this post was submitted on 05 Feb 2024
194 points (97.1% liked)

Technology

55919 readers
3240 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 content.
  3. Be excellent to each another!
  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, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] Byter@lemmy.one 18 points 5 months ago (3 children)

I'd love a browser-embedded LLM that had access to the DOM.

"Highlight all passages that talk about yadda yadda. Remove all other content. Convert the dates to the ISO standard. Put them on a number line chart, labeled by blah."

That'd be great UX.

[–] JoeyJoeJoeJr@lemmy.ml 10 points 5 months ago (1 children)

You are falling into a common trap. LLMs do not have understanding - asking it to do things like convert dates and put them on a number line may yield correct results sometimes, but since the LLM does not understand what it's doing, it may "hallucinate" dates that look correct, but don't actually align with the source.

[–] Byter@lemmy.one 1 points 5 months ago

Thank you for calling that out. I'm well aware, but appreciate your cautioning.

I've seen hallucinations from LLMs at home and at work (where I've literally had them transcribe dates like this). They're still absolutely worth it for their ability to handle unstructured data and the speed of iteration you get -- whether they "understand" the task or not.

I know to check my (its) work when it matters, and I can add guard rails and selectively make parts of the process more robust later if need be.

[–] Cqrd@lemmy.dbzer0.com 1 points 5 months ago

Arc has an LLM that lets you replace your search functionality with search or ask, where if you type a question it tries to answer it based on the content on the page. Kinda close to what you're talking about.

Arc is genuinely trying to use LLMs in their browser in interesting ways.

[–] daed@lemmy.world 1 points 5 months ago

That's actually fascinating to think about. Would be a fun project to mash something like Blazor Server and an LLM together and allow users to just kindly ask to rewrite the DOM in plain English.