Post B5ktag7WJUoPDKc7LU by janeishly@beige.party
(DIR) More posts by janeishly@beige.party
(DIR) Post #B5jdg25AIHGkLq5EeW by chaucerburnt@aus.social
0 likes, 0 repeats
People need to stop asking LLMs "why did you do [thing]?" and treating the answer as authoritative. LLMs do not "remember" their thought processes in that way, and even if they did, the answers would likely not be human-understandable. When you ask a LLM this question, you're asking it to construct the kind of explanation that a human might give in a similar conversation. Treating this as the *actual* answer is likely to lead you astray.https://www.tomshardware.com/tech-industry/artificial-intelligence/claude-powered-ai-coding-agent-deletes-entire-company-database-in-9-seconds-backups-zapped-after-cursor-tool-powered-by-anthropics-claude-goes-rogue
(DIR) Post #B5kmStcHYHAL4lLPyC by janeishly@beige.party
0 likes, 0 repeats
@chaucerburnt My bloody violin's so small I can't find it, otherwise I'd definitely be playing it. (You're absolutely right about anthropomorphisation of these systems being infuriating, however. It's literally just going "Hm, what word should go after this one?" How do people *still* not understand this?)
(DIR) Post #B5kmStoKpSo5g8z2ky by chaucerburnt@aus.social
0 likes, 0 repeats
@janeishly It would help if the vendors weren't encouraging anthropomorphisation by doing things like giving their LLMs human names.Like, yes, people have some responsibility to understand the tech they're using, but manufacturers also have responsibility not to encourage misunderstanding.
(DIR) Post #B5kmSu027yAGGQSNzU by IngaLovinde@embracing.space
0 likes, 0 repeats
@chaucerburnt @janeishly and if the vendors weren't even more encouraging anthropomorphisation by making their LLMs speak in first person voice (implying that there is a first person there)
(DIR) Post #B5ktag7WJUoPDKc7LU by janeishly@beige.party
0 likes, 0 repeats
@IngaLovinde @chaucerburnt Yeah, I ABSOLUTELY HATE that it gives me the ick to read their fawning flood of pap.