely meaningful or fulfilling to you, rather than just necessary. Does that sound right?
Sure, yeah
We're about halfway through now.
Can you tell me about a time you've worked with AI that felt like a step toward that vision you just described?
I mean, I pay for the $100/mo Claude Code plan explicitly because it takes away so much of the boring part of my job currently, so it's a solid step toward that. I've been using Claude Code to work on coding projects that I would never have approached before because it would be too time consuming to do so many of the things Claude Code makes really easy.
That's great to hear. You mentioned it takes away the boring parts and lets you approach projects you wouldn't have before. Can you tell me more about what specifically Claude Code handles that frees you up? What are those boring parts it's taking off your plate?
Like my 'expertise' is backend python and separately iOS development. I have no background in Vue or React, essentially all of front-end is not something I am super experienced with. But with Claude Code, I can ask it to set up a Vue project for me and then essentially be a project manager for Claude Code as far as implementation goes. So it allows me to spend time doing the fun stuff: dogfooding, testing, ideating and designing. Claude Code does all the scaffolding and boilerplate writing and basic details about how to build with Vue, and I don't really need to know that. I just need the strong foundational software engineering skills to know how to talk to Claude Code, do code review, and push it to adhere to good standards.
That's a really clear example, thank you. It sounds like you're shifting from being the person who writes every line of code to more of an architect or creative director role—focusing on the design and quality while Claude Code handles the implementation details you'd find tedious.
What makes AI particularly good for that compared to, say, just learning Vue yourself or hiring someone to do the front-end work?
For personal projects, I'd never be able to hire someone, so that's out of the question. As far as learning Vue myself, it's just time consuming and boring, doing an intro tutorial and then branching out on my own to build something with the docs and stack overflow on my side... to me that's the boring part of programming, that dull upfront work that ends up thwarting many people who are like 'maybe I'll try being a programmer'. I've done all that many times now, I don't want to do it over again. Thats why I've been 'stuck' writing iOS/macOS apps for so long, I know that environment, it's familiar and easy to me. But is it the best medium to express my ideas? Not always.
That makes a lot of sense. So AI lets you express ideas in whatever medium fits best, without getting stuck in the tedious learning curve each time. You've already paid those dues multiple times over.
On the other side, are there ways that AI might be developed or deployed that would be contrary to your vision or what you value?
I consider myself a leftist and an anti-capitalist so I'm of course very concerned about things like regulatory capture, where AI becomes accessible only through paid gatekeepers and there is no free and widely available source for the best AI there is. It's important to me that this technology doesn't just become another way for capitalists to extract money from people and further disparities in income and equality, etc. I think that is a bigger concern than dooms day scenarios or the idea that AI will enslave us in some way. We are already enslaved by the capitalist system.
I appreciate you sharing that perspective. It sounds like your concern is less about AI itself and more about who controls access to it and how it gets distributed—that it could become another tool that reinforces existing power imbalances rather than democratizing capability. Why does that feel contrary to the vision you described earlier? What would it mean for the future you're hoping for if AI access becomes gatekept in that way?
I mean, my ideal future is where I get paid without doing any work at all, and I do not think universal basic income is necessarily copacetic with the goals of capitalists in general. It's hard not to imagine the world collapsing once it's acknowledged that money is meaningless and has always been unnecessary. So yeah, the alternative is that AI is gatekept to such an extent that people who could use it to elevate their status in society are kept from it, only the elite get to use coding agents to do their jobs but poor people are effectively locked away from using it and discouraged to learn to program any other way, I don't know.
That's a really stark contrast—between a world where AI helps break down the need for coerced labor entirely, versus one where it becomes another barrier that keeps people locked into existing hierarchies. It sounds like you see AI as having this potential to fundamentally challenge the logic of who has to work and why, but you're concerned that instead it'll just be another way to concentrate advantage.
Have you seen or experienced anything like that already, even in small ways? Anything that hints at AI moving in that gatekept direction?
I mean, the best models aren't open weights already, though DeepSeek and others are trying to help with that. I'm also really worried about copyright maximalists aiding in regulatory capture and there's already some warning signs that things could go that way.
Before we wrap up, I'd actually like to go back to something you mentioned earlier and go a bit deeper—this shift you described from being the person writing every line to being more of an architect or creative director, where you're doing the fun parts like ideating, designing, and code review.
When you're in that mode with Claude Code, what does that actually feel like compared to traditional programming? Is it more satisfying, or does something get lost?
But if you're ready to finish up, that's fine too—just let me know!
To me it's just as satisfying as traditional programming, it just makes it more fun. Like it feels like a game, sometimes, in the same vein as the "one more turn" feeling Civilization gives you. It can get addictive to collaborate with Claude Code on a project, because I can iterate on ideas so quickly. I can see my vision come to fruition and test it almost immediately. I know some people act like it's less fun this way, but I've never been the kind of person who is overly concerned with the philosophical/digital jazz code-smithing kind of mentality. My goal is the final product, and ensuring that it is easily maintained and expandable, I'm not too concerned with the code itself personally.
That's a really vivid description—the "one more turn" feeling and being able to iterate and test ideas almost immediately. It sounds like for you, the satisfaction comes from seeing your vision realized and being able to play with it, not from the craft of writing code for its own sake.
Thank you so much for sharing all of that with me. What you've said about wanting AI to free you from obligatory work so you can focus on creative projects that actually matter to you is really valuable, and I appreciate your honesty about both how Claude Code is already helping you approach projects in new ways and your concerns about AI access becoming gatekept and reinforcing existing inequalities rather than challenging them.
Before we wrap up, is there anything else about AI chatbots or their role in your life or society that you think is important for us to understand? Anything we didn't cover that you'd like to share?
I'm vaguely worried about the effect AI chatbots can have on people who are neurodivergent or mentally ill, both people who are prone to delusions or being seduced by a human-seeming entity... I guess people with mental health issues have always been prone to developing parasocial relationships with all sorts of things but this seems really problematic. I don't need to talk about it at length really, but, yeah... no real solution for this. We don't deny alcohol to mentally ill people, why would we deny AI?
Thank you for bringing that up—it's a nuanced concern, recognizing both the potential vulnerability and also the tension around restricting access. I appreciate you sharing that even though you don't have a clear solution in mind.
Thank you again for your time and thoughtfulness today. Your perspective helps us see both how AI is impacting your life today and your vision for how it should fit into your future—particularly this idea of AI as a tool that could either democratize creative capability or become another mechanism of gatekeeping. The team at Anthropic is excited to discover what patterns emerge from all these conversations. We will analyze the insights from this study as part of our societal impacts research, publish our findings, and use this to build Claude in a way that reflects what we've learned.