CitizenBane @ CitizenBane @lemmy.world

Posts

1

Comments

17

Joined

5 days ago

I've opened up the custom GPT to the whole community. Please share if you find it valuable.

Generational alcohol abuse will do that.

I don't want to sound like a shill, but I've created a Custom GPT to help recognize distortion/misinformation/propaganda.
https://a.lemmy.world/lemmy.world/post/27608970

I'm hoping to receive more feedback on it. I'd love some help refining it too. Yes, I plan on open sourcing it once I get past the "OpenAI problem".

It will be open sourced eventually. I need to figure out how to properly replicate the responses on other LLMs, whether local or not. I'm seeking help in this.

Thank you ❤️

Anal Musk

I'd need better hardware to do that, unfortunately. Either way, some billionaire would get money for me to do that.

Yes, and rightfully so.

https://www.politico.com/news/magazine/2023/12/19/godwins-law-trump-hitler-00132427

Even Godwin himself said that comparing Trump to Hitler and the GOP to Nazis is apt.

https://www.politico.com/news/magazine/2023/12/19/godwins-law-trump-hitler-00132427

"Surely the leopards will not eat MY face!"

Yes. We know.

What's the alternative at this moment? Can you provide any insight that could help?

Here's an example, if anyone is interested:

prompt: 5g causes cancer

response:

💬 Claim: “5G causes cancer.”
🔍 Analysis: 🟠 Misleading Correlation

📌 Distortion Analysis (Perception Distortion Scale)

This claim misrepresents correlation as causation, which is one of the most common distortion patterns. It sounds alarming but lacks solid scientific grounding.

✅ What Does the Evidence Say?

• 5G uses non-ionizing radiation, which does not carry enough energy to damage DNA or cause mutations—unlike ionizing radiation (like X-rays or gamma rays).
• Large regulatory and scientific bodies (like the World Health Organization, FDA, CDC, and ICNIRP) have not found credible evidence linking 5G exposure to cancer when exposure remains within internationally accepted limits.
• Some animal studies (e.g., on rats exposed to high levels of radiofrequency) have shown effects at levels much higher than humans ever experience, making them inapplicable to real-world 5G conditions.

🛠️ Why This Claim Persists (Clarity Toolkit Insight)

This is a classic case of distortion via emotional triggers and misframing, especially fear-based framing:

• ❗ Fear of Harm: Suggests danger without proof.
• 🔀 Framing Effect: Reframes uncertainty ("not proven safe") as proof of danger.
• 🔎 Distortion Filter: The claim bypasses relevant scientific context and exploits public unfamiliarity with radiation types.
• 🧭 Reality Alignment Check:
  • Falsifiability → If new, repeatable evidence emerged showing harm at real-world exposure levels, the scientific consensus would shift.
  • Source Check → Most “5G = cancer” claims stem from unverified, fringe, or misinterpreted sources, not from peer-reviewed meta-analyses.

🧠 Perception Note

This claim preys on scientific uncertainty—the fact that science is always “open” to new findings is reframed to imply something is being hidden or ignored.

🧰 Want to dive deeper? Check out the Framing Neutralizer and Reality Alignment tools in the Clarity Toolkit for how to spot this kind of language distortion.

✅ Bottom Line:

📌 There is no credible evidence that 5G causes cancer.
📌 The claim is based on misinterpretation, emotional manipulation, and out-of-context data.

Would you like a breakdown of how this claim differs from scientifically valid caution, or want help evaluating a specific source spreading it?

Could you elaborate? Not sure what you mean.

I'd love to see a link of the chat.

Good question.

Hey, thanks for checking in! I am trying local versions of CLARi, but I don't have the best hardware for it at the moment. I'm working on upgrading that all soon.

https://lemmy.world/post/27608970

Right now, my main focus is to get this OFF of OpenAI. In the meantime, I hope you check out the custom GPT, and help me with giving some feedback on it.

I'm working on this the best that I can, given my limited resources.

Software architect here, for over 25 years. Now working on AI. I don't think it will replace software developers, but it will empower them.