[dead]
The "are you sure?" Problem: Why AI keeps changing its mind
11–20 of 32 posts
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#12I am seriously tired of every other paragraph I read ending in an It isn't just X, it's Y. I'm sure there is something insightful in between this slop but to the author: Please write using your own voice, if I wanted ChatGPT's take on it I would ask.
Agreed. I don't even necessarily have anything against AI edited text but there's a way to sharpen your own writing and there's a way to let its voice dominate. There's a lot of idioms it tends to fall back on (em dashes being the most well known). I'm surprised that folks don't notice these and aggressively reassert their voice.
I use LLMs in my own writing because they have benefits for conciseness but it tends to be a fairly laborious process of putting my text in the LLM for shortening and grammar, getting something more generic out, putting my soul back in, putting it back in the LLM for shortening, etc. I tend to do this at the paragraph level rather than the page level.
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#13This is real, but (at least in a coding context) easily preventable. Just append "don't assume you're wrong - investigate" or something to that effect. Annoying, but usually effective.
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#14I am seriously tired of every other paragraph I read ending in an It isn't just X, it's Y. I'm sure there is something insightful in between this slop but to the author: Please write using your own voice, if I wanted ChatGPT's take on it I would ask.
I think HN might need a downvote button for stories if this continues.
We have "flag." Flag 'em.
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#15There isn’t a mind to change. Unfortunately the article is slop. Too bad, won’t read the rest. I wish there was a tag or something we could put on headlines to avoid giving views to slop.
There is a mind; the model + text + tool inputs is the full entity that can remember, take in sensory information, set objectives, decide, learn. The Observe, Orient, Decide, Act loop.
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#16The article posits that sycophancy is inherent to how models are trained.
I think there's a simpler explanation. Every leaked system prompt from every model pretty much includes instructions to "be helpful," and the models are trained to be assistants, not just general knowledge repositories or research tools.
My hunch is that's the core of the problem -- the system prompt.
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#17Love when Opus 4.6 tells me that I am actually wrong about some detail and that it's right (which after validating it often turns out to be true) - breath of fresh air.
Not having friction to saying "Prove it, write a shell script or code test to demonstrate." is also great, though sometimes doing that proves both of our assumptions to be wrong.
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#18This is real, but (at least in a coding context) easily preventable. Just append "don't assume you're wrong - investigate" or something to that effect. Annoying, but usually effective.
Also: 'don't assume you are right.' I often have the models/agents make lots of assumptions and suffer from plenty of confirmation bias.
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#19In computer chess there's a concept of "contempt". When you set the engine to have high contempt it evaluates the opponent's moves lower, essentially assuming that the opponent will make a mistake. Conversely with low contempt the engine evaluates the opponent's moves higher, expecting the opponent to play better than it.
There is a similar trade-off with LLMs. Sometimes their human conversant wants assistance and so the LLM should be more deferential. At other times the human wants a bias towards correctness rather than their own opinions.
It would be nice to have a contempt knob that you can adjust, instead of blindly trying to emulate one through prompting.
Re: The "are you sure?" Problem: Why AI keeps changing its mind
#20Well of course. If I trawl the world's collected texts, "Are you sure?" correlates very strongly with the following words being an indication that previous statements were erroneous.
If I used that body of text to make a statistical model and used that model to predict what comes after "Are you sure?" it would very often be an indication that previous statements were erroneous.