I thought one of the parents had pointed out that Nero allows you to burn the iso directly from DVD Shrink, rather than ripping, then burning. In any case, if you're happy with DVDD, you should keep using it. I'm just saying you shouldn't ignore a solution just because it isn't free. Nero has a lot of great features; I happen to like it. I don't do any DVD ripping, but Nero is a pretty complete suite for DVD/CD authoring, IMO.
-Dan
The point is that consoles don't really sell for those low prices until they've been around a long time. The price of Doom3 will not be $55 in 4 years, either. If you are willing to wait 4 years to buy something, you can usually expect to get a great price on it.
I could similarly complain that Doom3 is way overpriced, because I just picked up Starcraft for $5, and Starcraft is one of the most popular games of all time! You pay a premium to get something when it comes out, and comparing it to a totally different product that's several years old doesn't indicate a whit about whether the price is reasonable.
If you're willing to compromise and use a non-free OS just to copy DVDs, surely you can shell out $40-$60 for a great piece of software (Nero) that makes copying these DVDs a little easier.
You make it sound like you're taking a principled stand by avoiding non-free software, but you are obviously willing to compromise out of necessity. If you really want to support free software, maybe you should refuse to use these products because they don't have a version that runs on free OSes (not that I would recommend that).
I like free software because of the good results it gets, not simply because it is free. That's just me, though
"Brand new console" is something of a misnomer here. Do you mean the 4-year-old console that was $300 when it came out (PS2) or the 3-year-old console that was also $300 (Xbox)?
Let's not forget that these consoles were sold *below* cost with the intention of making money on the games.
I'm not saying $55 isn't a lot for a video game, but comparing it to the price of 4-year-old consoles that were sold at a loss doesn't prove anything. What you should compare it to is console titles, because console titles are supposed to make up the loss on the consoles. OTOH, PC titles have no need to make up said loss, so why are they getting just as high as the console titles?
UT2004 was a nice exception, costing me only $25.
-Dan
Re:The correct responses
on
Are You Annoying?
·
· Score: 4, Informative
Your frustration is understandable, of course. After you figure out what the problem is, you can remind the user to check the error message, not do what he/she was doing wrong, etc. But being mean about it isn't going to fix the problem, it's just going to make them not want to ask you when they have a problem. When that starts happening, people start to hate IT and start thinking about replacing them.
Even if the user is wrong every time, it's your responsibility to help them. Some people just never learn, but if you keep helping them in a friendly way, they will worship you and think you are indispensible. When you start to write them off and act like it's always their fault, they will be just as frustrated with you and want to get rid of you.
USER: I can't send e-mail. E-Mail doesn't work. The system must be down.
IT: I don't think the system is down. Let me see. Hmm, I can send mail. I wonder why you can't.
USER: It doesn't work for me.
IT: Did the computer give you any error message?
USER: I think so but I wasn't paying attention.
IT: Ok, let me come look at it. Maybe something is wrong with your account.
-----------
You're supposed to have an attitude of wanting to help, not proving it's not your fault. Jeez, no wonder people hate IT users, with responses like that.
Unless you know the business internals and license agreements of those companies, you have no idea whether they respected the patents or not. However, all major graphics program vendors (Adobe, JASC, etc.) have LICENSED the gif compression algorithm, and used it in their programs. Those who paid to use those programs have the right to create gifs.
These commercial softwares did not disrespect "IP-rights," they meticulously followed the law by doing exactly what's required to use the patented algorithm. They showed respect for the patent by paying to use the algorithm. Free software respected the same rights by not using what they hadn't paid to use (because they either couldn't or weren't willing to).
I wasn't talking about the GT, but it is a good point that the GT, which is smaller and quieter than the Ultra, and cheaper than both the Ultra and the X800, is also beating ATI here by a significant amount. Hopefully ATI can do something about this performance problem.
However, it is worth noting that in general, Nvidia's had to resort to a "multi-slot monster" to beat ATI. The GT is a good move, and has a great price/performance ratio, but it simply doesn't match up well to the X800 in D3D titles, for example.
I'm planning to upgrade my computer soon, and I still haven't decided what to get. But I'm fairly sure it won't be Nvidia's high-end one; I'm still considering ATI's and the GT.
Are you implying that Carmack made the above statement? Because...he didn't. That's Kyle Bennet, the author of the HardOCP article speaking. Carmack only made the brief statement at the beginning (it's color coded to help you spot it), which states that "all of the modern cards play the game very well," and "there is no egregious cheating going on," and most importantly, "Nvidia drivers have been tuned for Doom's primary light/surface interaction fragment program."
I don't think Doom3 will be significantly changed to help out ATI, but I'm positive ATI will change their drivers to help out Doom3's performance. As Carmack pointed out, the Nvidia drivers have already been fine tuned for Doom. My guess is that ATI, after the fiasco with releasing the Doom alpha, hasn't had as much opportunity to optimize for Doom.
On the other hand, it's no surprise to see ATI losing to a card that obviously has more horsepower. Frankly, I'm impressed that a card that's so much cooler, smaller, and quieter does so well against Nvidia's monster. But in this case, at least, we see Nvidia's power fully utilized. Hopefully, ATI gets so more performance out of theirs, though.
MS has never minded OpenSource software via BSD license or what-not. Their real gripe is against GPL. OpenSource BSD-style license promotes standards and provides code for the world to use, regardless of their licensing model. GPL helps GPLed code, and no one else, unless you only want to use the programs, but not the code.
This would be more like your apartment complex putting a "No Solicitors" sign on the gate outside. Oh, and this apartment complex is small and cramped, but it's free to live there.
I would like to test this as well.
lllammme@hotmail.com
-Dan
The speed of java is only one concern
on
Java Faster Than C++?
·
· Score: 3, Insightful
What concerns me most is the amount of memory it requires. In theory, once the requisite stuff is loaded into memory, Java byte code can be processed at nearly the same rate that C++ code is. Depending on the bytecode and assembly that are generated in each case, Java or C++ could end up being faster. I think it's obvious that Java incurs some overhead in translating the bytecode, which ought to slow it down *some*, but that amount can be minimized.
On the other hand, Java takes a great deal of memory. If C++ had a dedicated server sitting in memory, ready to execute commands for it, it probably would speed up execution, but that wouldn't mean C++ were faster.
After accepting the memory hit for Java, the performance on things like apps servers seems to be pretty decent. I have yet to use a java client application, however, where I didn't feel that it was sluggish (even after loading). There are only two explanations: all java code is written poorly, or Java inherently causes a performance hit.
As we abstract languages more and more, we see performance hits for increased functionality and ease of developing. We also see that, because of the easier development, it is easier to improve scalability and use more efficient algorithms. It is rare that a program cannot be sped up by hand-optimizing the assembly, but it is also rare that anyone has time to design the much more critical optimized algorithms at such a low level. Therefore, I predict that eventually Java (or something like it) will be embraced as programmer time matters more than speed of execution.
The one thing that disturbs me about Java is that, while in C++, it is easy to change the assembly while maintaining the C/C++ code, in Java, you are tied to platform-independent code, which prevents you from doing platform specific optimizations. You have to depend on the native java implementations and/or widget toolkits for those kind of things. And so far, although the situation is improving, I've been pretty unhappy with the speed and my ability to improve it.
This is true:
"I got an email suggesting that I re-check NetBSD. The results are nothing short of astonishing. In two weeks time the NetBSD team made dramatic improvements."
This is impressive and we should congratulate the NetBSD team for optimizing so quickly. However, let's not forget they did so in *reaction* to specific benchmarks, rather than having generally fast code which was proven by a few specific benchmarks, as FreeBSD 5.1 and Linux 2.6 did. Unless proven otherwise, I'd be forced to assume that generally, the code scalability in NetBSD is less than in FreeBSD 5.1/Linux 2.6, with these specific benchmarks being exceptions.
Undoubtably, all of the OSes/distros could have been tweaked to improve these benchmarks, but NetBSD is the only one that was, or we were made aware of. Again, congratulations to them for showing they could fix the problems these benchmarks exposed, but it's not nearly as impressive as having good code the first time around. We know they can code to fix a flaw, but can they write code that scales well on arbitary code?
-Dan
I didn't say it was because they respected copyrights, I said it was to *show* they respected copyrights. In any case, as I said, just because a company violates copyrights does not mean they don't respect them. It happens all the time, to many different companies. The test is how they respond when someone points out their violation. There is no way to guarantee _anything_ is original, except by having compared it to every possible source in the world. Obviously some employee at SCO chose to plagiarize, SCO was informed, and SCO paid up. I don't understand what the problem is.
-Dan
I disagree with most of you
on
SCO Caught Copying
·
· Score: 4, Insightful
Yes, SCO was caught violating copyright. Is there any company in the world that doesn't do this, on occasion, by accident, or because some employee pretends he wrote something he didn't? I doubt it.
The test of respecting the copyright, however, isn't *never* violating one, but fixing it when you realize you have. SCO did exactly what it should have, here, and both parties are perfectly satisfied with the result, I should think. SCO's quick action shows that they are eager to demonstrate how much they respect copyrights of others.
Does any of this mean SCO's suit is more or less merited? No, of course not. Does this infringement make them hypocrites? Not unless those filing the lawsuits sanctioned this infringment.
Now, the one point that someone made which has some validity is that SCO is hypcritical to suggest that Linux's review process is tainted, when they themselves are unable to review sufficiently to avoid infringement. SCO has no business complaining about the review process of any software if they cannot guarantee their products are 100% clean (and no one can, of course). SCO has made that argument to make Linux sound out of control and "scary," but it is not really a legal argument, just a tactic.
Like SCO's documentation, Linux is open for review at any time by anyone. Like SCO's documentation, if something infringing is in Linux, it is likely to be noticed by the copyright holder. SCO is saying that they have noticed such a thing, but unfortunately isn't able to point it out. That is what makes this documentation case so cut-and-dry, and the Linux one so out of control.
Personally, I think SCO should put up or shut up...but the fact that they were caught infringing, and made amends doesn't do anything to the validity of their suit. From their point of view (assuming they actually believe there is infringement), they are just asking for the same treatment they offered here.
Ethereal is nice, because of its exhaustive list of supported protocols, but it still has many rough edges. Cutting and pasting various pieces of data is difficult, for example. It also is missing some advanced features, some of which are offered by this product:
It's amazing they don't sue Macrosoft. After all, it is just "Microsoft" with an "a" instead of an "i".
Yes, I recognize that the spelling is only different by one letter. But you clearly implied that "Lindows" was derived by replacing the "W" with an "L". I'm saying that's not the case--it was derived by recognizing the common letters "IN" and overlapping them to make a new word.
I'm sure you realized what I was expressing, but perhaps you really are a dolt. Originally, I had only used the term to chastise you for shortsightedness, but I guess it has more general application.
It's not "Windows" with an "L," you dolt! It's a combination of two similar words:
LINux +winDOWS --------
LINDOWS
There's no question it's partially a play of "Windows", but it's as much of a play off of "Linux". And no one is going to mistake the Lindows brand as representing Windows (nor do they want people to). They want people to see it as a LINux that's winDOWS like (user friendly, etc.).
Personally, I think Lindows is annoying, and I would never pay for it. But this isn't a ripoff of Windows's name, it's mix of two words (and the Windows name hardly deserves trademark status).
The Lindows name is similar enough to Windows, however, that the simple fact that it was partially derived from that word means a court could find for Microsoft.
I have not met one person in my life who has used both GIMP and PS for serious work that would actually argue that GIMP approaches PS in features, ease of use, or polish. I have used both extensively, and I can say quite authoritatively that GIMP simply doesn't cut it for many things I do graphically (and I'm not even a professional graphic artist, I just design web pages on occaison). All my professional friends who do graphics works agree with me on this point.
I use Firebird, Thunderbird, Apache, FreeBSD, Linux, and many other open source products *when they are right for the job* and because I believe they are actually better than their closed-source competitors. GIMP is a nice program, but it is emphatically *not* on par with PS.
Many people do find GIMP very useful. But it is not a Photoshop killer (for professional Photoshop users, that is). Photoshop has lots of features that the GIMP lacks.
I personally feel that ipfw/natd are a terrible combination, and are confusing and frustrating to use, to boot. I have been able to do everything I need to ipfw/natd, however. My major complaints were:
1. Cannot dynamically reload rules of ipfw (your connection can be broken after a flush, and before new rules).
2. Poor (really no) integration of natd/ipfw.
3. Weaker rules/macros than pf.
The FreeBSD pf port is coming along nicely. I am currently using it with a kernel loadable module and a startup script, both of which are installed by the port. You do still have to recompile the kernel:
You need these options:
"device bpf" and "options PFIL_HOOKS"
The port will tell you to do this when you install it. My transition was very easy, and immediately I was happier with pf. I had never used it before, and I prefer it immensely. I use it to do firewalling and NAT, and they are integrated, of course.
So, I'd say the status is...good! I'd prefer not to have to rebuild the kernel, but I'm used to that by now.
Slashdot Mirror
I thought one of the parents had pointed out that Nero allows you to burn the iso directly from DVD Shrink, rather than ripping, then burning. In any case, if you're happy with DVDD, you should keep using it. I'm just saying you shouldn't ignore a solution just because it isn't free. Nero has a lot of great features; I happen to like it. I don't do any DVD ripping, but Nero is a pretty complete suite for DVD/CD authoring, IMO. -Dan
The point is that consoles don't really sell for those low prices until they've been around a long time. The price of Doom3 will not be $55 in 4 years, either. If you are willing to wait 4 years to buy something, you can usually expect to get a great price on it.
I could similarly complain that Doom3 is way overpriced, because I just picked up Starcraft for $5, and Starcraft is one of the most popular games of all time! You pay a premium to get something when it comes out, and comparing it to a totally different product that's several years old doesn't indicate a whit about whether the price is reasonable.
-Dan
If you're willing to compromise and use a non-free OS just to copy DVDs, surely you can shell out $40-$60 for a great piece of software (Nero) that makes copying these DVDs a little easier.
You make it sound like you're taking a principled stand by avoiding non-free software, but you are obviously willing to compromise out of necessity. If you really want to support free software, maybe you should refuse to use these products because they don't have a version that runs on free OSes (not that I would recommend that).
I like free software because of the good results it gets, not simply because it is free. That's just me, though
-Dan
I can't wait to see what McGee does with this engine. Too bad he doesn't work for ID anymore.
-Dan
"Brand new console" is something of a misnomer here. Do you mean the 4-year-old console that was $300 when it came out (PS2) or the 3-year-old console that was also $300 (Xbox)?
Let's not forget that these consoles were sold *below* cost with the intention of making money on the games.
I'm not saying $55 isn't a lot for a video game, but comparing it to the price of 4-year-old consoles that were sold at a loss doesn't prove anything. What you should compare it to is console titles, because console titles are supposed to make up the loss on the consoles. OTOH, PC titles have no need to make up said loss, so why are they getting just as high as the console titles?
UT2004 was a nice exception, costing me only $25.
-Dan
Your frustration is understandable, of course. After you figure out what the problem is, you can remind the user to check the error message, not do what he/she was doing wrong, etc. But being mean about it isn't going to fix the problem, it's just going to make them not want to ask you when they have a problem. When that starts happening, people start to hate IT and start thinking about replacing them.
Even if the user is wrong every time, it's your responsibility to help them. Some people just never learn, but if you keep helping them in a friendly way, they will worship you and think you are indispensible. When you start to write them off and act like it's always their fault, they will be just as frustrated with you and want to get rid of you.
-Dan
-----------
USER: My e-mail doesn't work.
IT: What's wrong?
USER: I can't send e-mail. E-Mail doesn't work. The system must be down.
IT: I don't think the system is down. Let me see. Hmm, I can send mail. I wonder why you can't.
USER: It doesn't work for me.
IT: Did the computer give you any error message?
USER: I think so but I wasn't paying attention.
IT: Ok, let me come look at it. Maybe something is wrong with your account.
-----------
You're supposed to have an attitude of wanting to help, not proving it's not your fault. Jeez, no wonder people hate IT users, with responses like that.
-Dan
Unless you know the business internals and license agreements of those companies, you have no idea whether they respected the patents or not. However, all major graphics program vendors (Adobe, JASC, etc.) have LICENSED the gif compression algorithm, and used it in their programs. Those who paid to use those programs have the right to create gifs.
These commercial softwares did not disrespect "IP-rights," they meticulously followed the law by doing exactly what's required to use the patented algorithm. They showed respect for the patent by paying to use the algorithm. Free software respected the same rights by not using what they hadn't paid to use (because they either couldn't or weren't willing to).
-Dan
I wasn't talking about the GT, but it is a good point that the GT, which is smaller and quieter than the Ultra, and cheaper than both the Ultra and the X800, is also beating ATI here by a significant amount. Hopefully ATI can do something about this performance problem.
However, it is worth noting that in general, Nvidia's had to resort to a "multi-slot monster" to beat ATI. The GT is a good move, and has a great price/performance ratio, but it simply doesn't match up well to the X800 in D3D titles, for example.
I'm planning to upgrade my computer soon, and I still haven't decided what to get. But I'm fairly sure it won't be Nvidia's high-end one; I'm still considering ATI's and the GT.
-Dan
> As Carmack said, it's the pipecount:
It wasn't Carmack, but Bennet.
-Dan
Are you implying that Carmack made the above statement? Because...he didn't. That's Kyle Bennet, the author of the HardOCP article speaking. Carmack only made the brief statement at the beginning (it's color coded to help you spot it), which states that "all of the modern cards play the game very well," and "there is no egregious cheating going on," and most importantly, "Nvidia drivers have been tuned for Doom's primary light/surface interaction fragment program."
I don't think Doom3 will be significantly changed to help out ATI, but I'm positive ATI will change their drivers to help out Doom3's performance. As Carmack pointed out, the Nvidia drivers have already been fine tuned for Doom. My guess is that ATI, after the fiasco with releasing the Doom alpha, hasn't had as much opportunity to optimize for Doom.
On the other hand, it's no surprise to see ATI losing to a card that obviously has more horsepower. Frankly, I'm impressed that a card that's so much cooler, smaller, and quieter does so well against Nvidia's monster. But in this case, at least, we see Nvidia's power fully utilized. Hopefully, ATI gets so more performance out of theirs, though.
-Dan
MS has never minded OpenSource software via BSD license or what-not. Their real gripe is against GPL. OpenSource BSD-style license promotes standards and provides code for the world to use, regardless of their licensing model. GPL helps GPLed code, and no one else, unless you only want to use the programs, but not the code.
-Dan
Something that might interest users of FreeBSD who envy pf:
pf on FreeBSD
-Dan
I got the invite on hotmail. Don't know what the main post is talking about.
Thanks, Ben!
-Dan
This would be more like your apartment complex putting a "No Solicitors" sign on the gate outside. Oh, and this apartment complex is small and cramped, but it's free to live there.
-Dan
I would like to test this as well. lllammme@hotmail.com -Dan
What concerns me most is the amount of memory it requires. In theory, once the requisite stuff is loaded into memory, Java byte code can be processed at nearly the same rate that C++ code is. Depending on the bytecode and assembly that are generated in each case, Java or C++ could end up being faster. I think it's obvious that Java incurs some overhead in translating the bytecode, which ought to slow it down *some*, but that amount can be minimized.
On the other hand, Java takes a great deal of memory. If C++ had a dedicated server sitting in memory, ready to execute commands for it, it probably would speed up execution, but that wouldn't mean C++ were faster.
After accepting the memory hit for Java, the performance on things like apps servers seems to be pretty decent. I have yet to use a java client application, however, where I didn't feel that it was sluggish (even after loading). There are only two explanations: all java code is written poorly, or Java inherently causes a performance hit.
As we abstract languages more and more, we see performance hits for increased functionality and ease of developing. We also see that, because of the easier development, it is easier to improve scalability and use more efficient algorithms. It is rare that a program cannot be sped up by hand-optimizing the assembly, but it is also rare that anyone has time to design the much more critical optimized algorithms at such a low level. Therefore, I predict that eventually Java (or something like it) will be embraced as programmer time matters more than speed of execution.
The one thing that disturbs me about Java is that, while in C++, it is easy to change the assembly while maintaining the C/C++ code, in Java, you are tied to platform-independent code, which prevents you from doing platform specific optimizations. You have to depend on the native java implementations and/or widget toolkits for those kind of things. And so far, although the situation is improving, I've been pretty unhappy with the speed and my ability to improve it.
-Dan
This is true: "I got an email suggesting that I re-check NetBSD. The results are nothing short of astonishing. In two weeks time the NetBSD team made dramatic improvements." This is impressive and we should congratulate the NetBSD team for optimizing so quickly. However, let's not forget they did so in *reaction* to specific benchmarks, rather than having generally fast code which was proven by a few specific benchmarks, as FreeBSD 5.1 and Linux 2.6 did. Unless proven otherwise, I'd be forced to assume that generally, the code scalability in NetBSD is less than in FreeBSD 5.1/Linux 2.6, with these specific benchmarks being exceptions. Undoubtably, all of the OSes/distros could have been tweaked to improve these benchmarks, but NetBSD is the only one that was, or we were made aware of. Again, congratulations to them for showing they could fix the problems these benchmarks exposed, but it's not nearly as impressive as having good code the first time around. We know they can code to fix a flaw, but can they write code that scales well on arbitary code? -Dan
I didn't say it was because they respected copyrights, I said it was to *show* they respected copyrights. In any case, as I said, just because a company violates copyrights does not mean they don't respect them. It happens all the time, to many different companies. The test is how they respond when someone points out their violation. There is no way to guarantee _anything_ is original, except by having compared it to every possible source in the world. Obviously some employee at SCO chose to plagiarize, SCO was informed, and SCO paid up. I don't understand what the problem is. -Dan
Yes, SCO was caught violating copyright. Is there any company in the world that doesn't do this, on occasion, by accident, or because some employee pretends he wrote something he didn't? I doubt it.
The test of respecting the copyright, however, isn't *never* violating one, but fixing it when you realize you have. SCO did exactly what it should have, here, and both parties are perfectly satisfied with the result, I should think. SCO's quick action shows that they are eager to demonstrate how much they respect copyrights of others.
Does any of this mean SCO's suit is more or less merited? No, of course not. Does this infringement make them hypocrites? Not unless those filing the lawsuits sanctioned this infringment.
Now, the one point that someone made which has some validity is that SCO is hypcritical to suggest that Linux's review process is tainted, when they themselves are unable to review sufficiently to avoid infringement. SCO has no business complaining about the review process of any software if they cannot guarantee their products are 100% clean (and no one can, of course). SCO has made that argument to make Linux sound out of control and "scary," but it is not really a legal argument, just a tactic.
Like SCO's documentation, Linux is open for review at any time by anyone. Like SCO's documentation, if something infringing is in Linux, it is likely to be noticed by the copyright holder. SCO is saying that they have noticed such a thing, but unfortunately isn't able to point it out. That is what makes this documentation case so cut-and-dry, and the Linux one so out of control.
Personally, I think SCO should put up or shut up...but the fact that they were caught infringing, and made amends doesn't do anything to the validity of their suit. From their point of view (assuming they actually believe there is infringement), they are just asking for the same treatment they offered here.
-Dan
Ethereal is nice, because of its exhaustive list of supported protocols, but it still has many rough edges. Cutting and pasting various pieces of data is difficult, for example. It also is missing some advanced features, some of which are offered by this product:
Distinct Network Monitor
Download from here to avoid annoying forms.
It isn't free, or open source, but on the rare occasion where I want to modify and resend a captured packet, it's what I use.
-Dan
It's amazing they don't sue Macrosoft. After all, it is just "Microsoft" with an "a" instead of an "i". Yes, I recognize that the spelling is only different by one letter. But you clearly implied that "Lindows" was derived by replacing the "W" with an "L". I'm saying that's not the case--it was derived by recognizing the common letters "IN" and overlapping them to make a new word.
I'm sure you realized what I was expressing, but perhaps you really are a dolt. Originally, I had only used the term to chastise you for shortsightedness, but I guess it has more general application.
-Dan
It's not "Windows" with an "L," you dolt! It's a combination of two similar words:
LINux
+winDOWS
--------
LINDOWS
There's no question it's partially a play of "Windows", but it's as much of a play off of "Linux". And no one is going to mistake the Lindows brand as representing Windows (nor do they want people to). They want people to see it as a LINux that's winDOWS like (user friendly, etc.).
Personally, I think Lindows is annoying, and I would never pay for it. But this isn't a ripoff of Windows's name, it's mix of two words (and the Windows name hardly deserves trademark status).
The Lindows name is similar enough to Windows, however, that the simple fact that it was partially derived from that word means a court could find for Microsoft.
-Dan
I have not met one person in my life who has used both GIMP and PS for serious work that would actually argue that GIMP approaches PS in features, ease of use, or polish. I have used both extensively, and I can say quite authoritatively that GIMP simply doesn't cut it for many things I do graphically (and I'm not even a professional graphic artist, I just design web pages on occaison). All my professional friends who do graphics works agree with me on this point.
I use Firebird, Thunderbird, Apache, FreeBSD, Linux, and many other open source products *when they are right for the job* and because I believe they are actually better than their closed-source competitors. GIMP is a nice program, but it is emphatically *not* on par with PS.
See here:
http://www.gimp.org/~tml/gimp/win32/
Many people do find GIMP very useful. But it is not a Photoshop killer (for professional Photoshop users, that is). Photoshop has lots of features that the GIMP lacks.
Enough said.
-Dan
I personally feel that ipfw/natd are a terrible combination, and are confusing and frustrating to use, to boot. I have been able to do everything I need to ipfw/natd, however. My major complaints were:
1. Cannot dynamically reload rules of ipfw (your connection can be broken after a flush, and before new rules).
2. Poor (really no) integration of natd/ipfw.
3. Weaker rules/macros than pf.
The FreeBSD pf port is coming along nicely. I am currently using it with a kernel loadable module and a startup script, both of which are installed by the port. You do still have to recompile the kernel:
You need these options:
"device bpf" and "options PFIL_HOOKS"
The port will tell you to do this when you install it. My transition was very easy, and immediately I was happier with pf. I had never used it before, and I prefer it immensely. I use it to do firewalling and NAT, and they are integrated, of course.
So, I'd say the status is...good! I'd prefer not to have to rebuild the kernel, but I'm used to that by now.
-Dan