Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I used to love Claude, but the latest models are slowly ruining it

androidauthority.com

Post reply on HN
Print view View original

41–50 of 63 posts

Re: I used to love Claude, but the latest models are slowly ruining it

#41

Post by stringfood »

LeoPanthera wrote: post #36

This is a serious suggestion, not a joke: Have you tried being nice to the model? There are so many criticisms here that I just don't see myself. If the models have been trained on human responses, then it's plausible that they will prefer to become less helpful to requests which are blunt or even rude, because that's what humans do too.

yes I have hypothesized this as well - if you ask rudely on StackOverflow you will get bad or even misleading answers - but if you ask nicely you will more likely be given good information.

It could stand to reason that if you are nice to the AI, you will get a response that is trained on all of the nice responses and be higher quality.

Re: I used to love Claude, but the latest models are slowly ruining it

#42

Post by hirako2000 »

You've got to understand, proprietary models operate as the following:

- release: full precision, debrided, uncapped context

- shortly after, hooked: quantized, governance department slammed, and a pseudo large context, attention reduced to start and end of thread.

- down the road: 4bit quantized or worse with nerf incantation to make the next upcoming model feel amazing.

Rince and repeat.

Re: I used to love Claude, but the latest models are slowly ruining it

#43

Post by matheusmoreira »

nolok wrote: post #10
JumpCrisscross wrote: post #6

It's quite obnoxious. I asked if brown rice left in the fridge for a couple days–originally put in for use in fried rices–was still safe. Fable decided I'm trying to produce biotoxins. Which, ironically, prompted me to learn how to produce Bacillus cereus at home [1]. I paid for a year but am going back to Kagi's multi-model system [2]. [1] https://pmc.ncbi.nlm.nih.gov/articles/PMC7913059/ Don't Do It [2] https://ass…

"Beware of he who would deny you access to information, for in his heart he dreams himself your master." (he, in this case, would not be the llm but the people over it) I find those kind of limitation very dystopian and way more dangerous than the threat they claim to fight against.

Anthropic literally thinks they are uplifting people with Claude. As though you're some kind of caveman who just discovered fire while they're on the Enterprise.

Re: I used to love Claude, but the latest models are slowly ruining it

#44

Post by moezd »

Hard agree. I used to have a tuned setup where I could force it to do research properly, summarize in chunks that it would remember and form the synthesized response that way. Nowadays it's just like "oh I forgot about using that tool, sorry", "yeah I know we agreed on that and I didn't do it anyway", "That knowledge is beyond my training date, I suspect foul play" - even when you instruct it to fetch latest info all the time, or "you already told me X. This cancels your reasoning about A, B, C, so D is the only logical choice", even when those clearly still have merit, oh and never ending "your previous discussion X is relevant here, in combination to Y, but not so much as Z since there's a OSS implementation of it and another one blablabla..." Like, who remembers these all at the same time in their heads?

It's like with each release they force you to reconsider your pipelines altogether, and without announcing changes properly, you feel like a junior JS developer fighting dependencies once again.

Re: I used to love Claude, but the latest models are slowly ruining it

#45

Post by Leynos »

queenkjuul wrote: post #26

I get really sick of Opus 4.8 and Fable telling me things i ask it at work are "out of scope," "not related to my ticket," "not the real problem"... I decide what is in scope, what I work on, and what needs fixing! It drives me nuts, it's like it's trying to avoid doing work

Yeah, I went through a period after 4.7 launched of not using Claude for code work at all because of the condescending refusals. (Kept using it for planning and design work). Still had three pretty bad refusals from 4.8, but not the same quantity as from 4.7.

Claude.ai is pretty frustrating too. It will talk to me as if anything I ask for is below it. Could be the system prompt I use, but I did not have this issue with 4.6.

Yes, I tend to prefer GPT, but I can't remember having GPT ever refuse a direct instruction that wasn't an obvious ToS violation.

Re: I used to love Claude, but the latest models are slowly ruining it

#46

Post by gunalx »

BlueGh0st wrote: post #35
nozzlegear wrote: post #23

Earlier quoted context omitted.

> I paid for a year but am going back to Kagi's multi-model system [2]. I've been using DuckDuckGo's multi-model service for my "ask an AI random questions" needs. I was already paying them and discovered this LLM thing is part of my subscription. Works pretty well and has privacy guarantees I'd expect out of DDG, though I think they've been tightening the usage you can get out of it recently. I'll have to try Kagi i…

I use them frequently but I'm skeptical of their "private" claims. I asked one of the DDG ChatGPT bots about some error output from a program and apparently forgot to redact a URL. I found the DDG bot trying to access it about half an hour later. It was a long and randomly generated alpha-numeric subdomain and the conversation never discussed the URL or anything related to it- it was simply buried in the pasted error…

Interresting, Have you done any Møre testing trying to trigger this behaviour? If it is semi konsistent or even just alone it makes a god case to switch.

Re: I used to love Claude, but the latest models are slowly ruining it

#47

Post by delichon »

LeoPanthera wrote: post #36

This is a serious suggestion, not a joke: Have you tried being nice to the model? There are so many criticisms here that I just don't see myself. If the models have been trained on human responses, then it's plausible that they will prefer to become less helpful to requests which are blunt or even rude, because that's what humans do too.

  Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. -- https://arxiv.org/abs/2510.04950

Re: I used to love Claude, but the latest models are slowly ruining it

#48

Post by cma »

dmix wrote: post #8

Claude has never been the best Chat agent. GPT and Gemini have the lead there. But Claude chat is still perfectly serviceable if you don’t want to pay for two.

Compare Claude at the time to 4o's sycophantic era (when o4 updated in response to Grok), Claude was lightyears better.

Re: I used to love Claude, but the latest models are slowly ruining it

#49

Post by klipklop »

nolok wrote: post #10
JumpCrisscross wrote: post #6

It's quite obnoxious. I asked if brown rice left in the fridge for a couple days–originally put in for use in fried rices–was still safe. Fable decided I'm trying to produce biotoxins. Which, ironically, prompted me to learn how to produce Bacillus cereus at home [1]. I paid for a year but am going back to Kagi's multi-model system [2]. [1] https://pmc.ncbi.nlm.nih.gov/articles/PMC7913059/ Don't Do It [2] https://ass…

"Beware of he who would deny you access to information, for in his heart he dreams himself your master." (he, in this case, would not be the llm but the people over it) I find those kind of limitation very dystopian and way more dangerous than the threat they claim to fight against.

I often use this quote. One of my favorite of all times. Really cool to see somebody else use it! Every year that passes the more important that quote becomes.

Re: I used to love Claude, but the latest models are slowly ruining it

#50

Post by LeoPanthera »

delichon wrote: post #47
LeoPanthera wrote: post #36

This is a serious suggestion, not a joke: Have you tried being nice to the model? There are so many criticisms here that I just don't see myself. If the models have been trained on human responses, then it's plausible that they will prefer to become less helpful to requests which are blunt or even rude, because that's what humans do too.

Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. -- https://arxiv.org/abs/2510.04950

But this refers only to ChatGPT 4o, which was famous for being obsequious.
Post reply on HN