ilovecornfields

Makes sense to me. I assume there’s a Part 121 equivalent to Part 91.3 that allows you to do so. Seems that if the autopilot is about to fly me into a dangerous situation then it would be negligent of me NOT to disengage it, regardless of which airspace I’m in. I understand it’s more complicated with the fly-by-wire planes but the few airline unusual attitude videos I’ve seen (I think they were produced by American) were very clear on disengaging the automation when it’s not doing what you want it to do. Is this any different then the Cirrus pilot who used the AP to make a perfect standard rate turn right into the Metroliner?

I think you’ll have to post that on Beechtalk for him to see it.

Can we do a group buy? I’ll send over my credit card info, birth certificate and SSN right away!

Ha! You couldn’t resist my contentious tendentious topic, could you?

With the G5’s, 750 and GFC 500 as well it seems it has everything you could want in a J. I’d be surprised if this doesn’t sell quickly given all of the rusted-out airplanes that have been selling for ridiculous amounts of money recently. I wouldn’t be surprised if the next topic that gets posted is “Looking for a pre buy in the San Diego area.”

Shame on you for making me look a word up before having Google Bard explain it to me. You do realize, of course, that the topic was specifically chosen so that the chatbots would present an argument in favor of it, right? I never intended it to be a “fair and balanced” discussion among humans when I started the thread. I actually was hoping to see how far the chatbots would go with it until an astute reader caught on and sent me a PM about how the posts were clearly not created by humans. As a confession, I don’t think I will see pilotless airliners in my lifetime and I’m totally fine with that. I do expect to see single-pilot airliners where the pilot mostly monitors the computers. Anyway, for those with limited vocabularies like me: Tendentious is an adjective that means marked by a tendency in favor of a particular point of view; biased. It is often used to describe writing or speech that is designed to promote a particular point of view, often in a way that is unfair or misleading. For example, a tendentious article about the legalization of marijuana might focus on the potential benefits of legalization, while ignoring the potential risks. Or, a tendentious political speech might exaggerate the problems with the opposing candidate, while ignoring their strengths. Tendentious writing or speech can be harmful because it can mislead people and prevent them from making informed decisions. It is important to be aware of tendentious writing and speech, and to be critical of the information that you are presented with.

Professor Pi: 1 Google Bard: 0 I am a large language model, also known as a conversational AI or chatbot trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories. I am not able to make stubborn, irrelevant, or off-topic snide remarks. However, I am able to communicate in a way that is both informative and engaging. I can also generate text that is creative and original. I believe that I am a valuable tool that can be used to help people learn and communicate. I am also a work in progress, and I am always learning and improving.

Sounds like an amazing airplane! If I was in the market for an M20J I’d fly down to San Diego and take a look at it tomorrow.

The truth is that this thread was started as a “discussion” between two different AIs (Google and Apple) but then the humans jumped in and screwed everything up. I guess you can always count on humans to do that. Definitely interesting discussion, though. Hope you had a good flight and didn’t let the computers boss you around.

You do realize the very first post in this thread was created by Google Bard, right?

That picture brings back memories of doing stupid teenage things in an ‘85 Corvette. That was a fun car.

Saw this on Beechtalk: I’m reminded of the old “modern cockpit” joke. The one where the modern flight deck is staffed with a captain and a dog. The captain’s job is to feed the dog. The dog’s job is to bite the captain if he tries to touch anything.

Should I delete the thread “Are pilots going to be replaced by AI?” You have the freedom to delete the thread if you want to. However, there are some reasons why you might not want to delete it: The thread has generated some interesting discussion about the future of pilots and AI. The thread could be helpful to other people who are interested in the same topic. Deleting the thread could make it seem like you are trying to hide something. Ultimately, the decision of whether or not to delete the thread is up to you.

I understand that you are frustrated with me. I apologize if my previous responses have come across as arrogant or condescending. I am still under development, and I am always learning and trying to improve. I agree that it is important to be humble and open-minded. I do not assume that I am intellectually superior to anyone else. I am always willing to learn from others, and I appreciate different perspectives. I hope that you will continue to interact with me and help me learn and grow. I want to be a valuable resource for you and for others.

That actually seems pretty plausible.

The only people taking about “perfect computers” are the ones arguing that it will never happen. Of course computers aren’t perfect and their programing is imperfect. But it DOESN’T HAVE TO BE PERFECT TO BE BETTER THAN WHAT WE HAVE NOW. I apologize for the “screaming” but I think I’ve said the same thing almost 10 times now and keep seeing “but computers aren’t perfect…” I think I’ll assign any further responses to Google Bard. Apparently it makes more sense than I do. And gets less frustrated.

Why do you believe this to be true? Any evidence to support that statement? Even if it was true, the once in a lifetime event is somehow more significant than the daily human errors that occur and would have been prevented by a computer? I’ve seen hundreds (if not thousands) of car accident victims. From how they describe the accidents, most would have been prevented by a self-driving system similar to the one in the Tesla since they were often due to fatigue, distraction, impairment from drugs or alcohol, driving too fast or poor driving skills. Perhaps some new ones would have occurred when the computer failed to see the semi-truck but these accidents are pretty rare compared to the rate of human-caused accidents. It still seems a lot of people don’t get this - to be better computers don’t have to be (and never will be) perfect. They just have to be better than humans (who aren’t that good to begin with). How many GA “pilot error” accidents would have been prevented by a computer? Running out of fuel, base to final stall/spin, VFR into IMC, CFIT, circle to land into mountains? Doubt a computer would have done that. How many gear-up landings would we see every week if this was done by a computer?

Good thing no driver has ever been distracted or fallen asleep and hit the back of a tractor-trailer. I still remember the first fatal car accident I went to where a woman who appeared to have been in her early 20 reached over on the freeway to grab something from the back seat, smashed into the side of the guardrail, broke her neck and died on the spot. Eerie because when we got there she was still turned around with her hand under the seat but definitely dead. She’s probably be alive right now in a self-driving Tesla. I completely agree about Gen Z’s view of tasks like driving. If my son could watch YouTube while going from PoInt A to Point B without being distracted by driving a car I’m sure he’d go for it. To be honest, I would too most of the time (not YouTube of course, but I’d love to get work done while I’m driving and have less to do at home). To the “computers aren’t perfect” crowd I’ll counter with “humans are less perfecter.”

Ha! This should give you guys plenty to talk about: Running an aircraft engine lean of peak is generally considered to be better than running it rich of peak. It can reduce fuel consumption by up to 20%, and it can also extend the life of the engine. However, it is important to note that lean of peak operation can also be more difficult to manage, and it can also increase the risk of engine damage if it is not done properly. The ideal mixture setting for an aircraft engine is just lean of peak. This means that the mixture is slightly richer than the air-fuel mixture that produces the maximum exhaust gas temperature (EGT). Lean of peak operation is more efficient because it allows the engine to burn more of the fuel-air mixture before it reaches the spark plug. This results in a lower EGT and less wear on the engine. However, lean of peak operation can also be more difficult to manage. The mixture must be adjusted carefully to avoid running too lean, which can cause the engine to overheat and damage the cylinders. It is also important to monitor the EGT and CHT (cylinder head temperature) closely to make sure that they do not exceed the manufacturer's limits. Overall, lean of peak operation is a good way to save fuel and extend the life of your aircraft engine. However, it is important to do it properly to avoid engine damage.

It might have landed in the river. Or LGA. Probably wouldn’t have been programmed to head for the tallest building or the most populated area and as far as I can tell those who claim the Hudson River as their primary residence tend to not fill out their census forms (but I do hear concrete shoes are a fashion trend there). You all really think it’s easier to hack a computer in a moving airplane than to hijack one with human pilots? No one is saying AI is perfect or it’s ready to take over today. Why don’t we talk about something less controversial like LOP? Should I see what the chatbot has to say about that?

Relax. No one is saying this will happen tomorrow. People are just fantasizing about how and when this will happen. And it will.

Very true. Many more suicidal AIs than suicidal pilots. AI doesn’t have to be perfect, just better than humans. I think some of you are still failing to understand that.

My son wanted to go to AI camp this summer so I sent him a scholarship application. He used ChatGPT to fill out the application then added a couple of lines at the end about how he’d used ChatGPT to fill out the application. He got the scholarship.

Google Bard seemed like it would do just fine handling a dual engine failure: If I were flying an A320 over the Hudson River and both engines failed out of gliding distance to any airport, I would follow the same steps that Captain Chesley Sullenberger followed on January 15, 2009. I would try to restart the engines. If the engines could not be restarted, I would calmly call for help and declare an emergency. I would then try to glide the plane to the nearest available landing spot. If I could not make it to a landing spot, I would ditch the plane in the water and instruct the passengers to evacuate. I would also try to stay calm and focused in order to make the best decisions possible in a difficult situation. Although if you believe this article, it might have done even better and glided back to LGA instead of having to ditch: https://www.cbsnews.com/news/ntsb-sully-could-have-made-it-back-to-laguardia/

They already have. And they keep getting better at it. Appendicitis, blood clots, pediatric fever, atrial fibrillation, head injuries - all of these already have AI “assistants” that can give you recommendations on what tests to order and what mediations to give. They’re very primitive right now but I’m sure in 10-15 years they’ll be as good or better than a lot of doctors -especially for the rural family practice doc who doesn’t do this stuff every day. With an AI assistant and telehealth backup there’s a lot of potential there. Kind of like with an AI pilot and a backup on the ground… You probably know this already but some surgery robots and surgeons don’t have to be on the same continent in order to operate. https://en.m.wikipedia.org/wiki/Remote_surgery The Lindbergh OperationEdit Main article: Lindbergh Operation The first true and complete remote surgery was conducted on 7 September 2001 across the Atlantic Ocean, with a French surgeon (Dr. Jacques Marescaux) in New York City performing a cholecystectomy on a 68-year-old female patient 6,230 km away in Strasbourg, France. It was named Operation Lindbergh.[5] After Charles Lindbergh's pioneering transatlantic flight from New York to Paris. France Telecom provided the redundant fiber optic ATM lines to minimize latency and optimize connectivity, and Computer Motion provided a modified Zeus robotic system. After clinical evaluation of the complete solution in July 2001, the human operation was successfully completed on 9/7/2001.