@jlai.lu
"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.
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'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!
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 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 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.
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.
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.
Interesting read, but boy does this journalist have a ... different read on things than I do.
People talk a lot about the protocols that power Bluesky vs. ActivityPub, because we're nerds and we believe deep in our hearts that the superior protocol will win.
IMO it's the exact opposite; we talk about this because we want the best protocol to win, this time, while knowing full well that usually it doesn't.
Of course search was broken because all OSS social tools must have one glaring lack of functionality.
My understanding is that search on the microblogging side of the fedi is intended to be "broken" (from the view of someone expecting a Twitter-style search); hashtags are for opting-in to global discoverability whilst without them your posts are intended to be stumbled upon and/or passed around rather than sought out.
If the American press had given me 20 minutes of airtime I could have convinced everyone they don’t want to get involved with Greenland. We’re not tough enough as a people to survive in Greenland, much less “take it over”.
I doubt that trump supporters cheering on the USA throwing their weight around like the world's bully-in-chief would be receptive to such a message.
I can't tell if I'm just too deep in the fedi-culture weeds, or if the article really is confidently ignorant.
Labeling the AfD as far-right is clearly wrong when you consider that Alice Weidel, the party’s chairwoman, has a same-sex partner from Sri Lanka! Does that sound like Hitler to you? I beg to differ!
Fuck you. There were gay Nazis. There are gay neo Nazis today. Fascism cares about power more than any internal consistency. The moment those gay Nazis are no longer useful to their higher-ups, they'll be disposed of.
When will someone with more reach than I, a random internet commenter, start saying this shit to his face?!?! The people who are swayed by his bullshit rhetoric are not coming here to read our takedowns, and I can't tell if I can expect them to read the counter- and response op-eds...
The background trend, unfortunately, is of the far right slowly but surely gaining votes. We pushed them back to third place today, but they still almost doubled the number of representatives they'll be sending to parliament (from 89 to the projected ~130 for today's elections).
IMO it's largely a consequence of the center-left and center-right (Hollande, Macron) completely abandoning the working class, and demonizing the left whilst cozying up to the far-right (mostly Macron, though Hollande definitely slid right over his term).
Artificial Intelligence Image
For some reason it's hilarious to me that the person who made this flyer felt the need to specify that the ClipArt-level illustration, placed next to 3-4 pictures of the kid the flyer is complaining about, is not, in fact, an actual image of the kid.
I really despise how Claude's creators and users are turning the definition of "skill" from "the ability to use [learned] knowledge to enhance execution" into "a blurb of text that [usefully] constrains a next-token-predictor".
I guess, if you squint, it's akin to how biologists will talk about species "evolving to fit a niche" amongst themselves or how physicists will talk about nature "abhorring a vacuum". At least they aren't talking about a fucking product that benefits from hype to get sold.
thanks for using Leebra!
go to feed...