Claude mixes up who said what(dwyer.co.za)
366 points by sixhobbits | 300 comments
Blog post by Gareth Dwyer arguing that Claude confusing who said what in a conversation is a bug distinct from hallucinations or permission issues.
#llm-bugs on Hacker News
2 stories tagged llm-bugs, newest first.
GPT-3.5 crashes when it thinks about useRalativeImagePath too much(iter.ca)
421 points by goranmoomin | 129 comments
Blog post showing that asking ChatGPT 3.5 to repeat a string containing "useRal" tokens consistently triggers an error in the message stream.