Re: [PLUG] something I am considering doing...
Okay, I get it, that AI is as only good as the input and if it is fed garbage, it can only spout garbage (wish that there was someway to clue the investors into this fact) On 3/22/24 17:51, Russell Senior wrote: On 3/22/24 17:39, Ben Koenig wrote: On Friday, March 22nd, 2024 at 5:04 PM, American Citizen wrote: A few years ago, I took my Linux OS which is openSuse Leap v15.3 or so and ran a check on the documentation such as the man1 through man9 pages (run the %man man command to pull all this up) versus the actual executables on the system. I was surprised to find < 15% of the command executables were documented. Naturally I was hoping for something like 50% to 75%. If I am going to talk to an AI program, such as ChatBot or one of the newer popular AI program and ask it to generate the documentation for the complete OS, what AI chatbot would you choose? My idea is to clue the AI program into the actual OS, then ask it to finish documenting 100% of all the executables, or report to me all executables which have no available documentation at all, period. This means the AI program would scour the internet for any and all documentation for each command, and there are 10,000's of executables to examine. (which is why I believe this is an AI task) Your thoughts? - Randall That would be an interesting experiment to see what it comes up with. I would question the results simply due to the quality of current LLM implementations. From recent anecdotal experience, I recently bought an expensive Logitech keyboard and it was behaving strangely so I tried to look up how to perform a "factory reset" for this model. The search results I found via DDG were interesting, there were multiple duplicate hits for what appeared to be a tech blog with generic instruction pages for my device. However there were multiple iterations of this page, for this keyboard model, each of which had instructions referencing physical features that do not exist on this actual keyboard. These appeared to be AI generated help pages that were clogging up actual search results. They were very well written, If I hadn't had the actual device in front of my I might have actually believed that there was a pinhole reset button next to the USB port. If you do this, you may need to find a way to define a "web of trust" that allows the AI to differentiate between human written articles, and AI written summaries. As it is right now, you might find yourself telling an AI to summarize help pages that are AI written summaries of AI written summaries of ( AI written summaries of ( AI written summaries of ( AI written summaries of (actual manuals) ) ) ) Recursion FTW! :) It seems inevitable that the AI serpent will stupidly eat its tail and devolve into even more of a stochastic septic tank than it is now. If I was an investor, I would be shorting hard into the AI bubble. To me, the only open question is whether humans get stupider faster than the machines.
Re: [PLUG] something I am considering doing...
Ben: You have touched on something very important here. For example I bought a brand new Logitech headphone, but suddenly found that my openSuse linux system could not support the acoustic dB volume that I was accustomed to in the past. An arduous search showed that the OS was not in sync with the newer Logitech firmware code for that headset. I had to play around sometime before I found a setting which restored the original volume levels. Please understand that Logitech was a bit on the defensive when I originally contacted them explaining my difficulties. I am not sure that the average person would have been able to satisfactorily resolve this. The key idea here is "web of trust". Randall On 3/22/24 17:39, Ben Koenig wrote: On Friday, March 22nd, 2024 at 5:04 PM, American Citizen wrote: A few years ago, I took my Linux OS which is openSuse Leap v15.3 or so and ran a check on the documentation such as the man1 through man9 pages (run the %man man command to pull all this up) versus the actual executables on the system. I was surprised to find < 15% of the command executables were documented. Naturally I was hoping for something like 50% to 75%. If I am going to talk to an AI program, such as ChatBot or one of the newer popular AI program and ask it to generate the documentation for the complete OS, what AI chatbot would you choose? My idea is to clue the AI program into the actual OS, then ask it to finish documenting 100% of all the executables, or report to me all executables which have no available documentation at all, period. This means the AI program would scour the internet for any and all documentation for each command, and there are 10,000's of executables to examine. (which is why I believe this is an AI task) Your thoughts? - Randall That would be an interesting experiment to see what it comes up with. I would question the results simply due to the quality of current LLM implementations. From recent anecdotal experience, I recently bought an expensive Logitech keyboard and it was behaving strangely so I tried to look up how to perform a "factory reset" for this model. The search results I found via DDG were interesting, there were multiple duplicate hits for what appeared to be a tech blog with generic instruction pages for my device. However there were multiple iterations of this page, for this keyboard model, each of which had instructions referencing physical features that do not exist on this actual keyboard. These appeared to be AI generated help pages that were clogging up actual search results. They were very well written, If I hadn't had the actual device in front of my I might have actually believed that there was a pinhole reset button next to the USB port. If you do this, you may need to find a way to define a "web of trust" that allows the AI to differentiate between human written articles, and AI written summaries. As it is right now, you might find yourself telling an AI to summarize help pages that are AI written summaries of AI written summaries of ( AI written summaries of ( AI written summaries of ( AI written summaries of (actual manuals) ) ) ) Recursion FTW! :) -Ben
Re: [PLUG] something I am considering doing...
On 3/22/24 17:39, Ben Koenig wrote: On Friday, March 22nd, 2024 at 5:04 PM, American Citizen wrote: A few years ago, I took my Linux OS which is openSuse Leap v15.3 or so and ran a check on the documentation such as the man1 through man9 pages (run the %man man command to pull all this up) versus the actual executables on the system. I was surprised to find < 15% of the command executables were documented. Naturally I was hoping for something like 50% to 75%. If I am going to talk to an AI program, such as ChatBot or one of the newer popular AI program and ask it to generate the documentation for the complete OS, what AI chatbot would you choose? My idea is to clue the AI program into the actual OS, then ask it to finish documenting 100% of all the executables, or report to me all executables which have no available documentation at all, period. This means the AI program would scour the internet for any and all documentation for each command, and there are 10,000's of executables to examine. (which is why I believe this is an AI task) Your thoughts? - Randall That would be an interesting experiment to see what it comes up with. I would question the results simply due to the quality of current LLM implementations. From recent anecdotal experience, I recently bought an expensive Logitech keyboard and it was behaving strangely so I tried to look up how to perform a "factory reset" for this model. The search results I found via DDG were interesting, there were multiple duplicate hits for what appeared to be a tech blog with generic instruction pages for my device. However there were multiple iterations of this page, for this keyboard model, each of which had instructions referencing physical features that do not exist on this actual keyboard. These appeared to be AI generated help pages that were clogging up actual search results. They were very well written, If I hadn't had the actual device in front of my I might have actually believed that there was a pinhole reset button next to the USB port. If you do this, you may need to find a way to define a "web of trust" that allows the AI to differentiate between human written articles, and AI written summaries. As it is right now, you might find yourself telling an AI to summarize help pages that are AI written summaries of AI written summaries of ( AI written summaries of ( AI written summaries of ( AI written summaries of (actual manuals) ) ) ) Recursion FTW! :) It seems inevitable that the AI serpent will stupidly eat its tail and devolve into even more of a stochastic septic tank than it is now. If I was an investor, I would be shorting hard into the AI bubble. To me, the only open question is whether humans get stupider faster than the machines. -- Russell
Re: [PLUG] something I am considering doing...
On Friday, March 22nd, 2024 at 5:04 PM, American Citizen wrote: > A few years ago, I took my Linux OS which is openSuse Leap v15.3 or so > and ran a check on the documentation such as the man1 through man9 pages > (run the %man man command to pull all this up) versus the actual > executables on the system. > > I was surprised to find < 15% of the command executables were > documented. Naturally I was hoping for something like 50% to 75%. > > If I am going to talk to an AI program, such as ChatBot or one of the > newer popular AI program and ask it to generate the documentation for > the complete OS, what AI chatbot would you choose? > > My idea is to clue the AI program into the actual OS, then ask it to > finish documenting 100% of all the executables, or report to me all > executables which have no available documentation at all, period. > > This means the AI program would scour the internet for any and all > documentation for each command, and there are 10,000's of executables to > examine. (which is why I believe this is an AI task) > > Your thoughts? > > - Randall That would be an interesting experiment to see what it comes up with. I would question the results simply due to the quality of current LLM implementations. >From recent anecdotal experience, I recently bought an expensive Logitech >keyboard and it was behaving strangely so I tried to look up how to perform a >"factory reset" for this model. The search results I found via DDG were >interesting, there were multiple duplicate hits for what appeared to be a tech >blog with generic instruction pages for my device. However there were multiple >iterations of this page, for this keyboard model, each of which had >instructions referencing physical features that do not exist on this actual >keyboard. These appeared to be AI generated help pages that were clogging up >actual search results. They were very well written, If I hadn't had the actual >device in front of my I might have actually believed that there was a pinhole >reset button next to the USB port. If you do this, you may need to find a way to define a "web of trust" that allows the AI to differentiate between human written articles, and AI written summaries. As it is right now, you might find yourself telling an AI to summarize help pages that are AI written summaries of AI written summaries of ( AI written summaries of ( AI written summaries of ( AI written summaries of (actual manuals) ) ) ) Recursion FTW! :) -Ben
[PLUG] something I am considering doing...
A few years ago, I took my Linux OS which is openSuse Leap v15.3 or so and ran a check on the documentation such as the man1 through man9 pages (run the %man man command to pull all this up) versus the actual executables on the system. I was surprised to find < 15% of the command executables were documented. Naturally I was hoping for something like 50% to 75%. If I am going to talk to an AI program, such as ChatBot or one of the newer popular AI program and ask it to generate the documentation for the complete OS, what AI chatbot would you choose? My idea is to clue the AI program into the actual OS, then ask it to finish documenting 100% of all the executables, or report to me all executables which have no available documentation at all, period. This means the AI program would scour the internet for any and all documentation for each command, and there are 10,000's of executables to examine. (which is why I believe this is an AI task) Your thoughts? - Randall
Re: [PLUG] rsync: not all files copied
On Fri, 22 Mar 2024, Tomas Kuchta wrote: Errors with rsync usually mean that the file system changed - such as logs, proc, sys, var, etc. Tomas, I thought this might be the cause. While I did nothing in the partitions being sync'd the kernel or some other application might have made a change. Thanks, Rich
Re: [PLUG] rsync: not all files copied
On Thu, Mar 21, 2024, 13:20 MC_Sequoia wrote: > "I worry that the copy omitted content. Especially when the size reported > as copied doesn't match the size of something like "du -s"" > > rsync = remote synchronization of local & remote files. If there's no > delta, there's no need to sync the files. > . Errors with rsync usually mean that the file system changed - such as logs, proc, sys, var, etc. It you want to avoid them you could: a) do not copy/sync system files b) boot from USB/DVD the mout and copy/sync the disk. Tomas >