Steam screenshots end up somewhere deep in the steam folder structure. Not simply in an easily accessible downloads or screenshots directory in my home dir.
A lack of information density... I felt like I could glean more from the above-the-fold Yahoo.com site in 2001 than any site today.
Note Japan has not embraced the so-called "clean" UI design aesthetic. Check out any Japanese website and it looks like US web sites in 1999, but even more so. I wouldn't mind me some of that.
I’ve been through this thought process many times and I’m not comfortable leaving a device like an iPad permanently connected to AC with a battery that was never designed for that. I can just imagine ending up with a spicy pillow, except now it’s plugged into the wall all the time.
Yep AI will just invent the missing stuff; that's not purely an AI thing, we do the same as well until we become experienced enough to know what questions to ask in order to narrow down vague requirements.
If I'm tired, yep I'm going to write more sloppy code, I'll put less thought into it and be more tempted to tell the AI 'just do it'. That hasn't changed. I'm not sure where this new breed of "don't read the code" is coming from when it's actual software engineers making the statement; maybe it's just over-excitement and it'll die down (hopefully).
Or it's just over-simplification -- I don't read ALL the code either anymore, but at the same time I'm reading SOME of the code. Tell your AI agent you're doing a code review workshop, ask it to select ten files at random and then go through them with you one at a time. Ask it to review common anti-patterns and put them in your coding standard. Then you can start asking it to review and fix code against your standard as a first pass. You'll still need to manually review the code to keep it in check, but at least you can make it a bit less daunting and a little more fun by actively collaborating on the AI with the review.
I'm learning it's just a 'different kind of tired'. AI has made some stuff much more efficient, including the choice between efficiency and carefulness. You can make that choice at a micro level and very quickly now if you want. There's still fatigue though, it's just a different kind of fatigue. You still get tired from all the thinking. You can still choose to put the work in or not and it still makes a difference. It's just a different kind of difficult. Doesn't mean that the thing to do is to throw your hands in the air and declare that your job shouldn't be difficult or include hard work anymore.
Reading the code is not good for AI corporations bottom line. If programmers are needed to read the code, you can’t create a narrative of complete labor replacement. But they don’t have a real solution to make the LLM output good enough to not need a review, so here we are.
Oh I totally get that; I just don't understand why someone like DHH actually thinks that you don't have to read the code, if that's what he actually thinks. He's not a clueless C-suite.
Daaaang you're gonna be pleasantly surprised if you haven't seen it already; look up what's happening with decompilations and recompilations now with AI :)
Asmongold also did a stream recently where he showed a bunch of insane mashups of AAA games that people are doing, like Mario in Elden Ring or Spiderman in the Arkum Asylum Batman map. You can find it on Youtube.
If this trajectory continues, the AAA games industry will be in trouble. It will be a golden age for game restoration and game modding.
I just had Claude get me a 1997 game up and running on modern Windows in 30 minutes, and few days of off-hours prompting later, I'm part-way into upscaling/remastering graphics, have a browser 3D level preview, asset viewer, headless rendering pipeline, and entire internal game logic VM reversed and scripts decompiled to Lisp code.
Getting the game to work and upgrading some graphics was something I dreamed of since childhood (and attempted myself several times). I casually threw Opus 5.5 at it and was surprised at the result.
Didn't know until now that everyone else is doing the same with their favorite old games now.
Huh - I played ‘A Final Unity’ but had no idea they’d turned Generations into a sequel. MicroProse probably made way too many of my fond childhood memories.
I never thought of "Generations" as a sequel, I didn't even know for a long time they were related. As far as I can tell, the main relationship between the two games is that "Generations" uses the same engine and assets in space combat as "A Final Unity".
FWIW, AFU is next on my list, I just need to... dig up an old copy of that too.
Shame GoG never got around to remastering either of them, but thankfully Claude has no problems helping here.
I almost feel like we need a different word that doesn’t have the confusing association. Like scratching your car (‘little t’ trauma) vs smashing the frame (big ‘T’ trauma).
If you come up with one, I'm happy to use it - but we're comfortable with a lot of big umbrella categories: "car accident", "job", "conversation", "computer", "app", "injury", to name a few.
Yeah but that's just bad code in general, no? You can make good code with LLMs, you just have to actually engineer it and give up some of the velocity; which is just a bigger version of the same problem we've always had (yes, I get that code review can't scale).
This is just really silly.
The more I think about this the more I think it's like self-driving cars. We have this expectation that self-driving cars MUST be 101% safe and never get into any accidents, ever, before the technology is worth adopting. LLMs are the same -- it's like we think if you can't one-shot a prompt and get perfect software out of it, it's failed. You can choose to spend time getting the LLM to refine the code it's written, review the architecture, come up with an actual engineering process around the LLM. Yes that means you'll be producing less code per time spent -- which is a good thing.
reply