this post was submitted on 09 Oct 2026
412 points (97.2% liked)
Technology
88988 readers
2598 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
IIRC a decent amount of researchers have been able to get the enterprise models to do things they shouldn't by "being mean" to the AI.
Makes sense then, rather than improve the system to not just cave to rude words they tell people they can't use rude words... Just more proof it's all a big joke.
Makes sense. Get it into an adversarial kind of context and it will predict more text that goes against other rules "established" in the context.
There will be other paths to do this. Like a context where there's a lot of suspicion for other parts of the context would be one of my top guesses. Given the way they work, you could gaslight the shit out of them, since they aren't an entity that has any memory of its actions. You can even edit the context to modify its responses, which will affect the tokens it predicts going forward.
Though I'm curious how this will be handled by companies that expose access to claude to anonymous people on their website, like ddg.