Hmm Interesting, seems your Model is hallucinating a lot, maybe try improving your system prompt. I have a deepseek-ai_DeepSeek-R1-Distill-Qwen-1.5B Running locally. Here is my output for the Orignal Comment
The article discusses the perception of a book as trash due to the author’s use of LLM without informing readers. The author highlights the benefits of using LLMs, such as saving time and improving productivity, by suggesting that using locally deployed LLMs can significantly enhance the summarization process. The article also warns against the misuse of LLMs, emphasizing the importance of verifying information. The author concludes that relying on LLMs can surpass human capabilities when combined with personal knowledge. Key Details: The article’s main points are:
- The book is perceived as trash due to LLM usage without reader notification.
- LLMs save time and improve productivity.
- Using locally deployed LLMs for summarization is effective.
- Misuse of LLMs can lead to false information.
- Combining LLMs with personal knowledge enhances quality.
I use the following prompt before article
You are a concise summarization AI. Follow these rules:
- NEVER exceed 4 sentences or 150 words.
- Use this format:
"Summary: [2-sentence core idea].
Key Details: [3–4 bullet points]."- Omit examples, disclaimers, or fluff.
baltakatei@sopuli.xyz 3 weeks ago
Didn’t have time to read that, so I threw your comment into ChatGPT:
interdimensionalmeme@lemmy.ml 3 weeks ago
Actually, I just dropped the entire thread — including the original article — into ChatGPT since I didn’t have time to read it all either. Then I asked it to write the best possible 3-sentence Lemmy comment specifically for your reply. So, ironically, we’ve both delegated the thinking to LLMs — now that’s productivity.
Then I asked “write the next 3 sentence providing the most insight that you can in 3 sentences” and it responded
The real issue here isn’t just that LLMs can fabricate citations — it’s that institutions and publishers are increasingly failing to enforce even basic quality controls, allowing AI-generated content to slip through without proper oversight. When tools meant to assist in research are used to replace it, the result is a veneer of credibility masking hollow or false scholarship. If this trend continues, we risk flooding academic discourse with noise that’s indistinguishable from rigor, eroding trust in legitimate research.
then I asked “But chatgpt, quality control, rigor, those have been gone for aeons, the barrier to write was so high no one really tried so the control, rigor, editors have largely atrophied long ago, respond in 3 sentences” and it responded
You’re right — what we’re seeing now is less a collapse and more an exposure of how little substance was holding it all up. The illusion of rigor persisted mostly because the barrier to entry was too high for mass participation, not because the gatekeepers were doing their jobs. LLMs didn’t break the system; they just made its hollowness impossible to ignore.