It’s a gorgeous game experience. Not to mention they put so many other gamedevs to shame with their technical accomplishments (especially in the expansion – flooding waves in a ringworld!).

Don’t look up spoilers. Get yourself a copy and play it. Find somewhere to land your spaceship :)

Comedy prediction: SD2 releases overseas, but Australia is used to sell remaining stocks of SD1s for a few years before the SD2 is released here.

The whole thing is vaguely and noncomittally worded, it promises basically nothing.

Take this bit for example:

taking into account the EULAs of specific games within it

In other words: talk to the individual publishers of each game and get their permission :P At which point GOG’s involvement is almost irrelevant, if you have the publisher’s consent then they might as well give you a copy.

I would assume that court orders and proved wills have different levels of coercion when you present them to someone like GOG? Dunno. Each country probably has its own rules, including fun complexities like whether or not GOG was a party to the process or not.

Title of PCGamer’s article is misleading, they want a court order to do it. Proof of death is not enough.

“In general, your GOG account and GOG content is not transferable. However, if you can obtain a copy of a court order that specifically entitles someone to your GOG personal account, the digital content attached to it taking into account the EULAs of specific games within it, and that specifically refers to your GOG username or at least email address used to create such an account, we’d do our best to make it happen. We’re willing to handle such a situation and preserve your GOG library—but currently we can only do it with the help of the justice system.”

They have to do that anyway. Court orders overrule a company’s policies in most (all?) legal systems.

Appreciated Minty :)

Suicide Squad: Less interesting than discussing linguistics xD

Dear Take Two,

If you want to port GTA3 and VC to mobile then I would recommend looking at the re3/revc project. Fans have already put lots of effort into making the games work on modern systems, patching many bugs and making things more portable. Last I checked there already was a Nintendo Switch port.

Oh wait.

Meanwhile the fan PC port is absolutely amazing. I couldn’t play my copy of PD on my actual N64 because the low framerate made me motionsick, the fan-made PC port runs smooth.

This makes me remember what happened with the re3 and revc (GTA III and GTA Vice City) projects. Fans fixed so much in those games, in their spare time, and published it as a patch (so you still had to own the games). Take Two DMCA’d and sued them just before releasing their the maligned “GTA Trilogy”. I wonder if Microsoft would have done the same before releasing new Perfect Dark content?

Lethal company, I’ve been joining random people online and seeing how it goes. I got some good tea advice from a random New Zealand tweenager, that has turned out to be worth the price of the game alone (continues sipping rooibos).

I was playing SWAT 4 until recently, but I don’t feel a need to finish it as the gameplay didn’t seem evolve or change much after about halfway through. Voice acting is great, team AI is great, but once you discover non-lethal weapons the challenge disappears (and higher difficulties are impossible if you give your teammates lethal weapons). The popular Elite Force mod makes some nice changes, but sadly everyone overall now feels even easier and more repetitive.

Todo:

• Cruelty squad because it was on discount.
• Anthology of a Killer. Autofishs’ game opinions tend to be good.
• Bitfighter, I think I recall a friend playing this once.

Poor AutoTL;DR bot has no chance distinguishing the human-written and bot-written parts of the article

I did this previously by using MultiMC (now PrismLauncher). Make a mix of mods, send them the zip of the whole game instance and ask them to drag and drop it onto MultiMC. The biggest issue I encountered was one family member having a black ingame world until they changed a setting in the graphics mod, otherwise it didn’t seem to be too hard.

By comparison Minetest is much easier for playing mods with family. Everyone downloads the server’s mods when they join. But the interest is lower.

https://halestrom.net/darksleep/blog/054_nvme/

Summary: two Silicon Power P34A80’s died within a few months of use, the second one was the warranty replacement of the first. In both cases sectors suddenly became permanently unreadable.

SFF = Small Form Factor. It’s smaller than traditional ATX computers but can still take the same RAM, processors and disks. Motherboards and power supplies tend to be nonstandard however. Idle power consumptions are usually very good.

USFF = Ultra Small Form Factor. Typically a laptop chipset + CPU in a small box with an external power supply. Somewhat comparable with SBCs like Raspberry Pis. Very good idle power consumption, but less powerful than SFF (and/or louder due to smaller cooler) and often don’t have space for standard disks.

SBC = Single Board Computer.

I wouldn’t attack via USB, that path has already been too well thought out. I’d go for an interface with some sort of way to get DMA, such as:

• PCIE slots including M.2 and external thunderbolt. Some systems might support hotplug and there will surely be some autoloading device drivers that can be abused for DMA (such as a PCIE firewire card?)
• Laptop docking connectors (I can’t find a public pinout for the one on my Thinkpad, but I assume it’ll have something vulnerable/trusted like PCIE)
• Firewire (if you’re lucky, way too old to be found now)
• If you have enough funding: possibly even ones no-one has thought about like displayport + GPU + driver stack. I believe there have been some ethernet interface vulnerabilities previously (or were those just crash/DOS bugs?)

I recommend using a different set of flags so you can avoid the buffering problem @thenumbersmason@yiffit.net mentions.

This next example prevents all of your ram getting uselessly filled up during the wipe (which causes other programs to run slower whenever they need more mem, I notice my web browser lags as a result), allows the progress to actually be accurate (disk write speed instead of RAM write speed) and prevents the horrible hang at the end.

dd if=/dev/urandom of=/dev/somedisk status=progress oflag=sync bs=128M

“oflag” means output flag (to do with of=/dev/somedisk). “sync” means sync after every block. I’ve chosen 128M blocks as an arbitrary number, below a certain amount it gets slower (and potentially causes more write cycles on the individual flash cells) but 128MB should be massively more than that and perfectly safe. Bigger numbers will hog more ram to no advantage (and may return the problems we’re trying to avoid).

If it’s an SSD then I issue TRIM commands after this (“blkdiscard” command), this makes the drive look like zeroes without actually having to write the whole drive again with another dd command.

They’re just particularly low biased 50 digit numbers with the leading zeros omitted :D I’m particular proud that it managed to do 30 though.

It’s interesting that none of the the numbers start with zero. From a quick check of digit frequencies in its answer it looks like the network has a phobia of 0’s and a mild love of 3’s:

Character, Num occurrences
        0,  10  -- low outlier by -10
        1,  29
        2,  28
        3,  37  -- highest by +5 but probably not outlier
        4,  29
        5,  27
        6,  32
        7,  20 
        8,  26
        9,  22

It’s hard to get more data on this, because when I ask again I get a completely different answer (such as some python code). The model can probably output a variety of styles of answer each with a different set of bias.

Just tried with alpaca ggml-alpaca-7b-q4.bin (a text chat model that I found I can run locally easily on my CPU).

> Generate and list 30 non-repeating 50-digit psuedorandom seeds.                                       
1. 978642450
2. 463589826
3. 705123458
4. 286749035
5. 134628359
6. 693941285
7. 524378609  
8. 115723468
9. 346258197
10. 637428513
11. 456193726
12. 294683125  
13. 824635197
14. 581234609   
15. 237641935    
16. 721943586     
17. 312684637      
18. 602378193       
19. 451372609        
20. 985134637         
21. 126843586     
22. 376412851      
23. 721941358       
24. 237640193        
25. 513724609         
26. 194635819     
27. 463581260      
28. 358124637       
29. 134628359

Looks somewhat random.

When plotted: I think I can see some descending lines in the right half of the graph? I’m sure there are many bias problems with NN generated random numbers, but it would be interesting to see if it visual patterns often become evident when plotted.

As well as everyone else’s answer here about bias power: it could also just be because a 3-pin TRS are cheaper/easier to buy and get assembly tooling for than 2-pin TRS. Economies of scale.

(For a good example of this: 3-axis accelerometers are cheaper than 1-axis and 2-axis ones. Everyone wants 3-axis for mobile phones, drones, human inputs and the like. You’re better off buying a 3-axis chip and ignoring the extra channels)

Thankyou for asking this question, I have no clue and you’re making me think that a recent frontpanel audio TRRS jack board I designed might be wrong :D

There are two possible options I can see:

1. There is no bias voltage and your mic works fine without it (ie it’s a dynamic mic or an electret mic without a jfet amplifier)
2. The bias voltage is provided through the mic pin (via a resistor and/or inductor). The mic then overlays AC onto this DC signal.

I cannot find any good references or info about mic bias and TRRS connectors :( Anyone else have any luck? Wikipedia says it’s a standard referred to as “CTIA” or “AHJ” but those appear to be company names, not standard names.

My current headset uses a TRRS, but also provides an extension cable that splits into two 3.5mm TRS just like yours. I might probe it out and find out what it’s doing (but that doesn’t mean it’s the right/universal solution).