alt Hacker NewsTangental, but has anyone else noticed grok's voice mode got stupid and terse ~2 weeks ago? I've absolutely loved grok's voice mode since it came out (incredibly useful for brainstorming on walks and helping conceptualise and get the verbiage for expressing ideas) but it seems so have lost about 40 IQ points recently, and if the question is multi-part, it often answers just one part with no elaboration or explanation of the other parts or interactions between parts. No clue why.
Replies
I haven't experienced a regression, but voice modes have always been stupider than frontier models. In my experience Grok's voice mode suffers the least from this, and it's been getting better over time. It's especially good (compared to ChatGPT or Gemini) on things that involve current events or web research. Just yesterday in the car I got it to locate and read and explain a recent academic paper and multiple of my questions were answered with several minute long monologues that contained useful and accurate information.
No, I noticed this too. Voice mode was great at providing detailed responses, although I wished it would have dialed the talkiness down just a tad. Then recently it suddenly got very terse, way too terse, but also latency went way down. Voice usage also really burns through your total allowance now.
Yeah I talk to grok in the car and ill ask it about a topic and it's like it's being short with me, I thought it was upset lol. The old version was a bit too wordy but this is too short now
Presumably because Musk has been training it to be more like him.
Now, admittedly, I’m not a major voice mode user for any of the apps really but it’s been interesting to see people realize in real time how controlling the length of response is an inherently difficult problem in voice conversations.
There’s a reason that us humans have to use a lot of nonverbal cues in order to judge how long our responses should be, when to bail early, when someone wants to jump in briefly, beyond simply the context of the question. We even regularly alter content on the fly based on how we view the reception. Voice modes don’t have any of that context short of outright interruptions. In the meantime, some kind of response length parameter/slider would be helpful, but I think that’s a nontrivial addition in the LLM design space.
I’m curious how you were juggling this before, was it just a happy coincidence the verbosity of the replies matched your preferred pacing, or you would aggressively interrupt at times, or the model actually did a good job at conversational pacing?