this post was submitted on 02 Jul 2025
252 points (99.2% liked)

Technology

72319 readers
2758 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 2 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] sundray@lemmus.org 17 points 2 days ago (2 children)

Didn't have time to read that, so I threw your comment into my local TinyLlama instance:

The article discusses an artificial intelligence assistant named "AiLlMa," which is used for summarizing news and articles in various languages. The author suggests that using such AI assistants, including LLMs, can save time by taking away the need to manually search and read source material. He argues that LLMs generate summaries that are spot-on without missing important points or topics, and that using them along with personal knowledge gives a distinct advantage over independent reading of sources. The author uses examples of LLMs generating useful summaries from articles on various topics, such as summarizing news headlines for readers and creating nuanced takes on articles based on contextual information. Overall, the article suggests that using AI assistants like LLMs can improve productivity, boost efficiency, and produce more accurate summaries.

[–] baltakatei@sopuli.xyz 13 points 2 days ago (1 children)

Didn't have time to read that, so I threw your comment into ChatGPT:

Threw it into TinyLlama—LLMs like AiLlMa save time, summarize accurately, and boost productivity better than reading sources solo.

[–] interdimensionalmeme@lemmy.ml 6 points 2 days 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.