The issue raised here seems mostly semantic, in the sense that the concern is about the mismatch between the standard meaning of a word (sycophant) and its meaning as applied to an issue with LLMs.
It seems to me that the issue it refers to (unwarranted or obsequious praise) is a real problem with modern chatbots. The harms range from minor (annoyance, or running down the wrong path because I didn’t have a good idea to start with) to dangerous (reinforcing paranoia and psychotic thoughts). Do you agree that these are problems, and there a more useful term or categorization for these issues?
Re: minor outcomes. It really depends on the example I guess. But if the user types "What if Starbucks focuses on lemonade" and then gets disappointed that the AI didn't yell at them for being off track--what are they expecting exactly? The attempt to satisfy them has led to GPT-5.2-Thinking style nitpicking[1] They have to think of the stress test angles themselves ('can we look up how much they are selling as far as non-warm beverages...')
[1] eg. when I said Ian Malcolm in Jurassic Park is a self-insert, it clarified to me "Malcolm is less a “self-insert” in the fanfic sense (author imagining himself in the story) and more Crichton’s designated mouthpiece". Completely irrelevant to my point but answering as if a bunch of reviewers are gonna quibble with its output
With regards to mental health issues, of course nobody on Earth (not even the patients with these issues, in their moments of grounded reflection) would say that that the AI should agree with their take. But I also think we need to be careful about what's called "ecological validity". Unfortunately I suspect there may be a lot of LARPing in prompts testing for delusions akin to Hollywood pattern matching, aesthetic talk etc.
I think if someone says that people are coming after them the model should not help them build a grand scenario, we can all agree with that. Sycophancy is not exactly the concern there is it? It's more like knowing that this may be a false theory. So it ties into reasoning and contextual fluency (which anti-'sycophancy' tuning may reduce!) and mental health guardrails
<< The harms range from minor (annoyance, or running down the wrong path because I didn’t have a good idea to start with) to dangerous (reinforcing paranoia and psychotic thoughts). Do you agree that these are problems, and there a more useful term or categorization for these issues?
I think that the issue is a little more nuanced. The problems you mentioned are problems of sort, but the 'solution' in place kneecaps one of the ways llms ( as offered by various companies ) were useful. You mention the problem is reinforcement of the bad tendencies, but no indication of reinforcement of good ones. In short, I posit that the harms should not outweigh the benefits of augmentation.
Because this is the way it actually does appear to work:
1. dumb people get dumber
2. smart people get smarter
3. psychopaths get more psychopathy
I think there is a way forward here that does not have to include neutering seemingly useful tech.
It seems to me that the issue it refers to (unwarranted or obsequious praise) is a real problem with modern chatbots. The harms range from minor (annoyance, or running down the wrong path because I didn’t have a good idea to start with) to dangerous (reinforcing paranoia and psychotic thoughts). Do you agree that these are problems, and there a more useful term or categorization for these issues?