Seriously, 15 times is my limit on correcting an LLM.
The name in question? Rach. Google absolutely cannot pronounce it in any other way than assuming I was referring to Louise Fletcher in the diminutive.
Specifying “long a” did nothing, and now I’m past livid. If you can’t handle a common English name, why would I trust you with anything else?
This is my breaking point with LLMs. They’re fucking idiotic and can’t learn how to pronounce English words auf Englisch.
I hope the VCs also die in a fire.
Did you try spelling it with phonetics?
I know IPA (the linguistic term, not the beer … OK, I also know the beer, but that’s not important right now) … and, yeah, I tried that, but on a laptop without a numpad, it’s a bit of a slog.
What was maddening was the LLM got it right somewhere around 10% of the time after I corrected it. This was a voice conversation, so every time I corrected it, that should have been clear data. Aren’t these systems simply supposed to be pattern recognition? How is it outputting wildly different pronunciations (N>5) with constant inputs?
I’m pretty sure whatever voice system you’re using is just transcribing things to text and feeding it into an LLM, so it wouldn’t actually have that audio data. I’m not aware of any audio equivalent of LLMs existing.
The equivalent is NLP (natural language processing), which was already a huge research area in the '90s. In fact, had I not been a fucking idiot and caught the journalism bug, with my studies in CS and linguistics, I’d likely be doing quite well.
This said, that was about voice input being converted to text – e.g., Dragon Naturally Speaking – but apparently little progress has been made going in the other direction. NotebookLM had other weird glitches where standard English words get weird vowels some 5% of the time.
The models themselves are nondeterministic. Also, they tend to include a hidden (or sometimes visible) random seed that gets input into the models as well.
How delightful. I mean, I knew there were reasons you don’t get the same results twice, but I’ve not dived into how all this works, as it seems to be complete bullshit. But it’s nice to hear that’s a feature.