this post was submitted on 24 Aug 2023
437 points (88.7% liked)
Technology
59317 readers
5567 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- 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, to ask if your bot can be added please contact us.
- 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
view the rest of the comments
it doesn't even look at the smaller picture. LLMs build sentences by looking at what's most statistically likely to follow the part of the sentence they have already built (based on the most frequent combinations from their training data). If they start with "Hitler was effective" LLMs don't make any ethical consideration at all.... they just look at how to end that sentence in the most statistically convincing imitation of human language that they can.
Guardrails are built by painstakingly trying to add ad-hoc rules not to generate "combinations that contain these words" or "sequences of words like these". They are easily bypassed by asking for the same concept in another way that wasn't explicitly disabled, because there's no "concept" to LLMs, just combination of words.
Yes, but in many defense the "smaller picture" I was alluding to was more like the 4096 tokens of context ChatGPT uses. I didn't mean to suggest it was doing anything we'd recognize as forming an opinion.
Sorry if I gave you the impression that I was trying to disagree with you. I just piggy-backed on your comment and sort of continued it. If you read them one after the other as one comment (at least iny head), they seem to flow well