alt Hacker NewsWith how prevalent LLM verbal tics have become these days, I wonder if they're going to start un-passing the Turing Test at some point because of more and more people starting to notice and immediately clock these tics lol.
Replies
pants2 • yesterday at 9:02 PM
I might agree, GPT-4.5 was pretty close to peak conversationalist. Newer models are extremely cringe. 4.5 and o3 actually made me laugh on occasion. There might be a way of making Sol/Fable more human in its responses, but out of the box at least, they're terrible.
bbor • yesterday at 8:51 PM
You're overindexing on the past 3-6 months, IMHO.
That’s using the default system prompt, right? Which is told to be an assistant.