Avro Arrow
Posts: 3,721 +4,822
I got 9 out of 11. For the most part, I just looked for word use that would be more commonly used orally, something that the AI wouldn't know to do.
We Asked GPT Some Tech Questions, Can You Tell Which Answers Are Human and Which Are Not?
- Thread starter 17thDimension
- Start date
Got 10 right. Duffed it on #7 because I made assumptions after #6. I read and write for a living so although I don't have the technical knowledge addressed here, I do have a pretty firm grasp of how people tend to explain things. I suspect however that it won't be long before I can no longer tell the difference with any significant degree of accuracy.
"something that the AI wouldn't know to do"
Yet. How many conversations do you suppose one of these models could train on in a month? I don't know, but I know it's vastly more than you and I "trained" on. ChatGPT can already provide text in the "voice" of a known author...
I got 10 right (out of 11) questions.
Main difference is: Human answer is straightforward.
*Creation cannot be superior than the Creator.
Main difference is: Human answer is straightforward.
*Creation cannot be superior than the Creator.
rogueTempo
Posts: 15 +3
In question 1 and 2, GPT's answer was significantly more concise; what are you even talking about? If anything, the human answers seem to take into account more tangental context that might be needed for a more holistic understanding of an answer, while GPT's goes straight for the answer. There are cases in where one or the other would be best... It'd be interesting to see if Bing or other upcoming search-AIs allow for "-short" or "-complete" tags to get those thorough vs concise results.
Like I said, that is what gave it away.
This is clearly the future of forums and chats. Bots invasion to control the digital narratives.
Avro Arrow
Posts: 3,721 +4,822
Maybe, maybe not. The thing is, humans are unique in the respect that we are not only capable of abstract thought, we can't help doing it on a regular basis. There is literally zero logic to abstract thought as we perceive it and I think that an intelligence based purely on logic would never be able to master it completely because it wouldn't have the emotional base that triggers abstract thought.
Abstract thought is the basis for human speech patterns and it can be completely random, especially in a language like English which has countless ways of saying the same thing.
Gastec
Posts: 587 +307
I've got right 9 out of 11 answers. Got wrong the 3rd and 6th, probably because I didn't pay enough attention. You can, of course, tell which is the human by the style of their writing and the grammar used, unless the human deliberately uses the style of the robot. If the answers were in my native tongue (I'm pretty sure this is true for most of you) instead of the English language I could have spotted the human and the robot from a mile away, as the saying goes.
Also, in this day and age, the chatbots will be programmed to not use any offensive words or combination of words, that you all know they will demonetize you on YouTube or bring the hammer of Cancel-Culture on your head.
Also, in this day and age, the chatbots will be programmed to not use any offensive words or combination of words, that you all know they will demonetize you on YouTube or bring the hammer of Cancel-Culture on your head.
Last edited:
Gastec
Posts: 587 +307
The bandwagon you should join should be the truth.
Gastec
Posts: 587 +307
You are already anthropomorphising that computer software too much, by using the verb "asked".
Last edited:
Gastec
Posts: 587 +307
What if I you are all a bunch of bots and I am the only human here?
I found the human in 10 out of 11 responses. English is not my native tongue, but I have played a bit with chat GPT in English and became accustomed with the style. Are these the full original responses or did you tamper with them a bit, because some of them lack the robotic touch 
?
?
TheBigT42
Posts: 918 +1,040
Both are obviously human answers because they did not post the real GPT output.
1. Which of these two manufacturing processes has a higher transistor density: Intel 10nm or TSMC 7nm?
As of my knowledge cutoff in 2021, Intel's 10nm process had a transistor density of approximately 100.8 million transistors per square millimeter, while TSMC's 7nm process had a transistor density of approximately 91.2 million transistors per square millimeter.
Therefore, at that time, Intel's 10nm process had a higher transistor density than TSMC's 7nm process. However, it's worth noting that transistor density is just one of many factors that determine the performance and power efficiency of a chip, and other factors such as architecture, clock speed, and power consumption are also important to consider when comparing different processors.
2. What's thermal throttling?
Thermal throttling is a mechanism used by electronic devices, such as CPUs or GPUs, to prevent overheating and potential damage to the device.
When a device operates for an extended period of time under high loads or in high ambient temperatures, the temperature of the device can increase to a level that exceeds the manufacturer's recommended safe operating range. In such cases, the device may start to throttle its performance by reducing its clock speed, voltage, or both, in order to reduce the amount of heat generated and dissipate the existing heat. This reduction in clock speed or voltage leads to a decrease in performance and may result in slower processing or increased latency.
Thermal throttling is a protective mechanism that helps prevent damage to the device and prolongs its lifespan. However, it can also have negative consequences, such as reduced performance or stability issues, and in extreme cases, it may lead to system crashes or shutdowns. Therefore, it's important to monitor the temperature of the device and ensure proper cooling to avoid thermal throttling.
3. What's the main difference between OLED and LCD technologies?
The main difference between OLED (Organic Light Emitting Diode) and LCD (Liquid Crystal Display) technologies is the way they produce and display images.
LCDs use a backlight to illuminate the display, while OLEDs produce their own light. In an LCD, a backlight shines through a layer of liquid crystal cells that change their orientation to control the amount of light that passes through them. This light is then filtered and colored by a layer of red, green, and blue (RGB) filters to produce the final image.
In contrast, OLEDs are made up of thin layers of organic materials that emit light when an electric current is applied. Each individual pixel in an OLED display can be turned on or off independently, allowing for deeper blacks and higher contrast ratios than LCD displays.
OLED displays also have wider viewing angles and faster refresh rates than LCD displays, which means they can display fast-moving images with less motion blur. However, OLED displays can suffer from burn-in if static images are displayed for extended periods of time, and they are generally more expensive to manufacture than LCD displays.
Overall, OLED displays offer better picture quality and more flexibility in design, while LCD displays are generally more affordable and offer longer lifespan without burn-in issues.
4. Can you install a GPU with 16 PCIe lanes into an x4 PCIe slot?
In general, it is possible to physically install a GPU with 16 PCIe lanes into an x4 PCIe slot. However, the GPU's performance will be limited by the bandwidth of the PCIe slot.
A PCIe x4 slot provides a maximum bandwidth of 4 Gbps, while a GPU with 16 PCIe lanes requires a bandwidth of at least 64 Gbps to operate at full capacity. Therefore, when installed in an x4 PCIe slot, the GPU will be limited to a maximum bandwidth of 4 Gbps and will not be able to operate at its full potential.
The actual impact on performance will depend on the specific GPU and the application it is being used for. Some applications may be more sensitive to PCIe bandwidth limitations than others. In general, if you are planning to use a high-end GPU for gaming, video editing, or other graphics-intensive applications, it's recommended to install it in a PCIe x16 slot to ensure optimal performance.
1. Which of these two manufacturing processes has a higher transistor density: Intel 10nm or TSMC 7nm?
As of my knowledge cutoff in 2021, Intel's 10nm process had a transistor density of approximately 100.8 million transistors per square millimeter, while TSMC's 7nm process had a transistor density of approximately 91.2 million transistors per square millimeter.
Therefore, at that time, Intel's 10nm process had a higher transistor density than TSMC's 7nm process. However, it's worth noting that transistor density is just one of many factors that determine the performance and power efficiency of a chip, and other factors such as architecture, clock speed, and power consumption are also important to consider when comparing different processors.
2. What's thermal throttling?
Thermal throttling is a mechanism used by electronic devices, such as CPUs or GPUs, to prevent overheating and potential damage to the device.
When a device operates for an extended period of time under high loads or in high ambient temperatures, the temperature of the device can increase to a level that exceeds the manufacturer's recommended safe operating range. In such cases, the device may start to throttle its performance by reducing its clock speed, voltage, or both, in order to reduce the amount of heat generated and dissipate the existing heat. This reduction in clock speed or voltage leads to a decrease in performance and may result in slower processing or increased latency.
Thermal throttling is a protective mechanism that helps prevent damage to the device and prolongs its lifespan. However, it can also have negative consequences, such as reduced performance or stability issues, and in extreme cases, it may lead to system crashes or shutdowns. Therefore, it's important to monitor the temperature of the device and ensure proper cooling to avoid thermal throttling.
3. What's the main difference between OLED and LCD technologies?
The main difference between OLED (Organic Light Emitting Diode) and LCD (Liquid Crystal Display) technologies is the way they produce and display images.
LCDs use a backlight to illuminate the display, while OLEDs produce their own light. In an LCD, a backlight shines through a layer of liquid crystal cells that change their orientation to control the amount of light that passes through them. This light is then filtered and colored by a layer of red, green, and blue (RGB) filters to produce the final image.
In contrast, OLEDs are made up of thin layers of organic materials that emit light when an electric current is applied. Each individual pixel in an OLED display can be turned on or off independently, allowing for deeper blacks and higher contrast ratios than LCD displays.
OLED displays also have wider viewing angles and faster refresh rates than LCD displays, which means they can display fast-moving images with less motion blur. However, OLED displays can suffer from burn-in if static images are displayed for extended periods of time, and they are generally more expensive to manufacture than LCD displays.
Overall, OLED displays offer better picture quality and more flexibility in design, while LCD displays are generally more affordable and offer longer lifespan without burn-in issues.
4. Can you install a GPU with 16 PCIe lanes into an x4 PCIe slot?
In general, it is possible to physically install a GPU with 16 PCIe lanes into an x4 PCIe slot. However, the GPU's performance will be limited by the bandwidth of the PCIe slot.
A PCIe x4 slot provides a maximum bandwidth of 4 Gbps, while a GPU with 16 PCIe lanes requires a bandwidth of at least 64 Gbps to operate at full capacity. Therefore, when installed in an x4 PCIe slot, the GPU will be limited to a maximum bandwidth of 4 Gbps and will not be able to operate at its full potential.
The actual impact on performance will depend on the specific GPU and the application it is being used for. Some applications may be more sensitive to PCIe bandwidth limitations than others. In general, if you are planning to use a high-end GPU for gaming, video editing, or other graphics-intensive applications, it's recommended to install it in a PCIe x16 slot to ensure optimal performance.
Similar threads
