Haven’t you heard? “React” content is the new meta (/s only half way).

Oh wow, I think this is the first time I’ve seen analognowhere referenced outside of the the fediverse community where pmjv posts their artwork.

I’m halfway through the logs; I’m finding them much more compelling than the initial story - something to do with the tone(s).

Thank you for writing/making this!

Without ever having actually played it, it reminds me of Riven

Put a cracker on his head and called it macaroni 🎶

Also that repo is full of vibed slop that barely works, see: https://github.com/deletexiumu/wifi-densepose

Slay the Spire but with poker hands instead of medieval-fantasy-combat

“sorry to disappoint you, Timmy, but the tooth fairy only comes once she knows the parents are aware their child is about to get some money/a visit”

I’m very surprised there are parents telling their kids about the tooth fairy that can’t recover the story when confronted by their kid with such evidence.

I’m probably going to play dwarf fort on my desktop once the trial is over - I don’t have the disposable income to justify buying CrossOver.

There are a bunch of games on steam that natively work on my M1 mac, so you can try suggesting Slay the Spire to your friend for example. For multiplayer, satisfactory and 7 days to die both have native Mac versions available through steam.

I’ve started a two-week free trial of CrossOver, the paid macos wrapper for wine whose developers contribute to wine, in order to play dwarf fortress on my M1 MacBook. It works like a charm, and the setup to get the game running is just like how Lutris does their “pre-packaged” game installations.

Dwarf Fortress Classic (without the premium graphics) is a bit disappointing; the ASCII graphics don’t seem to be able to render crosshairs on the tile you point at with your mouse and so designating certain things like bridges and screw pumps is hard - if I hadn’t played a bunch of Premium on a linux box through steam I don’t think I would understand half of what’s going on. For the first time since purchasing Premium I’m missing the old, keyboard-centric user interface… Other than certain things not rendering, the updated UIs are surprisingly pleasant to navigate in ASCII mode.

Making crafts from mussel shells is still as overpowered as ever for bootstrapping a fort’s trade capacity!

Oh definitely. I think it’s anthropic who have stated in multiple interviews that they break even on most of their models, it’s just that they keep spending exponentially more to train the next model. They and openai seem to be stuck in an arms race where switching to purely serving existing models to their existing clients just won’t work. I do wonder how accurate that assessment is on their part.

I find it interesting that according to these numbers, if they entirely stopped R&D and marketing, they would just about break even.

Have you tried turning on “developer mode” in lmstudio and looking through it’s logs? No idea about your particular case, but any time generation in LM Studio has failed for me I’ve been able to figure out why and work around it by looking at the logs.

GC enables webpage bloat, in the sense that these bloated designs would be unfeasible to code with manual memory management. I’m not saying they are caused by GC, but that now extra discipline is needed to resist taking the “easy path”. This is the point I’m trying to make with regard to making LLMs code for us; they’ve added incentive to be sloppy because the “black box” result is the same only more trivially obtained. I’m worried about the knock-on effects because I feel like I’ve seen this cycle happen numerous times. And for some reason some places going “all-in on ai” are now either backing off from that approach or shipping buggier software. If you’re not getting worse code from using LLMs, great. Good for you. Having tried again and again to work with these tools myself, I don’t see how to overall gain any actual effectiveness with/from them - shuffle around the effort, sure, but trying to arrive at the same place as without them only faster and/or with less effort? I just don’t see it happen in my attempts. Invariably I come out feeling like I’ve been over promised and simultaneously lost time trying to wrangle hard truths and intentional code out of something designed for the exact opposite. Or that I’ve burnt what used to be my hourly salary in data center costs to save me a few minutes of doldrums.

It’s funny, I get the impression that you’re doing the exact same thing just with the opposite conclusion to mine. I can’t tell if we just have different priorities when it comes to programming, or some other fundamental miscomprehension of what the other is writing. If there is a conclusion I’m already at and guilty of retrofitting into this conversation, it’s that we are collectively, as a species, taking yet another step towards ballooning our energy consumption out of greed and lazyness and I would at least like to be certain it’s partly enabling meaningful progress towards emancipation of the common person, not further proprietary capture of the tools of labor. This is too close to “factory farming so that everyone can eat (dubiously nutritious) pork chops every day for cheap without doing any farm work themselves” for me to just focus on individual luxury or productivity. I don’t understand how the externalities make up for less manual writing of boilerplate, especially when you need to make the thing double-check it’s boilerplate because it can’t reliably one-shot it.

I want to write more but I’m not certain how relevant it would be to the current discussion, so I’ll just wait to see if you’re still interested in continuing this exchange.

I want to agree, but for example GC has enabled webpages that take 3gigs of ram to do the same tasks we could do with 200 megs fifteen years ago. We don’t automatically build more interesting things once the gritty details and boilerplate are automated, and this stochastic automation gives even more room for “bad practices” to creep in and rob us of the gains it is supposed to bring.

Sorry, I misspoke (miswrote?). I meant growing the code through a genetic-algorithm-like process. Though, fundamentally, I don’t think there’s that much difference between applying a selection process on randomized bytes and having an LLM churn on a codebase.

I feel like you’re only considering the time it takes to reach a particular solution when considering what is inefficient - in which case I would agree it’s probably a wash. However, I don’t think an LLM is less energy-hungry than my own body, and I learn by doing, effectively reducing the cost of future coding iterations. I guess if I could run the LLM and surrounding hardware entirely off of solar power I wouldn’t mind nearly as much - though there’s still that part of banging my head against a problem that I believe is crucial for my own growth. I think that, over time and problems/projects, this compounds in a way that letting the LLM figure out the gritty details just won’t.

I think I agree with your last paragraph, though I do wish the LLM was capable of needing less massaging the more it runs. I hope we’ll be able to figure out how to achieve effectively infinite context length so that it doesn’t have to “forget” all of the previous tasks I’ve had it work on.

I really dislike the idea of making the whole program a genetic algorithm - that approach is nice when you don’t have a straightforward approach to employ/enact, but otherwise it feels both overkill and horrendously inefficient.

The next step for my own harness (whenever I get back to working on it) is definitely to look at leveraging structured outputs to help these smaller models iterate towards a longer term goal.

I’ve been pleasantly surprised by Qwen3.6-27b on a Radeon 6700xt (12GB of VRAM) with 32GB of system RAM for it to offload onto (especially when pushing the context window up past 50k). Definitely more of a “compose prompt and hit send -> do something else -> check back after a while to view results” experience than an engaged back-and-forth, but at least compared to previous models I’ve tried running over the past year or two the results are palatable and sometimes even meaningfully useful.

Given the speed I get, I’ve mostly found it useful for doing overviews of a codebase southy some sort of improvement plan suggested at the end. Tool calls work, but I’m still not comfortable letting it code outright (plus, I think I can still code faster than it for now).

I agree with these “inverse” laws as enumerated, and agree with the reasoning given for them. However, how do we enact them? It seems to me that, currently, the incentives are heavily aligned towards the opposite of these three “laws”.

Turns out we’re both off the mark: it’s catastrophic backtracking that is “dangerously” vulnerable to performance issues. Something as simple as (a+)+b is enough to trigger the “bad” behavior. I assume you can achieve it with back references and lookarounds as well.

This video gives a good breakdown of what exactly is going on inside a compiled regex automata that encodes such a case: https://www.youtube.com/watch?v=gITmP0IWff0

I am thankful I have been away from my arch machine this past week and so never got the chance to install infected updates from the AUR, because I for sure have gotten complacent with checking entire PACKAGEBUILDs. The checker scripts the community has put together found a single potential infected package on my machine - alvr-git - but I had last installed/updated that one on may 21 (so in theory it’s clean).

When the script is three pages long on a 4k screen, and I have ten other packages to review, I have found it’s really hard to stay committed to checking it all with my own eyes. The threat of needing to nuke my entire machine and rotates all my creds will certainly help with that, sadly.