Possible AI answer bot?
@krisrodriguez - Can you fire off an email as this person is using AI answers - Stuey
Is this a worthwhile discussion?
@krisrodriguez - Can you fire off an email as this person is using AI answers - Stuey
My take is probably, but likely yes. Based on this answer being the same as so many, it looks and smells like AI: https://www.ifixit.com/Answers/View/8818...
4 Comments:
@nick, yea, this is definitely being generated by AI. But, would it still be helpful to OP if they followed the steps?
@krisrodriguez I need to review a sample of questions. I just checked two to get a quick answer.
by Nick
@krisrodriguez Example 1: https://www.ifixit.com/Answers/View/8859... - Is the fuel pump easily accessible, or does removal require you to remove the gas tank? Foreign cars usually have a door, but the OP did not check. I would consider this unusable, especially for someone with this major misstep. I know it's probably under a door and would be able to cope, but does the OP? NOT EVERYONE KNOWS THIS OR HOW TO CHECK QUICKLY. I think this one needs to go, with caution to the OP about tailoring the responses.
Example 2: https://www.ifixit.com/Answers/View/8854... - usable, but it's a straight copy which isn't tailored to the OP's question.
Example 3: https://www.ifixit.com/Answers/View/8860... - same as 2, usable but posted as-is.
by Nick
@nick, thanks for looking into this.
I'm a little torn. The answers do seem AI generated, but the answers also seem on topic. I would be more inclined to instantly ban them if they were copy-pasting the same thing across multiple questions. @danj j and @nick , in Stuey's answers, are they at all helpful in assisting OP solve their problem?
11 Comments:
Hi Kris, it’s more of spraying a lot of things than a focused answer. Can you just email him to refrain from deviating from the question and limit the AI involvement.
by Dan
I've already posted a comment to the user regarding using AI in an answer just to inform them about their responsibilities to ensure that their answers are relevant and accurate and not just what the OP of the question that they responded to in this way could find by searching online themselves.
This was a few days ago and there was no feedback from them, but I noted that their answers have improved slightly away from just what I believe to be AI copy and paste.
Time will tell.
Cheers
by jayeff
@jayeff There's coruses online for it that are literally low cost or free to actually make it useful. I'm not saying mandate an AI certificate or something like Google Cloud, but don't use the response as-is. People often prompt it with absolute (for lack of a better word) dogshit or use the original poorly written question from the OP and get bad responses, and you end up with garbage and then post it as if it's viable. No, read the post, tune the response.
AI is not mature enough. Yes, I can use AI well but it's a learning process and I can't exactly teach everyone who makes an account about how to not write hot garbage. Even if I wrote a guide to effective prompting, it would probably be ignored because GIGO is faster then effective prompting.
by Nick
To futher add to the discussion on why I cannot stand AI on a forum like this let me take this question as an example:
ORIGINAL POST: https://www.ifixit.com/Answers/View/8853....
== My printer doesn't turn on. ==
I've already replaced the power supply but the problem remains. Is there a possibility the main board is faulty or do I have to check something else?
This is the base response I get from ChatGPT:
It sounds like you've already ruled out the power supply, which is good progress. If the printer still isn't turning on, there are a few things you can check before jumping to the main board.
- Power Button and Switch: Sometimes, the issue could be something as simple as a faulty power button or a stuck switch. Try pressing the button multiple times, or check if it’s physically stuck.
- Fuse or Circuit Breaker: Many printers have an internal fuse or circuit breaker to protect against power surges. If the fuse is blown, the printer won’t turn on. Check your printer’s manual to locate it and see if it’s blown.
- Power Cable and Outlet: Double-check that the power cable is securely connected and that the outlet is working (you can test it by plugging in another device).
- Main Board Issues: If the printer still doesn't turn on after checking these things, there’s a strong chance the main board could be at fault, especially if there are no lights, sounds, or other signs of life when you press the power button. A blown component on the main board can prevent the printer from powering up.
Before going for a replacement, you might want to check for visible signs of damage on the board, like burnt components or any smell of something fried. If you have the tools and know-how, you can also try testing the power coming into the board to see if it's getting the correct voltage.
Would you feel comfortable opening up the printer further to inspect or test the board? Or are you leaning toward getting a professional to take a look?
Now let me show you what it says, both with effective prompting, AND crap prompting:
I got this response from someone:
I'm assuming you checked the connections and all of that, so the next thing I would do is check for a pinout on the power supply (the last Epson I had was an NX415, which I believe had it on the supply). Take note of that power supply pinout, and get a multimeter (even a basic Walamrt meter will work here). Look for something like this, a $20-30 meter will suffice. I use a Southwire, but I work on enough devices with higher voltages that I need a reputable meter like a Southwire, Klein Tools or Fluke. Plug it into the printer just in case there's a signal wire. I don't believe this is a thing with Epson power supplies, but if it is, you will need to plug it into the motherboard OR jump it. It's easier to do it connected to the motherboard. If there's no immediate ground, you can use your household ground in a pinch, but please try to find an LV ground on the board or something else to avoid as many issues as possible. It will probably work, but I don't like using a household ground when it's avoidable (and it usually is). If the voltages are exact (or marginally higher) then the supply is rated for, you have a motherboard issue or something else is off like the control panel. You might get lucky and find it's the control panel wire, but very often a bad board.
In this case, I am prompting it as if I do not know how to effectively prompt it, on purpose. This is purely to make a point.
Now, when I reload ChatGPT with the same base question to remove any history, this is the same response with the original prompt (the answers post):
It sounds like you’ve already done a good bit of troubleshooting with replacing the power supply. If the printer still isn’t turning on, there are a few possibilities to consider:
- Mainboard (PCB) Fault: Yes, the mainboard could definitely be the issue. If it’s not receiving power or if a circuit on it is damaged, that could prevent the printer from turning on. You can check for obvious signs of damage like burned components, damaged traces, or blown capacitors.
- Fuses: Sometimes printers have internal fuses that blow and prevent power from reaching the rest of the components. Check if your printer has any internal fuses and see if they’ve blown. These can sometimes be hard to spot, but a continuity test with a multimeter should help.
- Wiring/Connections: It’s also worth checking if there’s a loose connection somewhere—especially if the mainboard is still receiving power but there’s no response. Look for loose or corroded connectors, damaged cables, or signs of wear.
- Power Button/Switch: In some cases, the power switch itself could be faulty. If you’re comfortable with it, you could test the switch with a multimeter to see if it’s closing properly when pressed.
- Capacitors or Power Circuitry: Even though you’ve replaced the power supply, there could still be a problem with the capacitors or other power-related components on the mainboard that are preventing the printer from powering up.
If you're comfortable with taking things apart, starting with a visual inspection of the mainboard and testing the fuses could give you some insight. If all that checks out, then replacing the mainboard might be the only next step.
Do you know the model of the printer? I could help with more specific advice if you do.
See how the AI didn't know the printer model because the OP did not include it? OP has a L3150, but I excluded that to simulate crappy initial prompting.
When I prompt it with the bad foundation with the model (L3150):
My prompt: It is an L3150
Thanks for sharing the model! The Epson L3150 is a popular ink tank printer, and while it’s a relatively simple design, there are still a few areas where issues could arise that prevent it from powering on.
Given the troubleshooting you’ve already done, here’s a more specific list of things to check for:
1. Power Button Issue
Sometimes the power button itself might be the culprit. It could be physically stuck or the internal switch might be faulty. If you're comfortable with it, you can check if the button is making proper contact when pressed. It’s not common, but it’s worth verifying.
2. Mainboard Check (PCB)
The mainboard in this model could be at fault. The L3150’s board has a few key components, like a power controller IC and capacitors that manage power regulation. If any of these components fail, they can prevent the printer from turning on.
- Capacitors: Check for bulging or leaking capacitors on the mainboard.
- Burn marks or discoloration: Look for any obvious signs of overheating around power components.
3. Fuses
The L3150 has a few internal fuses that could blow and prevent power from reaching the mainboard. These can often be overlooked since they're tiny and may not look blown at first glance, but they can be tested with a multimeter to ensure continuity.
4. Power Supply Connection
Even though you replaced the external power supply, ensure that the connection between the power brick and the printer is secure. Sometimes, even a loose cable or slightly damaged port can cause issues, particularly if the connection isn’t tight enough.
5. Resetting the Printer
In some cases, printers like the L3150 might require a reset if there's an internal fault. If you’ve checked all the wiring and connections and the board looks fine, you can try unplugging the printer, waiting for about 10-15 minutes, and then plugging it back in. This can sometimes help the system recover from minor faults.
6. Error Codes or Lights
Check if there are any blinking lights on the printer when you try to power it on. Some printers have a self-diagnosis feature where certain light patterns indicate specific issues (e.g., a blinking power light could indicate a paper jam, ink tank issue, etc.). If you see any lights blinking, that might be helpful in diagnosing the issue.
7. Firmware Issues
Rare, but some printers might have issues with firmware corruption or software bugs that prevent boot-up. If the printer starts showing signs of life (like flashing lights or sounds), you might want to check if there’s a firmware update available on the Epson website. Sometimes, updating or reinstalling firmware can reset any weird behavior.
If none of these steps reveal the issue, and you're still seeing no signs of life, it's possible the mainboard might need to be replaced. The L3150 doesn't have as many replaceable parts as higher-end models, so the mainboard is usually the part that would need to be replaced in case of failure.
Have you noticed any other signs of malfunction before the printer stopped turning on, or did it happen suddenly? That might give us more context to narrow it down.
Now, when I prompt it with my initial answer (again, simulating bad use of AI like so many AI Answers post use):
That’s a good suggestion from the person who replied to you. It sounds like they’re recommending a more in-depth approach with the power supply and the board diagnostics. Here’s a breakdown of their advice and how you could apply it to the L3150:
=== 1. Check the Power Supply Pinout ===
If your Epson L3150 has a similar setup to the NX415 (as mentioned), you could be dealing with a power supply that has a pinout to send signals or voltage to the motherboard. This would mean the power supply might need a “signal” or “enable” pin connected to activate the printer. Some power supplies won’t output power unless this signal is present.
Here’s what you can do:
- Check the pinout of the power supply by looking up the documentation for your model, or by opening up the power supply and checking the markings (some units have a sticker or diagram on the back or side).
- Multimeter Test: Using your multimeter, measure the voltages coming from the power supply to verify that it’s outputting the proper voltages to the motherboard. The correct voltages will depend on the power supply’s specifications, but typically, for the L3150, you should see something like 24V DC output (for the mainboard) and possibly 5V DC (for control logic).
2. Jumping the Power Supply (Signal Wire)
If there is a signal wire that needs to be connected to the motherboard to tell the power supply to turn on, you may have to test this:
- Multimeter: Test for continuity between the power supply and the board. If there’s a signal line, you can jump it (make a temporary connection) to see if that triggers the power supply to output the necessary voltages.
- Grounding: As they suggested, you should avoid using the household ground if possible. Look for a low-voltage (LV) ground on the motherboard or use a known ground from the power supply itself (if marked). You could also check for a ground plane on the mainboard if it’s not labeled.
3. Measure the Power Supply Voltages
This is a crucial step. Even though you replaced the power supply, it's still important to confirm that it’s working as expected:
- Voltage Readings: Use the multimeter to measure the output voltages at the connection points. If you’re getting the correct voltages (usually around 24V DC), the power supply is likely working fine.
- If the voltages are either too low or absent, then you’ll need to replace or repair the power supply.
4. Check the Control Panel Connection
As they mentioned, if the control panel or its connection is faulty, it could prevent the printer from powering on. Here’s how you can check:
- Inspect the cable from the control panel to the motherboard for any loose or damaged wires.
- Use the multimeter to test the continuity of this cable and ensure that there’s no broken wire or poor connection.
5. Motherboard Issues
If all the power supply voltages are correct, but the printer still doesn’t turn on, it’s most likely an issue with the motherboard. If you’ve tested the power and the control panel wiring and it all looks fine, the next step would be replacing the mainboard or performing more detailed diagnostics (e.g., checking the onboard components for damage).
Equipment Recommendations
If you don’t have a multimeter yet, I’d recommend getting something around the $20-30 range like a Southwire or Klein Tools meter, as they’re known for being reliable, and should give you accurate voltage readings.
If you’re following these steps, take your time and double-check the pinout and voltages. This method should give you a better idea of whether the problem lies with the power supply, control panel, or the motherboard itself. It sounds like you're close to finding the root cause! How are you feeling about diving into the troubleshooting with the multimeter?
This is BEFORE I prompt it more effectively.
When I prompt it with an effective iterative prompt:
My prompt:
Can you explain their logic and why they recommended checking the power supply, motherboard and front panel connector? I am not sure what is going on with their answer, and need a simplified version.
Once I put the iterative prompt into ChatGPT this is what I got:
Of course! Let’s break down the logic in simpler terms.
1. Why check the power supply?
The power supply is the first thing that provides electricity to the printer. It powers up everything, including the motherboard and other components. If the printer isn't turning on, the first step is to check if the power supply is delivering the right voltage.
- If the power supply isn't working properly, then nothing downstream (like the motherboard or control panel) will work either. So, it’s important to first confirm whether the power supply is giving the correct voltages (like 24V DC or 5V DC, depending on the printer).
2. Why check the motherboard?
The motherboard is the "brain" of the printer. If the power supply is working fine but the printer still won’t turn on, the motherboard could be the problem.
- The motherboard needs a signal to turn on, which could be sent by the power supply itself or from another source, like the control panel. So, if the power supply is okay but there’s still no power, it’s possible the motherboard is not receiving the "on" signal it needs, or it’s damaged.
3. Why check the front panel connector (control panel)?
The control panel (the buttons and display on the front) is what you use to turn the printer on. Sometimes, the wiring between the control panel and the motherboard can fail, preventing the power button from working properly.
- If the control panel isn’t sending the correct signal to the motherboard, it could prevent the printer from powering up. This could be due to a loose wire or broken connector.
Simplified Logic Flow:
- Power Supply:
- If the power supply isn't giving the correct voltage (like 24V DC), the printer won't turn on at all. So, this is the first thing to check.
- Motherboard:
- If the power supply works fine but the printer still doesn't turn on, the motherboard could be the issue. Maybe it’s not getting the power it needs or something is wrong with the circuits that control the printer’s power-up sequence.
- Control Panel:
- If the power supply and motherboard are fine, but the printer still doesn't turn on, the control panel or the wiring between it and the motherboard might be faulty. A loose or broken connection here could stop the printer from powering on.
Why this is important:
When diagnosing electrical issues, it’s important to follow the signal flow:
- Power comes from the power supply → it goes to the motherboard → the control panel sends a signal to the motherboard to turn the printer on. If any of these parts aren’t working or are miscommunicating, the printer won’t power on.
In this case, the person is suggesting to start at the power supply (because that’s where the power begins), then check the motherboard (because that's where the signals go to control everything), and finally check the control panel (because it’s the user interface that tells the printer to start).
Does this breakdown help clear things up? Essentially, they’re troubleshooting in the order that power flows through the printer, which is a logical approach to finding the issue!
The issue isn't using AI - it is an issue of poor prompting when it gets used, as people think it can be done with one or two crap prompts, and expecting a decent response. It took MULTIPLE TRIES to get a viable starting point, and you had to iterate on a poor intial starting point effectively!!!
As you see here, it can be an excellent way to get some points quickly, but it cannot be used as-is on your first go - it requires iteration and human verification to make sure the information is correct. The only reason I got an effective answer is that I could feed it a bad post, a good answer, and properly iterated the prompts. At this point we've beaten the horse to death on how AI is nearly useless with bad use, but I am using this to prominently highlight why I want to see a standard such as human corrections being a must if you want to keep your AI posts up. If the discussion is left at "check your work" maybe someone on the iFixit side can make a guide on how to effectively prompt AI to make these answers bearable, as a last ditch effort. Take note it even missed my point about the $20 meter being sufficient for LV work and assumed my Southwire was $20 - it was closer to $40-50, so double the price. I left that in on purpose to show the hallucination problem.
***This is the current version of what I have: https://www.lowes.com/pd/Klein-Tools-Dig...
@krisrodriguez - Not to add salt to the wound here’s another run of quick AI answers within this users answers Jakub Topolski
3 Comments:
Haha. @danj, thanks for being so considerate. But, these are good catches. I've gone ahead and done the same for this account: temporary ban and will reach out with an email explaining why. Part of me wants to hope that they are just trying to help, but the truth is that these incorrect answers can make an already bad repair problem, much worse.
@krisrodriguez - Mod’s can only go so far with cases like these. It’s your @ifixit that makes the difference. I’ve already removed a few way off answers. But until the person gets a notice we are just chasing the problem not dealing with it.
As always Thanks!
by Dan
@dan, I agree. I think this will be the way to go when we come across a user who is just copy/pasting AI answers.
Hey @krisrodriguez I suppose I found another one: https://de.ifixit.com/Antworten/Ansehen/...
Answers are not wrong but too general and less detailled for this topic.
@krisrodriguez Not necessarily bad answers, but certainly AI: 4658802
1 Comment:
Yep, title and ending gives it away. *facedesk* - edit your AI responses, people.
by Nick
@krisrodriguez we have had a discussion about the use of AI (KI for our European colleagues :-). It is my understanding that it is up to us to moderate this. We should remember that we all decided on an iFixit Community AI Policy "Caution is essential when using AI for repairs. AI lacks hands-on experience, real-time assessment, and may provide inaccurate advice, risking worsening issues. Its static knowledge may not address evolving technologies or unique circumstances, potentially leading to unsafe situations. Balancing AI with human expertise is crucial for accurate and safe repairs" and "If a community member uses AI to write content for iFixit, they must check for accuracy and safety 100% of the time."
To me, this means that it is not a @krisrodriguez issue but a moderation issue. We should adopt approaches just like @dadibrokeit did on here I have always advocated that the OP of the AI/KI answer must be transparent and openly make a statement declaring any AI/KI answer as such.
Let's moderate according to established guideline. To me this means Klappe zu, Affe tot ;-) when it comes to AI/KI.
11 Comments:
The issue is a combination of education (poor use) and nondisclosure for me :/. It's tolerable with a good base question, but it's still a crapshoot. I've tested it with a properly abysmal sample question I rigged up in 5 minutes (yes, it was unusable), then revised the question with a fresh ChatGPT session. Thw refined one came out better, but it still left way, way more then I'd like to see.
I didn't put an AI disclosure on this tester, but I did note it was for a sample. I didn't want to give too much away why... See here: https://www.ifixit.com/Answers/View/8870...
There's no way to remove the AI markers, no matter how much I can think of to clean it up. I would probably call that a good thing, as the amount of editing I'd need to do to remove it would make it such you're better off skipping it.
by Nick
@oldturkey03 - if it was just one or two posts then I have no problem just dealing with them. The issue I pressed was when someone does a good dozen or more which spans many products. Having Kris pen a warning note to the poster helps keeps the mess to a more tolerable level.
by Dan
@danj this assume that this person even uses their email account. If we comment on this, the OP of the AI/KI answer at least sees that we are serious about this. You as a mod have always the opportunity to delete the account, which gives the Admins a chance to review. If nothing else, you can start to downvote with the rest of the mods following. That will alert those that read the answer that there is something fishy going on. If we want to continue to run answers the way we think it would be best, then we need to take the initiative. I have a feeling the Admins are busy with something else. You've all noticed how quiet things have gotten......
by oldturkey03
@oldturkey03 A lot of these AI Answers people pump them out without regard for quality. I doubt they give a %#*@ about trying. I hate to say this, but we need a way to tag it as an AI answer the person who posted the AI answer cannot remove. The ONLY WAY to remove it aught to be admin stepping in or deleting the answer and posting an original.
Do you think I wanted to use the nuclear solution? No, I wanted to give them time to prove us wrong but it keeps happening.
by Nick
Thanks for the reminder Mike, after thinking twice it might really be the better way to moderate the "answers"and show the writer (and the public) that we are serious about AI. I will try to use that approach.
by BenZ78
Perhaps we should consistently mark all the answers that catch our eye in the first line like this:
"Warning: This answer is generated by AI. Use it with caution."
1 Comment:
This might be a good way to get ahead of these. Let me talk with the team internally to see what they think. I'll follow-up soon.