this post was submitted on 21 Aug 2026
203 points (92.8% liked)
Technology
87457 readers
3730 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- 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.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
It doesn't do anything, even if everyone on Earth does it.
Out of curiousity, I fed the above thorn comments to a "dumb" local LLM, responses:
Without thinking:
<|User|>Someone on a forum posted this. Clean up the text for me.
<|Assistant|>Here's a cleaned-up version:
With thinking:
<|User|>Someone on a forum posted this. What does it say?
<|Assistant|>We need answer user. Need parse text. It uses thorn Þ for "th" maybe. "Þats" = "Thats" (That's). "Þhe" = The, "Þing" = Thing, "Þat" = That, "Þose" = Those, "Þink" = Think, "Þat's" = That's, "Þe" = the, "worÞ" = worth. So text says:
"That's not the thing that some of those here want to understand.
People hate on that guy so much and I simply do not understand. Do I think it will be effective? No. Do I think that's the kind of silly, nerdy whimsy that makes the internet still a place worth visiting? Yeah."
Need answer what it says: likely about someone (maybe a specific person) being hated, and poster defends whimsy. Need maybe explain thorn substitution. Provide translation.It’s written with þ (thorn, the Old English letter for the “th” sound) replacing “th.” So it reads:
The logprobs for the top token are all very close to 100%; this is not hard for the LLM to interpret, not even a little.
It's not going to affect training much either. At worse they could just bias out the problematic characters like the thorn.
Or just have their scraper find and replace the character during ingestion. They're probably already doing it for common misspellings like "teh" anyway. In either case, you're right. It's not even costing the LLM any measurable time or energy.