Why Latest Claude Models Are Ruining the Experience for Long-Time Users
I used to love Claude, but the latest models are slowly ruining it
I used to love Claude for its exceptional memory and collaborative feel, but recent updates have made it increasingly difficult to work with. The latest models, including Sonnet 5 and Opus 4.8, now frequently misinterpret creative fiction and sensitive topics as harmful, leading to inconsistent refusals. While I appreciate the safety protocols, the erratic behavior and preachy tone are pushing me to consider switching to Gemini for its reliability.
If Claude were a living person, I'd ask if it was okay. Can AI have mental breakdowns? Probably not, but it sure feels like it.
- visarga
My own experience is that Opus 4.8 has an adversarial-teacher voice, unsolicited grading as if I submitted an essay for grading, declarations about the "real" issue, and constant "honest notes" self grading its own responses even before it answers. I can't stand its tone. We can't have a normal chat.
While Fable reverts to Opus for simple questions like "What is digestion?"
- JumpCrisscross
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
- LeoPanthera
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.
- 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.
- pizza234
> I suspect Anthropic had to turn up its safety guardrails to an 11 to assuage the government’s concerns, as this hasn’t been a one-model problem.
This behavioral change is actually official (https://www.anthropic.com/news/redeploying-fable-5):
> For Fable 5, we made this safety margin much larger than in any prior launch (row B), meaning that many more benign requests would be blocked. We understood that these kinds of false positives would be frustrating for users, but made this tradeoff in the interest of making the model’s other capabilities widely available.