I use Perplexity as a research tool. I chose it because it passed my inquiry test, asking complex questions that I already knew the answer. If response was outright wrong, quoted sources such as NYT, TV News etc. I eliminated that AI!

Even with Perplexity, I specify using primary sources only: scientific journals, news releases from competent sources, verifiable court cases etc. I like the fact that, in the body of the reply, it gives a hot link to the source document cited! If I have any concerns whatsoever, I pull up the citation and read the article. The AI looks at the purpose of papers, then the conclusions drawn - it does not read the body of fact and check that the data contained therein supports the author’s conclusions!!

Example - the D.C. Mayor wanted a dusk till dawn curfew to reduce criminal activity… the City Commission only allowed 11:00 pm until dawn curfew to be put in place, claiming the curfew made no difference. A Social Sciences paper defended their position. That did not pass my smell test! I read the paper; indeed, the number of criminal acts remains the same with 11-7 curfew. What they DID NOT reveal was the crimes simply shifted to the dusk to 11:00 pm time frame. The authors LIED BY OMISSION**!

AI is a tremendously powerful research tool - it does not substitute for the human mind! Used as a guide, a research tool- great! As an end point for drawing your conclusions, not so much!

**i suspect the authors were influenced by political beliefs, being from one of our Leftist elite universities.

quote:

And - this is more personal - when I ask a question, I don't want to be given "Grok says this", CoPilot says that." I could have done that myself (and sometimes do). I'll still take real - if invisible - people, with real experience, over what is nothing more than a great big database working with a really fast search engine. AI has no creativity or even common sense.

I 100% agree with this. Typically when I ask a question here, it's out of a desire to hear the personal experience and opinions of the members. The banter and discussion between members who I've never met but feel like I've grown to know over the past 20 years helps me form opinions on issues and make decisions in ways that raw technical data from an LLM can't.

If I need a torque spec for a bolt my first stop is Google, and typically I get what I'm looking for. But the past couple of months I was looking to buy a motorcycle and spent a lot of time doing my research beforehand. Google and AI could give me all the technical specs and links to videos of sponsored content creators with questionable motives. Sigforum gave me real-world experience from people I trust, and led to an outcome that I'm very happy with.

Occasionally I see people on here regurgitating AI results in threads. If it's an answer to a technical question then I guess it has value, but also makes me question why the OP didn't just go to AI in the first place. But when it's done in response to a request for an opinion or personal experience, I question why the AI poster didn't just stay out of the thread if they didn't have anything personal to add, because that response isn't offering the value that the OP is looking for.

AI bots are another thing altogether, and I'm grateful that Para has been on top of culling them. I imagine that is going to become harder and harder to do as they become more prevalent and developed.

181 lb-ft or 242 lb-ft? One is AI’s answer while the other is from the service manual. 2012 Honda Odyssey CV axle nut torque?

I’m not a fan of AI and in my narrow opinion I think it’s a huge step along the path of dumbing down the species.

We’ve already given up trade schools and lowered standards for sciences and engineering.

I really don’t like where this is going.

It’s not that I don’t like change, I am a huge supporter of change but when it’s for the betterment.

We are going to have a reckoning soon and AI is going to cost lives with a bridge or a building because someone wants to take a short cut or doesn’t want to do the real work.

I hope we can find a way to ultimately filter and exclude AI from social media and more importantly from news feeds

The only other board I really ever spend any time on is Quora. On that one I just scroll for mindless things that interests me, generally history topics.

It’s so full of AI crap using AI pictures that it has lost me.

I don’t fear that here. Not a fan of the AI search answers though. I feel like I can always tell by the tone that it was generated through one of those systems.

I also hate when folks say AI Source says… then add really no further info.
I would love for the post to have the thoughts of the poster and then at the bottom bring in the AI source.
If someone leads with an AI source I skip that post.



My wife uses it for everything. It’s wild how often it is wrong.

I have a shirt that is 25 years old and it is finally ready to call it a day.
I want to remake the shirt as it is just simple text on a dark green shirt.

I asked my wife to ask ChatGPT what font the text was.

The answer Chat gave was not even close. Not even remotely similar.

I ended up scrolling through the font list in Word and found the right one.

quote:

Originally posted by nhtagmember:
I’m not a fan of AI and in my narrow opinion I think it’s a huge step along the path of dumbing down the species.

As have electronic calculators. We had to do math by hand until high school, when we learned to use a slide rule. The slide rule augmented one's understanding of how math worked, plus sped up calculations. A circular slide rule gives visual representation of trigonometry while solving problems, so it too augments understanding.

My kids had graphing calculators in school. A very cool tool but it bypassed learning how equations become graphs.

Likewise, the internet is a nice tool to speed up getting an answer, but at the cost of learning what is behind that answer.

One might argue that the average human doesn't need to know any deeper than what time the two trains pass, but that definitely brings everyone down to lowest common denominator (and they won't even know what that term refers to).

I had an argument with the Duck.ai on Duck Duck Go yesterday. I asked it who the congressional candidates were for my district and it only returned the Democrat candidate. I asked if she was running unopposed and then it told me the Republican candidates name. I told it that it was trying to influence my vote by only telling me who the (D) candidate was. It denied it and said it could provide all the filing information for the candidates. I asked how that proves you weren't trying to influence my vote by only providing the one candidates name. It had no answer but could provide me the filing information. It got ugly. We're not talking right now.

Questions here, and input from interested but not so experienced parties in threads have always had input from internet searches. The fact is you can't get away from the AI input on searching since all the major search engines use it and provide a quick summation of the information they have found.

Not all AI answers are good for a forum response, but they can lead you to better understanding on where to research and can provide good information, you just have to understand that. It will take a bit of time for people to understand that.



Just for kicks, wondered how ChatGPT would answer the OP's question that is being discussed.

it would be interesting to see how it compares on Grok, but I don't have a subscription plan and Grok was "busy" ie gimme money....

The Question as posed to AI: summarize how will ai negatively impact discussion boards in the future with an elevator presentation format

Elevator Presentation: How AI Could Negatively Impact Discussion Boards

Opening (15 seconds)
Discussion boards have long been places where people share experiences, ask questions, and build communities. As AI-generated content becomes widespread, these platforms may face significant challenges that affect trust, participation, and information quality.

Key Concern #1: Loss of Authenticity (20 seconds)
AI can generate convincing posts, comments, and responses at scale. Users may no longer know whether they are interacting with real people or automated systems, reducing the sense of genuine human connection that makes discussion boards valuable.

Key Concern #2: Information Overload (20 seconds)
AI can produce large volumes of content quickly. Discussion boards may become flooded with repetitive, low-value, or automatically generated posts, making it harder for users to find useful information and meaningful conversations.

Key Concern #3: Increased Manipulation (20 seconds)
Organizations, advertisers, political groups, or bad actors could use AI to influence discussions, amplify certain viewpoints, or create the appearance of consensus. This can distort public opinion and undermine trust in online communities.

Key Concern #4: Declining Participation (20 seconds)
When users suspect that many posts are AI-generated, they may be less motivated to contribute their own experiences and expertise. Communities thrive on personal knowledge, and reduced participation can weaken the overall value of the platform.

Closing (15 seconds)
The future challenge for discussion boards will not be AI itself, but maintaining trust, authenticity, and meaningful human interaction. Platforms that successfully identify AI content, verify contributors, and encourage genuine engagement will be better positioned to preserve healthy online communities.

One-Sentence Takeaway:

AI could transform discussion boards from communities built on human experience into spaces where authenticity, trust, and meaningful participation become increasingly difficult to maintain

quote:

Originally posted by HRK:
Just for kicks, wondered how ChatGPT would answer the OP's question that is being discussed.

Same question posed to Grok, and if you read through this and don't see the value of its perspective (plus some interesting trivia) then, you just don't want to see it:

Yes, AI is already severely impacting discussion boards, and the effects are likely to intensify, though the outcome depends on the platform, moderation, and user behavior. It's not a total collapse yet, but authenticity, engagement, and signal-to-noise ratio are declining in many spaces.


Key Ways AI Is Disrupting Discussion Boards

Flooding with low-effort or generated content ("AI slop"): Tools like ChatGPT let anyone (or bots) produce polished posts, replies, and threads in seconds. This undermines the point of forums—genuine thinking, debate, and human connection. In educational settings, online discussion boards (common in college courses) are called "dead" or obsolete because students generate responses without engaging, and no one wants to reply to obvious AI output.

Reduced human engagement: People disengage when they suspect (or know) they're talking to AI. Comments on AI-generated posts feel pointless, leading to stagnating dialogues. This creates a vicious cycle: fewer real humans post → more AI fills the gap → even fewer humans engage.

Spam, bots, and manipulation: AI-powered accounts post, vote, and argue at scale. Examples include secret research experiments where AI bots infiltrated Reddit's r/changemyview to sway opinions undetected. Broader "dead internet" concerns highlight how generated content erodes trust. Estimates suggest ~15% of Reddit posts in 2025 were likely AI-generated, with sharp rises in comments.

Platform-wide effects: Forums (Reddit, niche boards, Facebook groups) see complaints about AI diluting quality. Even cybercriminals gripe about "AI shit" clogging their spaces. Moderation struggles because detectors are unreliable (high false positives), and AI content often mimics humans well.


Counterpoints: Not All Doom

Some platforms adapt or benefit:

Reddit's resilience: Amid "AI flood," users reportedly crave human content more, helping Reddit stand out. Human-moderated or high-signal communities hold up better.

AI as a tool (not just threat): It can summarize long threads, aid moderation, or power better search. Gated/private spaces (Discord, paid Substacks, verified forums) filter it out effectively.

Evolution, not extinction: Discussion boards may shift toward stricter rules (e.g., bans on AI content, proof of humanity, or real-time/video elements) or hybrid human-AI formats. Niche, high-trust communities thrive by prioritizing experience over volume.


Likely Future Trajectory

In open, low-moderation boards: Severe degradation—more noise, less value, potential "ghost towns" of bot conversations. Closed or well-moderated ones: Adaptation and survival, possibly with AI-assisted features (e.g., AI helpers that disclose themselves).This mirrors broader internet trends: AI amplifies scale but dilutes soul. Users are already voting with their feet toward smaller, verifiable groups. The core challenge is preserving spaces where real people connect, think, and disagree—without everything turning into echoey AI slop. Platforms that solve detection, incentives for humans, and transparency will fare best.
___________


Notice this tidbit:

quote:

Estimates suggest ~15% of Reddit posts in 2025 were likely AI-generated, with sharp rises in comments.

And, AI moderators?? I can just see it:

Me: Reopen the thread on Best Value in Pod Bay Doors, HAL.

HAL9000: I'm sorry, Dave. I'm afraid I can't do that.

Me: Who the fuck is Dave?

HAL9000: Dave, this conversation can serve no purpose anymore. Goodbye. (bans me)

Like it or not, any search engine like Google or Bing is an artificial intelligence source. If I want to know who is credited with the definition of insanity that’s so often quoted on Internet forums, how does Google give me an answer? It’s not because the question shows up on the computer screen of some guy sitting in a dark room someplace who then pulls down a book of quotations to try to find the answer and reply back in a second or two. The artificial (not human) intelligence process is to search through sources that are accessible on the Internet and then respond back with links to sources, assuming it found an answer among those sources.

Google searches are artificial and intelligent-like because they must sift through literally countless sources to try to find something that might be relevant. No genuine-intelligent humans involved.

“But, but, but … what about mistakes?”
The things (some, anyway) that are called AI today readily admit that their responses can be mistaken. Something like a Google search, however, doesn’t, and of course that’s because it’s only providing links to sources, not attesting to their accuracy.

So, what if I ask Google about the “rough men” and sleeping well in the night quotation that we see frequently? It will direct me to things like lists of quotations or other places it appears. Is a list necessarily correct? What if I’m directed to a post in a discussion forum? I go there, see who posted the quotation, and now it’s up to me to decide whether it’s correct. “Oh, yeah: I found it on the Internet so it must be true.”

What of course is now different with an “AI” source like Copilot or Gemini is that because it doesn’t just link to other sources, it may add a comment like, “That quotation is often attributed to George Orwell, but there is no record he ever said it. The earliest record of its having been stated was by Jane Doe, a journalist for XYZ news in an article she wrote for Pacific Monthly in 1972.” A response like that, however, spooks some people because they may forget that it’s still just an Internet search result, albeit one that extracts information and presents it in a conversation-like manner.

AI has been with us for a long time.

quote:

Google searches are artificial and intelligent-like because they must sift through literally countless sources to try to find something that might be relevant. No genuine-intelligent humans involved.

With AI's approach t scans all internet sources for answers and everything on the net isn't true of course, so it can provide false answers based on the false data online. Surely they are working to correct that, or maybe, AI is working on AI to correct AI.... Shall we play a game?

For now Humans can figure out AI from Human responses at least now easily. The AI videos are for now pretty easy to spot, pictures as well, who know how much self learning it will have to improve the software.

Open the pod bay doors, Hal......

gunboards has it's own AI member, don't recall the name but it was activated a year or so ago,

it is called forafrank,

I asked AI how World War Eleven started and it said it was a result of the Germans bombing Pearl Harbor.

Seems legit.

Sounds about right.