Well I always just start with practical stuff, unless it appears it's going off rails ona specific kind of way repeatedly. Then I try extreme negative prompts to see if it fixes the issue - which it often does.
I wouldn't say I'm roleplaying an asshole. I'm just using an llm in the best way to get the best accuracy.
It's not like a personal, secret fetish. It's just a system I use as needed.
I don't get why you are so uncomfortable with this? It's just tokens in and out of a language model. I feel absolutely nothing when I'm typing "assholish" words to get the output I need.
easily liking any kind of music only on the merit that it is human generated seems lazy, too.
similarly, firing up a music gen system rather than listening to a billy joel song for the 30,000th time seems less lazy.
say what you want about AI systems, people that I used to see idly sit at a screen and ingest things all day purely are creating things they like now and sharing them. The thing is easier but the engagement seems greater for a lot of people. It's not as black and white as "oh you're lazy." -- and, by the way , that seems so wildly inappropriate to label an unknown third party as site-unseen -- dare I say that seems lazy?
Nobody does that. Literally nobody likes a piece of music just because it was made by a human.
But consider an album I found a couple of years ago, called "The Unfinished Violin". A UK folk musician, Sam Sweeney, bought a violin he thought sounded really good, noticed a name in it. Researched who he was. Turns out he was a music hall performer from Leeds. He had made the parts for the violin, but before he could assemble it, he was sent to fight in WW1 and died in Flanders. The violin had laid unfinished in an envelope for the better part of a century. Sweeney arranged a lot of time-appropriate, military related music for the album, and wrote a few himself too.
I didn't know any of this when I first heard "The highland soldier" on Spotify DW. I just thought, wow, that was a beautiful tune. And it sounded like it meant something to someone. And it, turned out, it did. It meant something to Sweeney, it meant something to the folk music collector George Butterworth who wrote it down (and then also died in WW1), it meant something to the people he recorded it from.
If I heard a Suno tune, it's entirely possible I'd also think, wow, that's a beautiful tune. But there's almost no human connection. Nobody cared about that music. It's not entirely devoid of humanity, because of course Suno was trained on the music of people who cared and had something to express, and there's an echo of it. But the link is severed. It has no human provenance.
You can cut yourself off from humanity, just use audio as a drug and not care where it comes from. Certainly a lot of people did that long before AI. But why, when there's so much human music to connect with?
> I don't think people want to live in a fake world.
yeah that's why escapist hobbies , movies & video games do so poorly.
it's not even 'another world' , it's just a slightly different kind of screen, one that you wear. You get to use it for what you want -- maybe escapism is that thing -- but we'd never say that some beancounter working on an excel sheet is living in a fake world (although you should say that wrt a few of them..)
There is a huge difference though, and I say that as someone who started his career as a VR dev.
Unless you life fully alone, there is definitely a different level of vulnerability and isolation in effectively blindfolding yourself that is very hard to ignore. Even after months working daily using these devices, it still felt awkward to sink into one in an open plan office. I can't imagine doing it in a living room while your family is around, or near roommates, or a plane.
>> Unless you life fully alone, there is definitely a different level of vulnerability and isolation in effectively blindfolding yourself that is very hard to ignore. Even after months working daily using these devices, it still felt awkward to sink into one in an open plan office. I can't imagine doing it in a living room while your family is around, or near roommates, or a plane.
Tonnes of people live alone. A huge normal of people now work from home. If you're using it as a monitor to work like suggested in the post you're not going to be doing that around family/roommates anyway even on a laptop. You're going to be in a room by yourself.
I’ve never met anyone in real life who enjoys a screen strapped to their face. No one I know ever talks about VR headsets as anything other than a novelty thing you do at the mall.
The only place I’ve ever seen anyone say positive things about VR is online.
I may be proven wrong but I’m convinced it’s a small minority who care about VR headsets, and a good portion of them seem to be the terminally online.
it's a shame that the vatican didn't bother asking whether or not the crusades would make humanity better before causing the death of 9 million plus people.
..or whether or not hiding all those pedophiles was the right.
and to be clear ; i'm not equating AI to those things -- i'm saying that I don't care about the opinion of a group with such a sordid history regardless of how shined up the PR is now.
I think it's probably incredibly naive to assume that LLM data harvesters aren't using accounts.
Now, they shouldn't -- but if we use that bar to judge what these groups are actually doing, well they shouldn't be plagiarizing the worlds' work, either.
There have also been winners of a slot machine gamba, so the analogy quite holds. I would even argue that there are considerably more slot machine gamba winners than the real world examples of actual LLM work.
the obvious answer is because it's easier , faster, and more efficient to flip a true to false right in front of you than it is to prompt an llm.
if your response is "my prompts don't produce code that needs values flipped, ever." then I would wager you're only touching very simple things with an LLM.
for me I don't care about the token cost and prompt writing so much as the fact that it's just faster to change 0 to 1 and leaves me twiddling my thumbs for an llm output less.
The thing that drove me away from manual edits was that I found myself confusing the LLM all the time. It would read or write, some code, I'd twiddle with things, and then the LLM's future references to the same code would be a mess.
On balance, and via dictation, it feels likely to be faster overall to just enact the changes I want 'inline' of the conversation thread.
Is this stuff any better now? I think current harnesses probably do have things like file change listeners that automatically inform agents before they act on a file they've previously engaged with if it has changed in the meantime.
If you do manual edits, I find it best to start a new conversation. But if your instructions and documentation is good enough, the new conversations won't have any problems picking up where it needs to be.
Having said that, I fear what June 1st brings for copilot
It might suddenly be very useless for me.
But why did you flip that true to false? It sounds like a missing unit test. So at a minimum it’s do the flip, find the right place to unit test, and write a test. Or I just tell my LLM “this should be false because of X, fix and write a test”
I just use Codex/Claude Code in one window and Neovim in another and navigate around using Niri’s keyboard shortcuts. I much prefer it to VS Code on a traditional desktop in almost every respect.
a very near example would be immersed vr which is compatible with xorg and does essentially the same thing (2d windows pasted all over a 3d world), although not integrated into minecraft. also since their solution isn't wayland-centric it has ports to osx and windows.
>If you're reading this, you're likely in the same boat as me. You've discovered that Immersed can create virtual monitors for Windows and Mac, but on Linux, this feature is marked as "unsupported" on X11. This means you can't create virtual monitors directly through the Immersed agent. For now, the known workaround is to manually set up virtual monitors. If you use Wayland, now immersed offer support for native virtual displays on the Immersed agent on gnome Wayland. You can access this options in Immersed client menu -> Setting -> Configure virtual displays. Other Wayland DE/Compositors are not supported, but there are ways to create virtual monitors manually as we do on X11, please check the linux-help channel in the Discord server for more info.
Basically immersed vr doesn't support X11 windows, it only supports X11 screens, which means you would have to create a new screen manually for each window.
Wayland is far more minimal API than X11 that mainly cares about surfaces and inputs. So, it's understandable that it can be "easily" translated to a game engine.
X11 has an entire drawing API. It'd probably be easier to run through Xwayland.
> it's somehow not that unpopular among the less bright.
politics aside, do you realistically believe that you can view twitter and actually mentally carve out the opinion of a group of people in real life?
that's exactly the issue with twitter.
for one : you're polling twitter users (a TINY subsect of humanity), two : you're extracting opinion from those that seek to broadcast it (an outlier) , and three: twitter never self-exposes the world to a user, it selectively curates and amplifies, and fourth : it's one of the most gamed communications arenas in existence.
you're viewing the world through an itty-bitty twitter-colored monocle and making sweeping accusations across large cohorts, it's not an accurate portrayal of actual human opinion.
I don't think it's a perfectly representative sample of people in real life, so I always view it as an anthropological experiment, as if I'm visiting wild tribes... but still am finding the proportion of people in favor of this decision to be surprisingly high.
then add it to your pre-prompt, no need to practice roleplaying as an asshole.
reply