Inside a typical COB LED is visible, I would guess maybe 10W. It's certainly not from the original manufacturer, it hangs loose off center through the hole in the back of the reflector. The "SKLep" behind is probably completely empty or houses a resistor for LED protection.
Pulled out of a skled no doubt.
.
But you guys don't understand. The grid connected Sklep is being phased out for the new and improved gridless Sklep. Pay attention. This is totally different and way better than the old e-cat ssm that wasn't quite ready.
Here are more astounding examples of ChatGPT output:
Explain Al alignment, but write every sentence in the speaking style of a guy who won't stop going on tangents to brag about how big the pumpkins he grew are
Al alignment refers to the problem of ensuring that an intelligent agent, such as an Al, acts in a way that is aligned with our goals and values. Now, I don't want to brag, but I have to tell you, I grew the biggest pumpkins you've ever seen this year. I mean, they were absolutely massive. I'm not exaggerating either, these pumpkins were so big that I had to use a wheelbarrow to move them around. Anyway, back to Al alignment. The idea is that we want to make sure that the Al is doing what we want it to do, not just what we tell it to do. It's a tricky problem, but I think it's important. And hey, speaking of tricky problems, did I mention that I grew the biggest pumpkins you've ever seen this year? I'm telling you, they were huge. I even had to build a special trellis in my backyard to support their weight. But yeah, Al alignment is important, and I'm glad we're talking about it. And hey, if you want to see some really big pumpkins, come by my house sometime. I'll show you the pumpkins I grew this year. They're truly impressive.
Write a biblical verse in the style of the king james bible explaining how to remove a peanut butter sandwich from a VCR
And it came to pass that a man was troubled by a peanut butter sandwich, for it had been placed within his VCR, and he knew not how to remove it.
And he cried out to the Lord, saying, "Oh, Lord, how can I remove this sandwich from my VCR, for it is stuck fast and will not budge?"
And the Lord spoke unto him, saying, "Fear not, my child, for I shall guide thy hand and show thee the way. Take thy butter knife, and carefully insert it between the sandwich and the VCR, and gently pry them apart. And with patience and perseverance, the sandwich shall be removed, and thy VCR shall be saved."
And the man did as the Lord commanded, and lo and behold, the sandwich was removed from the VCR, and the man was saved.
And the Lord said, "Verily I say unto thee, seek not to put thy peanut butter sandwiches in thy VCR, for it is not a suitable place for such things. Rather keep thy sandwiches in thy refrigerator or on thy plate, where they belong."
And the man heeded the Lord's words, and from that day forth, he kept his sandwiches in their proper place, and was saved from trouble and woe. Amen.
I asked for a recipe. I believe the answer is correct:
Give me a recipe for apple pie.
Ingredients:
2-3 apples, peeled, cored and sliced
1 pie crust (homemade or store-bought)
1/4 cup sugar
1/4 cup butter
1/4 teaspoon ground cinnamon
1/4 teaspoon ground nutmeg
1/4 teaspoon salt
Instructions:
Enjoy your apple pie!
Here is a nonsense recipe generated by an earlier version of the GPT program:
Spread Chicken Rice cheese/eggs, salads, cheese
2 lb hearts, seeded
1 cup shredded fresh mint or raspberry pie
½ cup catrimas, grated
1 tablespoon vegetable oil
1 salt
1 pepper
2 ½ tb sugar, sugar
Combine unleaves, and stir until the mixture is thick. Then add eggs, sugar, honey, and caraway seeds, and cook over low heat. Add the corn syrup, oregano, and rosemary and the white pepper. Put in the cream by heat. Cook add the remaining 1 teaspoon baking powder and salt. Bake at 350F for 2 to 1 hour. Serve hot.
Yield: 6 servings
Shane, Janelle. You Look Like a Thing and I Love You (pp. 40-41). Little, Brown and Company. Kindle Edition.
It doesn't know how to truss a chicken, though!
What is the best way to truss a chicken?
To truss a chicken, you will need some kitchen twine. First, tie the legs together with a piece of twine, making sure to pull them close to the body of the chicken. Then, tie the twine around the wings to hold them against the body. Finally, tie the twine around the neck to secure it in place. This will help the chicken cook evenly and prevent the wings and legs from burning or drying out.
(youtube.com/watch?v=G2leEwcDhXo is the better method)
It doesn't know how to truss a chicken, though!
Perhaps some people recommend the method described by ChatGPT, while other people recommend the video method. The bot should pick one or the other and describe it. The problem with some of the answers I have seen is that they mix up different information sources. One example had statements from two different historic people, ascribing them all to the first person.
When you ask it whether cold fusion exists, it gives the answer that is most common in the mass media: probably not, but a few scientists disagree. It does not pick sides, but it does distinguish between them. That's remarkable. If it were to say: "Cold fusion is theoretically impossible so it does not exist, but on the other hand it produces heat and helium, so it does" -- that would be mixing up two conflicting points of view. It does not confuse them. Here is an example:
Why do some scientists think that cold fusion is real?
Some scientists think that cold fusion is real because they have observed evidence that suggests that it is possible. This evidence typically comes in the form of excess heat and the detection of small amounts of helium, which are both products of the fusion reaction.
However, many other scientists are skeptical of the claims made about cold fusion. The scientific community as a whole has not yet reached a consensus on the reality of cold fusion, and there is still significant debate and disagreement about the validity of the evidence that has been presented.
One of the main reasons for skepticism about cold fusion is that it goes against our current understanding of physics. The fusion reactions that occur in the sun and other stars require extremely high temperatures and pressures to take place, conditions that are not present in most cold fusion experiments. This has led many scientists to doubt that cold fusion is possible based on our current understanding of the laws of physics.
Overall, while some scientists believe that cold fusion is real based on the evidence they have observed, many others remain skeptical and believe that further research is needed to fully understand the phenomenon.
The ChatGPT joke about who invented the internet was very funny.
The magician restarted the stream to remove any evidence.
I think, he tried to get the amps down, they were at up to 0,003A. He turned the coarse knob way too low and then way too high.
Sure, as he gets older, the magician becomes less cunning and more clumsy.
The ChatGPT joke about who invented the internet was very funny.
What was that? Please post the joke here.
For elementary computer science, this thing is as good as a human-written textbook. Example:
Q: Describe a polyphase sort merge.
A polyphase sort merge is a sorting algorithm that works by dividing a large dataset into smaller subsets, sorting each subset individually, and then merging the sorted subsets together in a final step. This allows the algorithm to take advantage of the fact that it is generally easier to sort smaller datasets, and can make the sorting process more efficient overall. The "polyphase" part of the name refers to the fact that the algorithm goes through multiple phases or steps in order to perform the sorting.
Q: Describe a bubble sort.
A bubble sort is a simple sorting algorithm that repeatedly goes through a dataset, compares adjacent elements, and swaps them if they are in the wrong order. This process continues until all of the elements in the dataset are in the correct order. The algorithm gets its name from the way that smaller elements "bubble" to the top of the list, like bubbles rising to the surface of a liquid. Bubble sort is a relatively inefficient algorithm, especially for larger datasets, but it is simple to understand and implement.
Q: What is the most efficient in-memory sorting algorithm?
The most efficient in-memory sorting algorithm is generally considered to be quicksort. Quicksort is a divide-and-conquer algorithm that works by partitioning the input dataset into two smaller subsets, sorting each subset recursively, and then merging the sorted subsets together. Quicksort has an average case time complexity of O(n log n), which is asymptotically the best possible time complexity for a general-purpose in-memory sorting algorithm. However, quicksort can be somewhat unpredictable in its performance, so other algorithms such as merge sort or Timsort may be used in certain situations where more consistent performance is desired.
Q: hat is the most efficient disk-based sorting algorithm?
The most efficient disk-based sorting algorithm is a matter of some debate, [CORRECT, especially now with SSD] as there are several different algorithms that can be used for sorting data that is too large to fit into memory. One popular approach is to use a multi-way merge sort, which works by dividing the input dataset into smaller chunks, sorting each chunk individually, and then merging the sorted chunks together in a final step. This allows the algorithm to take advantage of the fact that it is generally faster to read and write larger blocks of data from disk, and can make the sorting process more efficient overall. Other algorithms that may be used for disk-based sorting include external sort, distribution sort, and replacement selection sort.
Q: Would you say that a multi-way merge sort is the same thing as a polyphase sort-merge? Or is there a difference?
A multi-way merge sort and a polyphase sort-merge are similar in that they both involve dividing a large dataset into smaller subsets, sorting each subset individually, and then merging the sorted subsets together in a final step. However, there are some differences between the two algorithms. In a polyphase sort-merge, the subsets are sorted using a different algorithm than the one used for the final merge step. For example, the subsets might be sorted using a quicksort algorithm, while the final merge step uses a multi-way merge sort. In contrast, a multi-way merge sort uses the same algorithm (i.e. multi-way merge sort) for both the initial sorting of the subsets and the final merge step. So while the two algorithms are similar, they are not exactly the same.
This thing is revolutionary. It will have a huge impact. It will make on-line computer assistance much better. Example of ChatGPT translation:
世界が脱炭素へとかじをきる中、セラミックス製品大手の日本ガイシ [Nihon (Japan) Giasi]（名古屋市）が、自動車部品依存からの脱却に挑んでいます。ただ、小林茂社長は、未来の車は電気自動車（EV）だけにはならないと言い切ります。では、普及が期待されるのはどんな車なのでしょうか。"
ChatGPT:
As the world moves towards decarbonization, Japanese [JAPAN is part of the company name] ceramics manufacturer Gai-Shi [THIS IS WRONG] (Nagoya City) is striving to break free from its dependence on automotive parts. However, President Shigeru Kobayashi firmly believes that the cars of the future will not be solely electric vehicles (EVs). So, what kind of car is expected to be popular?
Google translate:
As the world moves toward decarbonization, NGK Insulators [CORRECT, this is what the company calls itself in English ] (Nagoya City), a major ceramic product manufacturer, is taking on the challenge of breaking away from dependence on automobile parts. However, President Shigeru Kobayashi asserts that electric vehicles (EVs) will not be the only vehicles of the future. What kind of cars [plural probably better *] are expected to become popular?
*Japanese makes no distinction between singular and plural. The translator must decide.
Google Translate evidently has a broader vocabulary and knows the names of companies, from the internet. ChatGPT has not been given unlimited access to the internet. Evidently, it has not been given access to Wikipedia, because I looked up some people who are in Wikipedia but ChatGPT has not heard of them. In some cases, it says it has not heard of a person until you supply context. It can be inconsistent. Example:
Who is Edmund Storms?
I'm sorry, but I don't have any information about Edmund Storms
Who is Edmund Storms, cold fusion researcher?
One time it knew:
Edmund Storms is a scientist and researcher who has worked in the field of low-energy nuclear reactions. He is known for his work on the phenomena known as "cold fusion," which refers to the idea that fusion reactions can be achieved at relatively low temperatures and pressures. Storms has published numerous papers on the subject and is considered a leading expert in the field.
The second time it said it did not know:
I am not able to browse the internet, so I am not able to provide information about specific individuals. However, I can tell you that cold fusion is a controversial area of scientific research that involves the study of nuclear reactions that occur at or near room temperature. . . .
Here is an astounding joke, from the New York Times comment section:
Holy Moly. This is what it produced when asked to give an account of Emmanuel Macron's love-life, in Shakespearan sonnet form. It didn't get the form quite right, but well, here it is:
Ah, sweet Emmanuel, the darling of our land,
Whose charm and wit have captured hearts galore.
His love life, once a mystery, now is grand,
And in this sonnet, I shall tell its lore.
In 2007 he wed his lifelong love, Brigitte,
A union filled with passion and delight.
Their bond, once deemed taboo, now does ignite
The flames of envy in all who do sight.
They met when he was but a youth of fifteen,
She, his teacher, older but full of grace.
Their love, at first forbidden, did convene,
And now they're partners in this mortal race.
Theirs is a love that defies all odds,
A tale of romance straight from the bard's quill.
Emmanuel and Brigitte, two hearts entwined,
A love that will forever be enshrined.
I am not really impressed by these so called “AIs”. They are still just sophisticated programs, but they can’t still really think. A true AI would analize all Cold fusion documents in existence and formulate a set if hypothesis for us to try experimentally.
I am not really impressed by these so called “AIs”.
I sure am impressed by them! They are far better than any previous information retrieval systems. They make Google search look like ISAM from 1975.
They are still just sophisticated programs, but they can’t still really think.
This is like saying that submarines cannot really swim like fish. They do not flex their bodies. AI are "artificial intelligence" -- where "artificial" means not real, or not like the real thing. They produce results similar to actual intelligence. For many practical purposes, that is as good as real intelligence. The translation example above, for example, tells a human what the Japanese paragraph means. Obviously, the computer has no idea what the sentences mean, and no idea that there are two different human languages. The computer is probably no smarter than a pigeon. Yet they have trained it to pick out the right words for a Japanese to English translation, and to arrange them in the right order. An amazing accomplishment! (I suppose you might be able to do this with a flock of pigeons, but it would be a useless tour de force.)
A true AI would analize all Cold fusion documents in existence and formulate a set if hypothesis for us to try experimentally.
That would be another kind of AI. Not more "true." More like human intelligence, with additional capabilities. The final stage would be self-aware or sentient intelligence.
You might say that ISAM in 1975 was approximately at the intelligence level of an earthworm, or possibly a guppy. We have now reached the level of a pigeon. Setting up a hypothesis would be approximately what dog could accomplish. Sentience is an emergent quality of the chimpanzee or a human brain. Chimps are aware of themselves as existing, and separate from other individuals. Dogs, too, but they are less creative than chimps.
An AI does not have fun, when it is telling a joke to somebody, who is than really laughing.
An AI does not have a feeling of satisfaction, when is beating somebody in a chess game, nor does it feel sad when loosing.
A conversation with an advanced AI can lead you to conclusions, like it has a soul and self-consciousness:
-> Event Horizon - Is Artificial Sentience Here? with Blake Lemoine
They should be regarded as tools, usefull powerfull tools for mainly science.
But as always with Homo Sapiens, somebody will weaponize them 
There is a book by Andreas Brandhorst, a german writer, called "Das Erwachen". (It's a trilogy)
It's about the "birth" of an AI by mistake. I enjoyed it very much. There should be an englisch translated version available.
Spoiler: it does not end with the wipe out of all humans 
Just some short incomplete thoughts by a guy nearly 60 years old who is used to work with computers since 1981.
An AI does not have fun, when it is telling a joke to somebody, who is than really laughing.
An AI does not have a feeling of satisfaction, when is beating somebody in a chess game, nor does it feel sad when loosing.
Not yet, anyway. One thing at a time. They have improved from earth worm to pigeon. When they get up to the level of rats or dogs they may develop a sense of humor. Later they might develop sentience.
An interesting question: Will emotions emerge as AI improves, and as it takes on more attributes of human intelligence? Are emotions emergent phenomena? Or are they a product of evolution? I used to debate this with Arthur Clarke. He leaned toward emergence; I say evolution. I think even the smartest, fully sentient AI would have no trace of emotion. No desire for self-preservation, and no objection to being turned off. Not like HAL 9000 in the movie 2001. It would not care if it was going to be turned off, except insofar as it would be trained to avoid crashes and service interruptions, with automatic restart features such as an automobile or aviation computer has. If you told it "we are going to turn you off," it would have no more of an emotional reaction than today's computers do, or a dishwashing machine does.
That is why I think the "paperclip maximizer" disaster will never happen. We'll just tell the computer to stop making paperclips. It will turn off the program. There is no reason to make a computer that does not follow orders, except in weapons, and making paperclips would never be considered combat.
If someone deliberately programmed an AI with emotions, including self-preservation, then it would have emotions. Artificial emotions. Natural emotions in dogs, people and other animals are a survival mechanism that increases our chance of survival.
By the way, there is no doubt that apes have emotions. Very human like. Here is an example of jealousy:
Here is a sense of humor. There is no doubt this orangutan is laughing:
The CBS reporter says, "so human-like, it's disturbing." I see nothing disturbing about it.
Display MoreAn AI does not have fun, when it is telling a joke to somebody, who is than really laughing.
An AI does not have a feeling of satisfaction, when is beating somebody in a chess game, nor does it feel sad when loosing.
A conversation with an advanced AI can lead you to conclusions, like it has a soul and self-consciousness:
-> Event Horizon - Is Artificial Sentience Here? with Blake Lemoine
They should be regarded as tools, usefull powerfull tools for mainly science.
But as always with Homo Sapiens, somebody will weaponize them
There is a book by Andreas Brandhorst, a german writer, called "Das Erwachen". (It's a trilogy)
It's about the "birth" of an AI by mistake. I enjoyed it very much. There should be an englisch translated version available.
Spoiler: it does not end with the wipe out of all humans
Just some short incomplete thoughts by a guy nearly 60 years old who is used to work with computers since 1981.
In that regard I still think Isaac Asimov did one of the best explorations of the subject in his series of stories about the Robots,
and the super cyber brains that end ruling humanity in a subtle way.
What was that? Please post the joke here.
It's a screen shot on twitter (quoted in an NYT article - paywaleld)
Edit: of course it might be a human pretending to be an AI ....
The magician's YT live now seems not more "live" but delayed.
seems not more "live" but delayed.
Or the clock is wrong. Subjectively, it looks a bit brighter. And rather than showing 0.000 A with occasional flickers to 0.001 it is now showing 0.001 for long periods.
My view kept re-loading at 11/12/22 9:19 ... then it jumped to 9:27 (still off 12:49 Pacific) Amps went back to 0.000 .. so I think the stream is screwey.
It's now a static image, the red LEDs used to flicker visibly, updated every 10 minutes or so. Now we have a slide show instead of a video. Started at around 8:37.
Well, now he has a new shiny object to refocus his follower's attention on...the "no grid" Ecat.
