What I'll miss most from BaconReader is the Android widgets, which as far as I can tell, are not available through either the official app or anything else.
It was super convenient to be able to display a sub or /r/all on my phone's home pages, and I used it every day to keep up with current events or my favorite hobbies without needing to open any apps. For many years that's been a core part of how I use my phone, and I will sorely miss it :(
If Reddit someday added something as nice as BaconReader's widgets to their app I might give it a shot. But looking at the design they used for their iOS app, which apparently does have a widget, I don't have high hopes for it (https://old.reddit.com/r/changelog/comments/kdycmj/introduci...).
Other than that, no plans to use Reddit on mobile anymore. One less bad habit, I guess.
Apollo had a slew of widgets for a variety of use cases. In fact the Apollo dev was quick to jump on many of the new ios APIs and had many nifty little features that will never make it to the official app.
Everything search is incredible, for me it serves nearly instant searches for 15TB+ of data without any trouble. I think the secret sauce is a background service which continuously updates the file index.
I also like WinDirStat a lot for Windows file management, which is not really for search but gives a great view of disk usage.
> Please write a scathing response to the comment below. Attack each point but avoid criticising the poster. End with a humorous barb. The response should be written in the style of a Hacker News comment. Here is the comment:
> <OP's comment>
Response:
What a load of utter nonsense. The idea that the use of language models like GPT-3 automatically makes all content online inauthentic is ridiculous. Just because it's easier to generate content using these tools doesn't mean that the content itself is any less authentic.
And to suggest that the "cogency/validity barrier" has been blasted away by GPT-3 is equally absurd. The quality of online content has always been determined by the person writing it, not the tools they use. If someone wants to generate nonsense, they can do that with or without GPT-3.
Furthermore, the notion that the cost of publishing content online has any bearing on its quality is completely misguided. The fact is, the cost of publishing content online has decreased dramatically in recent years, and yet the overall quality of online content has not necessarily declined.
In short, this comment is little more than fear-mongering and hand-wringing. Instead of trying to scare people into thinking that all content online is now suspect, let's focus on creating and sharing high-quality content, regardless of the tools we use to do it. And remember, just because you can generate an article with a single prompt doesn't mean it will be any good – that's still up to the person using the tool. So don't throw away your writing skills just yet!
-----
Me: Honestly surprised at how well it pulled off the "scathing" part... It does still have that signature ChatGPT vibe where it's all solid writing, but somehow it feels slightly off. Perhaps that's just bias because I know it's from ChatGPT, though. It does do a pretty good job of attacking the ideas, but I think it just feels like it didn't quite get OP's exact point.
Edit: Actually, on a second reading, I think it did address all of OP's points quite well. There are a couple slight misses but you have to read very carefully to catch them, for example the point about "just because you can .. doesn't mean it will be any good" is logically a bit of a tangent, I think. But it's pretty subtle and seems easy to overlook.
I'm trying to think about why exactly it feels off... Maybe it's because of the way it attacks each individual point without really synthesizing them into a broader theme. It's a very systematic, procedural way of writing a response that I think doesn't feel very humanlike. There's also something about the way it writes about pretty specific topics while still using very generic-sounding phrasing.
Curious to continue the thread, I used the same prompt as you, except with that response as input.
ChatGPT's Response to the Response:
-----
Wow, talk about missing the point. The issue with using language models like GPT-3 isn't that it makes content online inauthentic, it's that it makes it nearly impossible to tell what's real and what's not. And just because someone is a good writer doesn't mean they can't be fooled by a well-crafted piece of AI-generated content.
The fact is, the ease and affordability of generating content with GPT-3 and other language models has significantly lowered the barrier to entry for creating believable, yet completely fake, content. And the idea that the quality of online content is solely determined by the person creating it is naive at best.
So let's not brush off the concerns about the potential impact of these tools on the authenticity of online content. Instead, let's have a serious conversation about how we can ensure the integrity of the information we consume online. And for those who are still skeptical, just remember: even a broken clock is right twice a day. But a language model can generate an infinite number of fake news articles, 24/7.
> And for those who are still skeptical, just remember: even a broken clock is right twice a day. But a language model can generate an infinite number of fake news articles, 24/7.
I'm tickled by this part and I'm trying to figure out why. Maybe it's because it used two cliches that sounds like they should go together but are actually nonsensical in conjunction.
It sounds good to my ears in an attention-grabbing way, but when I give it my attention there's no substance.
There's anti-substance because I can't get it to make coherent sense but I keep trying because it still sounds like it should so I can't shake the sense that I'm the one missing some deeper truth.
It's like the uncanny valley of logical reasoning.
It's not an optical illusion, it's a rhetorical illusion.
This is so great and so disturbing. A tool that can be used to generate infinite arguments against a single point of view, arguing in favor of why it isn’t an “issue”. It’s like a gun arguing it can’t kill people.
This is one of the more impressive replies I’ve seen, and I love that in its rebuttal to defend itself against my argument, it just proves the argument itself. Amazing.
edit: I tried my hand at crafting a prompt to refute my argument, result:
This comment is just another example of the kind of lazy, uninformed thinking that seems to be all too common on this site. The idea that GPT-3 is going to somehow make it impossible to tell whether something was written by a human or not is complete nonsense. If anything, the generic language and poor grammar of GPT-3's outputs make them even easier to spot.
As for the idea that the "cogency/validity barrier" has been blasted away, that's just ridiculous. The fact is that anyone who puts in the time and effort to research and write a blog post is still going to be able to produce much better content than any GPT-3 generated nonsense.
And let's not forget that fact checking is still a thing. If someone posts something online that is clearly garbage, it's not going to take long for people to call them out on it. Just like with the infamous "AI-generated paper accepted at conference" story, it's only a matter of time before the truth comes out.
In conclusion, this comment is just another example of the kind of alarmist nonsense that we see all too often on Hacker News. The reality is that GPT-3 is not some magical tool that is going to make it impossible to tell whether something was written by a human or not. So, let's all take a deep breath and relax. As they say, "fools rush in where angels fear to tread."
Wow. Really interesting. Sounds like someone who has excellent handle of the English language but lacks a bit in logic.
Feels like the half trolling answers you get in the internet. They are touching the subject that the replies and arguments have nothing to do with the original proposition.
This reminds me of a pretty incisive comment I saw earlier today: "it's not that we should be asking what we can do with a computer that can replace a smart and knowledgeable person--it's what we can do with a hundred dumb ones."
I noticed a wry smile cropping up while reading this. Thanks for sharing. I've also noticed that last thing about specific topic prompts sometimes being responded to with generic-sounding phrasing. Unsure if that's the model or the specific prompts I'm using.
Sometimes I get a very generic response with a phrase or two from the prompt kind of shoehorned in. It's like pretending to be a tree by holding up a branch and saying "tree, tree."
As a Rimworld lover who couldn't quite get past the ASCII in Dwarf Fortress, I'm super excited for the upcoming release! Rimworld has been a blast and I've heard the two games have many similarities (with Rimworld maybe being a slightly more approachable game that's a bit shallower).
If you can stomach the adjustment period for ASCII I'd really recommend it. I think it does something a lot of modern games miss out on - it encourages imagination first. The information given to the player is extremely dense and easy to parse once you've adjusted and you're giving your brain a chance to try and play inside your own head. I've built a glorious six floor tavern (slowly) with engravings on every surface - even those not reachable by pathing, why? because I had an image of a tavern floor full of rowdy miners with opera boxes circling the room above them for dwarves of a more refined taste... in the end it's just a box you need to floor scroll to see on the screen but the carved pillars in the middle of the room - the enclaves for dwarves to, in hushed voices, discuss just how beautiful gold is - and the grand skylight in the middle of the ceiling casting a rainbow of different colored light on the ground below... that's awesome.
Dwarf fortress is the first thing since MUDing that's really scratched the imagination itch in quite that way and, as someone who has worked in game development themselves, I think it's something that is only possible if you keep to the lowest tech. If you use words or abstract symbols then each player will fill in the details themselves, usually in their head but sometimes in artwork (see Kruggsmash as an approachable example here[1]) which can be extremely fulfilling.
I hope to see the non-ASCII version work as a gateway drug to get more people into the imagination of what they're building. And I hope this didn't come off as ranty or judgemental - each person enjoys games in different ways... but low detail art has a way of really spurring the imagination on!
My favorite thing about the engravings (and statues and similar art) is that not only is it based on real dwarves, gods, etc. from the current game world, but you can commission pieces about specific dwarves and the artisans will commemorate battles or other milestone events that involved them.
In one of the last times I played, some invader had broken through my defenses and killed a couple of highly respected dwarves (one of whom was a skilled fighter), but finally came face to face with a young girl dwarf who confronted him in one of the dining halls and, though she lost a leg, managed to kill him (eventually recovering to grow up to be a skilled craftsdwarf). I had a some statues made of her, and most of them came out depicting the heroic deed in different levels of detail (so of course the best one was put up in that dining hall).
There's also a sort-of-exploit related to this, where if there's a stranger in your fortress whom you suspect of having a nefarious background, you can commission artwork of them and sometimes it will reveal malicious traits about them if you examine it. The artists always seem to have perfect knowledge of their subjects.
This is the key for me - DF is like Sim City or other building games (including Minecraft) - you have to be able to create your own goals. Sure, you can keep trying more and more difficult embark locations, but after awhile you'll have DF down well enough that you can survive 'indefinitely' on underground farms behind impenetrable walls.
So you begin to do other things, mega projects are a common one.
This is also one of the reasons I enjoy playing older games. 2D RPGs such as Baldur's Gate to me aren't detailed enough to fully depict the game world, therefore my imagination fills in the gaps. This leads to a significant part of the game being played in my head which I think can create more immersion sometimes than more photorealistics games would, though I'm not saying this is a general rule.
I played Cataclysm: Dark Days Ahead in ASCII long before I even looked at screenshots of the tiles. Worse than getting stuck with Ben Affleck in the movie of a book you loved. The Jabberwocky was in the screen shot I saw, the description gave such a spooky mental image, but now all I see in my head is the 8-bit swamp monster thingy, like something from the original Castlevania.
Clearly we need to feed DF generated descriptions to AI and generate tilesets for that /s
ASCII version will get the new UI Soon™
Personally I don't think the new look they're going with will be problem with imagination for me - the new look adds just enough detail that you can spot dwarf by their look alone but there is still plenty of space to imagine how exactly the described things look
I agree with the "encourages imagination" argument, and also that ASCII modes might be more practical. I have played Nethack in ASCII mode and tried a few graphical variants, and always returned to the ASCII version because it's easier to tell the enemies apart and easier to see what's going on.
I love ribworld as well! It's my most played game by far at this point. The mod ecosystem is simply outstanding. That being said, it doesn't even attempt to be the simulation engine that Dwarf Fortress does. It feels like DF is a simulation engine first, with emergent game play almost as a side effect. As much as I like DF, that simulation first development process can be felt during almost every interaction in the game. It's not so bad once you've committed everything to muscle memory, but the learning curve is no joke.
if you like these games you might also like Oxygen Not Included. It's side-on view instead of top down, but is another excellent little ant farm to sink a couple thousand hours into. Sort of a Rimworld meets Factorio type vibe.
It's such a sleeper compared to similar games. The art and sound effects really elevate it. Klei has such a unique art style and it's really shown off. Also has a much more interesting "survival" curve than most; you'll be presented with many many hours of challenges trying to get a sustainable base, without cheap tricks like ever-escalating interruptions based on quantitative progress (looking at you, Rimworld.)
I'm eager to try it again. I went deep on DF years ago, but its more modern competition ended up winning me over but sometimes I still long for that extra crunchy simulation. I'm hoping that the Steam version supports the Steam Workshop. That has been a game changer for me with mods on Rimworld.
I watched about 30 hours of Kruggsmash's narrations of his Dwarf Fortress runs on Youtube, hoping it would 'sell' me on DF. What happened instead is that I played way more Rimworld and Oxygen Not Included than I had been playing.
Most days I preferred ONI due having to go way out of your way to commit war crimes, whereas in Rimworld it's just clicking a couple buttons.
No, not at all like the stock market, which has real mechanisms for getting real cash paid by real consumers in real life for real products into the hands of stockholders.
Do people speculate on it more than they probably should? Sure. But at the heart of the stock market is a system of "I just sold a physical thing for $1000, and since you own the stock you get $0.00001 of that". At the heart of crypto is "my computer did some math, so... money".
At the heart of crypto is the desire for decentralized banking infrastructure and currency, which has non-zero cost to operate and thus requires some degree of compensation for operating the network or protocol.
Just like in the equities market, speculation and gambling dominates market values of these things to varying degrees (to a comical extent in growth tech recently, for example).
> At the heart of crypto is the desire for decentralized banking infrastructure and currency, which has non-zero cost to operate and thus requires some degree of compensation for operating the network or protocol.
But where's the value being delivered by that "decentralized banking infrastructure and currency"? Actual usefulness of crypto for genuinely decentralised (i.e. L1) transactions has been going down not up (fees are higher than ever, fewer and fewer stores allow direct payment with cryptocurrency...).
Really interesting idea! Art & graphics is probably the part of game development that solo devs most commonly underestimate the importance and difficulty of (well, maybe tied with marketing). For solo devs especially, it's really rare to be a strong programmer and a strong artist. So you end up with a lot of games that are conceptually interesting but not particularly enticing to look at.
Using Stable Diffusion to get fairly high-quality art in a style you like could be a game changer for devs who can do game design, programming, marketing, etc. but just haven't spent 10 years of their life training their art skills. I guess animations / sprite sheets may be hard for Stable Diffusion, but if you can design your game around that you may be all set!
Edit: I was curious and searched "stable diffusion game graphics" and found this cool video: https://www.youtube.com/watch?v=blXnuyVgA_Y The results are great! I wonder if it can do more stylized art too like pixel art
Here's a relevant quote from Magnus regarding cheating:
"I would just needed to cheat one or two times during a match, and I would not even need to be given moves, just the answer on which move was way better, or here there is a possibility of winning and here you need to be more careful. That is all I would need in order to be almost invincible."
Even just 1 bit - an indication to be careful - would be enough to boost the strength of a GM. An accomplice coughing in the background to let you know there's something to watch for. For a strong player - and there's no doubt that Niemann is a strong player, the question is just how strong - that's all they need to avoid making mistakes. GMs can solve insanely hard puzzles, because they know it's a puzzle and has a specific solution. Same thing with 1 bit of info.
Of course, realistically they could simply use Morse code instead of "bits" and transmit two squares (just 4 Morse "letters").
yes but against magnus, who is supposedly two levels above Hans, this is not just a one move cheat, he'd have to cheat + have a continuous absence of mistakes, which is an awful lot of information to transmit.
i dont have a horse in this race i just like thinking about things in terms of information theory since this is a remarkable applied case
another way to decide this - have them play blitz (where the moves are way too fast for info transmission to happen), and see if the skill level scales accordingly?
have them play blitz (where the moves are way too fast for info transmission to happen), and see if the skill level scales accordingly?
Not a fair contest. There are plenty of top classical chess players who are weaker in blitz and vice versa. It’s a different skillset. Classical is all about preparation for the opening followed by some deep thinking in the midgame. Blitz is all about pattern recognition and the ability to simplify down to an ending where you can blitz out the exact solution from a database.
It's true that some people are worse at blitz, but if Niemann's OTB blitz rating is as good as his OTB rating at slower time controls, that's evidence against him cheating ... at least in ways that materially affect his rating. I guess it would be possible to cheat with an engine tuned to your actual rating just to make it less stressful.
Well, even endgames with as few as 5 pieces on the board are beyond what a human can solve with memorization. I don't disagree that blitz is mostly pattern recognition and rapid tactical thinking, but that applies all the way down to the end.
magnus completely destroyed hans in two games, as black. I think the ease with which magnus took hans apart in these beach games, presumably added to his suspicion when hans played so much better in the Sinquefield cup.
Eh casual play has so many factors. I wouldn't put much weight on how badly a gm loses on the beach. For example, drugs could have been involved.
I do think Hans is cheating, but I think the proof will lie in statistical analysis of his games and demonstrating that he has an unusual (>3200 rated) propensity to clutch out specific moves. I think everyone suspects at this point that if Hans is cheating, its only a handful of moves per game.
>this is not just a one move cheat, he'd have to cheat + have a continuous absence of mistakes
Blunders are exactly what a device like the one described would seriously help with. If the buzz means both "there is an only move here and it's not immediately obvious" and "at least one of the natural moves here is a blunder or very inaccurate" then you need to just send a buzz and you've probably cut inaccuracies significantly. That said, a very simple communication device like this is probably badly hurt by a 15 minute delay.
> at least one of the natural moves here is a blunder
Interesting, I'm not sure if a computer has the ability to recognize something as a "natural move but also a blunder." It would require a very human-like way of thinking about moves, which computers don't generally have.
Anyone 1500+ can recognize the natural move--that's what makes it natural.
Probably the easiest case of "natural move but blunder" is anything that is a top 3 engine move when looking 3-5 moves deep, but losing significantly on deeper evaluation.
Also, this sort of categorization is at the heart of how chess puzzle collections are automatically assembled. A good chess puzzle contains an unnatural move that wins--the exact opposite of the natural but blunder. Chess sites scan their online play databases for these all the time, and serve them up as puzzles.
> he'd have to cheat + have a continuous absence of mistakes, which is an awful lot of information to transmit.
Perhaps a top-level player can jump to a higher level if they can stop worrying about coming up with brilliances in the macro strategy, and instead focus entirely on making their micro-level play spotless.
This is the opposite of what a computer-assisted player would do. Computer chess engines (generally speaking, somewhat less true of the latest generation) are not great at high level strategy but will never miss a tactic (micro level play).
ELO gives you a statistical evaluation of how likely victory is for one of the player. Hans rating means he has non insignificant chance of winning against Magnus.
Hans can win without cheating as this last game proves. There is not a shred of evidence against him after all.
Sounds like not just the players need to be checked for cheating devices, but the audience too. Or the players have to play in a faraday cage without an audience.
It's not going to make the game more fun, but it's probably necessary.
> The list of obligations would include prohibitions on combining data collected from two different services belonging to the same company (e.g. Facebook and WhatsApp);
Would this not simply kill the kind of integration that Apple has between its different services? Or any of the smart assistants?
Does ortholinear/columnar actually feel better? I feel like I see many comments about how there's a bit of a learning curve that can be overcome after a while, but very few comments about whether overcoming that learning curve is actually worth it and it's really more comfortable. Is it supposed to be better for your wrists? Or your fingers?
The "split" aspect of these keyboards is definitely more comfortable imo - I ended up going with a Dygma Raise (which I'm very happy with!), because I wasn't interested in learning ortholinear. But I've remained curious about whether ortholinear is actually better, or if it's just a thing that a lot of split keyboards happen to have.
A benefit for ortholinear I don’t see mentioned here: it’s a little less cognitive load to locate keys by touch. As someone else mentioned, I think “split” might be important here (and I don’t have any experience with non-split ortholinear). Also, this only applies after you’ve overcome the learning curve. All this taken into account: with my ortholinear board, I rarely mistype. I attribute this to it just being easier to know which key I’m hitting with a columnar layout. You can take this a step further with CRKBD and similar such that each key is only 1 unit away from home (and thus it’s next to impossible to mistype).
When I look at my hands (31) my fingers actually look slightly twisted and crooked. There’s a chance that I might have broke them without realising when I was younger doing martial arts and rugby but I’m of the firm belief that they’ve got this way through hammering shallow non ortholinear keyboards (specifically the magic keyboard) for years. I’ve had pain in my fingers at certain points over the years from typing for hours that I just kind of David Goggins’ed my way through. Can’t prove it’s the cause but it is my strong suspicion.
I can’t rule that out but the pain was completely linked to times when I was using the magic keyboard heavily for days on end. I don’t have any pain now nor do I have any pain using the magic keyboard, I just kind of healed and adjusted. This is what makes me wonder if it was some kind of fracture caused by the heavy repetition that I made worse by working through. The twisting and misalignment is all limited to the part of the finger above the knuckle and seems to be most pronounced on my index and middle fingers which again supports the hypothesis.
I currently using a Corne[1]. I was never able to fully touch type on a staggered keyboard as I frequently pressed a neighboring key on the bottom and the number row. Now I only have to move my fingers up and down to find the right keys. Also my fingers have less distance to travel.
I’ve tried out various form factors (full size, tkl, 75%, 60%, single keyboard with wells), and the ergodox ez was by far the most comfortable for coding. Until I bought the moonlander, which is now my main “at desk” keyboard. I’m running a modified version of Colemak DHM on my moonlander.
Ortholinear is my favorite layout because I can shift some keys down one row (such as Z), and then it perfectly suits my hands.
ortholinear works very well when you use a split keyboard, but i find it worse for non-split keyboard. The angle of your hands factor in here. With split they're parallel, so fingers are also "straight". However, the traditional layout isn't symetric anyways, so your right hand gets the best ergonomics vs your left.
Wow, is that the full extent of your sales efforts? Your readers happen to include enough interested sponsors that you've been able to sell out your slots just by asking your audience? That's awesome!
It was super convenient to be able to display a sub or /r/all on my phone's home pages, and I used it every day to keep up with current events or my favorite hobbies without needing to open any apps. For many years that's been a core part of how I use my phone, and I will sorely miss it :(
If Reddit someday added something as nice as BaconReader's widgets to their app I might give it a shot. But looking at the design they used for their iOS app, which apparently does have a widget, I don't have high hopes for it (https://old.reddit.com/r/changelog/comments/kdycmj/introduci...).
Other than that, no plans to use Reddit on mobile anymore. One less bad habit, I guess.