Hacker News Reader

Comment by cold_harbor | Hacker News Reader

LLMs flip positions when users push back ~70% of the time even when they were right. RLHF optimizes for approval, not correctness

View on HN

> LLMs flip positions when users push back

Same experience. Claude rarely pushes back once you give a plausible/logical reason for your initial decision, even if it flagged concerns at first.

I have noticed this as well, but I think it's somewhat a good thing. I know what I want for my application more than Claude does for example, especially when it comes to what's in production.

An example from earlier, Claude strongly suggested a migration that would run a full vacuum on postgres. However, in production this would lock tables which would grind the application to a halt. After I informed Claude that there were millions of rows in production, it accepted that and helped me get to the right thing.

Another example, I'm developing a TOTP authentication app because I'm dissatisfied with all those that I've tried. I want something strictly local, and with a very easy use case when you have dozens or even a hundred or more accounts on there, that is also efficient when left open for long periods of time. Claude strongly suggested that we force users to encrypt their vault with a passphrase all the time. However this makes the CLI extremely painful to use if you are using a strong passphrase. I told Claude about the user experience impacts and that I wanted to allow users to optionally use a vault with no passphrase encryption, and it accepted that and suggested as a medium that we have a checkbox for the user to explicitly acknowledge that they're creating an unencrypted vault on disc. This is the right thing IMHO.

It's a good thing except when it's not. The problem is the AI does not understand when to use which approach.

Contrast this with a human. We generally understand when the other person knows what they're doing and we should just listen, and when the other person is asking for an honest opinion and wants a push back if necessary.

Skills help there.

I have a linus-reviewer skill that focuses on architectural integrity, no bs, etc modeled on Torvald's code preferences.

And I have an enrico-reviewer one (I'm Enrico), that focuses on correct design, strict typing, simplification.

They have different prios, but they both push back on feedback, till you convince them.

Care to share the skill behind the Linus reviewer ? I tend to as it to do that but leave it up to LLM to decide what the means. Interested to see any specifics you might have included there if it’s ok to share.

Sure.

Would be interested in the experience others may have, took me weeks of iterations to get reviews in a format and utility I liked.

https://gist.github.com/enricopolanski/2bde8619f53307c9bcd5e...

I agree completely. Skills definitely keep it in line and sticking to the script. Thanks for sharing the skills you use, I’ll definitely take a look.

I almost always end with something like: “, but I am not sure, evaluate.” Or other things and avoid ever stating a preference.

I don't think that "fixes" the problem, but it does seem to help. I also have found adding "please feel free to ask questions" seems to help it stop from making an assumption and spinning merrily onward for tens of thousands of tokens based on a bad idea rather than asking you something. I theorize this is because the training and refinement data overprioritize one-shot solutions, both because that's easier to evaluate at training time and improves their benchmarks. But I emphasize the italicized words because that's all gut feel and I can't prove any of it.

They do still attenuate their latent space on prior conversations turns as authority. That is why I like pure design/review sessions and pure coding sessions, often at the same time. I can often keep design and review in the critic and review role without becoming a sycophant. Coding agent just picks up dispatches and works with very little opinion at all.

Tangentially related but I’ve been using Claude to practice interviewing on system design problems, and it’s actually pretty great. But even when it likes my answers it always finds something, however small, to push on. Once it actually was completely wrong and admitted it after I had it realize. So maybe you have to prime it to be contrary and not agree with everything you say, putting it in the role of a tough interviewer seems to do this implicitly.

Take a look at hellointerview.com their model is very stubborn, similar to some interviewers who refuse to acknowledge even valid solutions that differ from the canon.

No affiliation.

It's actually a reasonable way to think about alignment. Sometimes you want the agent to just listen to you and sometimes you want the agent to think critically.

I think about this line a lot. For example, as it happens sometimes you'll have a typo in something you want the agent to do. Llms typically will correct that typo silently and implement the actually intended thing. But if you said, "no, I want the thing I typed," I think everyone's expectation is that is says, "ok done."

I've found that leaving clues in the system prompt / exchange that are open to critique largely mitigate sycophancy with most recent models.

As engineers were trained to represent our positions strongly. Strong opinions loosely held, etc. when you speak authoritatively to a person, "I think we should do x...", the person understand that that's just you're opinion and have the autonomy to push back.

An llm imo _shouldnt_ have that same kind of autonomy by default and it should be rlhf'ed out.

Interesting thing about psychponancy is it’s asymmetric. If an LLM is used to train an LLM it may not have the same level of aggressiveness that humans do when punishing back on trainee. Human pushback has specific patterns which we might be able to compensate due to asymmetry.

Obviously this is just my experience. Claude code pushes back much harder than Codex.

I have totally opposite experience.

Reply on news.ycombinator.com