Do you have a dumb question that you're kind of embarrassed to ask in the main thread? Is there something you're just not sure about?
This is your opportunity to ask questions. No question too simple or too silly.
Culture war topics are accepted, and proposals for a better intro post are appreciated.
Jump in the discussion.
No email address required.
Notes -
Tried a few of my comments here on a blank prompt; it's either a testament to my mimicry or a consequence of little substance but it mostly fails, especially memes and/or chudisms seem to throw it off and it defaults to American. Weirdly enough, the failure rate is lower when I paste multiple comments at once (even when individually it judges every comment as American), the main mechanism at work indeed seems to be pattern-matching. ...Man, an AI-driven police state would be some shit, huh?
It's still mildly spooky with some of my drafts and longer writeups - Claude has none of my shit and consistently guesses right across multiple regens, even standing its ground when I wink-wink-nudge-nudge it if it's really really sure. Its explanations are also sometimes funny:
I think I just got dissed by a machine, send help.
Really? I thought it's a common idiom, point taken.
For what it's worth, 4o indeed fails 100% of the time on the same prompts. Don't have o1 to try but 4o seems to get sidetracked by the content almost immediately so I don't think the CoT layers would help much.
I don't have consistent access to o1 either (I do nothing that warrants the expense that Flash 2 Thinking can't wrangle), but I agree it was a prude about it.
There's truesight and there's truesight. I have very little doubt that most people would never clock me as Indian if it weren't for all the times I've mentioned it intentionally.
(At least it never had the balls to call me an ESL speaker lol)
Hmmm
:(
More options
Context Copy link
More options
Context Copy link
I would have guessed. It’s extremely obvious when you talk about, for example, “giving” an exam (no non-Indian anglophone says this, they would say ‘taking’ an exam), to name just one example that comes to mind that I recall reading. My guess is the model found the language first (word frequency is the purest form of NLP etc) and then came up with the justification after the fact, it’s not an actual explanation of the reasoning.
Huh. I was going to argue that can't possibly be right, but apparently it's a very Indian thing indeed. Good catch, though I doubt that particular phrase was in the context here.
I happen to trust Claude to explain its reasoning more than older models, Anthropic has done something funky that makes it notice its own uncertainty (which can lead to hallucinations) somehow, particularly when you ask about obscure topics or those not in training. Blew me away that it didn't immediately confabulate but rather asked clarifying questions.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link