Safety Alignment Should Be Made More Than Just a Few Tokens Deep · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2406.05946/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTSafety Alignment Should Be Made More Than Just a Few Tokens Deep — mentioned by jackdoehttps://news.ycombinator.com/item?id=44208801urn:hackerpapers:mention:2406.05946:44208801Sat, 07 Jun 2025 10:54:45 GMT<p>I think one of the reason we are confused about what LLMs can do is because they use language. And we look at the &quot;reasoning traces&quot; and the tokens there look human, but what is actually happening is very alien to us, as shown by &quot;Biology of Large Language Models&quot;[1] and &quot;Safety Alignment Should Be Made More Than Just a Few Tokens Deep&quot;[2] I am struggling a lot to see what the tech can and can not do, particularly designing systems with them, and how to build systems where the whole is bigger than the sum of its parts. And I think this is because I am constantly confused by their…</p><p><a href="https://hackerpaper.kaipfister.de/p/2406.05946/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CR