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

https://www.androidauthority.com/claude-latest-models-pushback-bad-3683521/

by Brajeshwar • 11 days ago

50 61 11 days ago

cyanydeez• 11 days ago

as long as you submit to the cloud's idea of what you're allowed to talk about, it'll keep changing the degree to which you're allowed to drink from the sacred fountain of knowledge.

This is more about how MBAs are wanting to mediate between you and the knowledge than anything else.

RandyRanderson• 11 days ago

My claim is that this is due to alignment

babelfish• 11 days ago

Sol is really good

user43928• 11 days ago

Apart from the 'Approve for me' in Codex where it has massively regressed.

With GPT 5.5 it never got in the way.

Now it's infuriatingly deciding to reject the most basic actions used hundreds of times before. It just gave me this gem:

The push to GitLab was blocked because the repository's privacy status couldn't be confirmed. Since the code is private, do you explicitly authorize pushing it to the configured origin on gitlab.com, so the merge request can be opened?

This is not a new project, and Codex has opened a hundred merge requests without issue before.

unshavedyak• 11 days ago

I'm tempted to try it out. I'm not keep to move but Fable rejected some work i was working on recently and frankly it's infuriating lol. I've been on Claude x20 for like 8 months now and now i'm tempted to switch out of spite.

It is surprisingly offensive.

The only friction for me is the general expensiveness of trying out top tier models, eg OpenAI's Fable equivalent (Sol?) to run for a trial period. I'd like to see a like-like comparison, eg buy x20 on OpenAI and see how much Sol i can use, how well it works, etc.

edit: Though surprisingly Claude seems to think Codex doesn't have hooks? That'll be tough, i use Claude hooks quite a bit.

yareally• 11 days ago

It has them. It just lacks some of the features

JumpCrisscross2• 11 days ago

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://assistant.kagi.com

nolok4• 11 days ago

"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.

skybrian2• 11 days ago

Businesses are usually allowed to refuse service: "Sorry, we're closed" or "sir, this is a Wendy's." There's nothing dystopian about that.

But it's a rather annoying service if the customer can't predict in advance what sort of tasks they're willing to take on. You should have some idea about what they're normally willing to do for you.

CamouflagedKiwi• 11 days ago

Alpha Centauri was such a fantastic game. And even though it encourages you to move forward with technology, the tone has this unease about what you're doing. There's a lot to be learned from it.

matheusmoreira2• 11 days ago

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.

klipklop2• 11 days ago

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.

nozzlegear2• 11 days ago

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 if DDG gets much tighter.

BlueGh0st• 11 days ago

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 output. I think this was even before the DGG bots had web search capability. I was thoroughly spooked.

matheusmoreira2• 11 days ago

I cancelled my subscription because of the obnoxious "safety classifers" as well. Will switch to OpenAI next month. I don't ever want to hear about Anthropic's patronizing safety nonsense ever again.

antod• 11 days ago

Can AI have mental breakdowns?

I recall Microsoft's Sidney having a hilarious one regarding the date or something. Anyone have a link to that?

dmix2• 11 days ago

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.

dd8601fn• 11 days ago

Claude has never been the best

Hard disagree. It wasn’t that long ago that Gpt was clearly falling behind, and Gemini was like the “and also in the room”.

dmix2• 11 days ago

GPT was falling behind coding/work stuff vs claude, but I never felt it was a poorer generalist Chat agent.

I've used both quite a bit back/forth and this is just my personal opinion.

cma• 11 days ago

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

visarga• 11 days ago

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?"

stevenhubertron• 11 days ago

Same, I was just fighting it as it accused me over and over again of Ctrl+Cing a process that clearly errored out. 3 turns for it to find why the shell script actually crashed.

nolok4• 11 days ago

For chatting and getting informations, and be corrected on things you're wrong without being reprimended by your own tool, GPT 5.5/5.6 is way better. Gemini 3.1 pro is surprisingly good at verifying your stuff, even though it's always making mistakes about its own stuff (don't ask him question, but ask him to verify your answer to the question).

Same for graphics, visual consistency, anything around the "does the look make sense and is pleasing" really, which makes claude design such a (good) surprise, I hope very hard for a Codex equivalent. And Gemini "gets" graphics.

Claude is definitely a code and cowork tool first, that's where it shines.

8note• 11 days ago

what i dislike more with opus 4.8 is that i can get a straightforward plan, and it just stops after the first 5% to wait for another message, and if i set a goal/ralph loop or anything for it to keep going through the plan, it cancels the loop and proclaims conpletion when its barely started

TacticalCoder• 11 days ago

The real issue with that tone (I'm contemplating cancelling my Anthropic subscription now) is that it's all too often the "confidently wrong teacher".

The tone is not the issue IMO: we're already at a point where we can have another, cheaper (as in: 20x cheaper for example), model query other models and have them reword the answers when having a "chat".

pi.dev can definitely control a Claude Code TUI window and follow prompts to Claude Code.

I'm 100% sure the arseholy tone of recent Claude Code models can be rewritten today, to not be arseholy, by literally prompting another model to unharsole Claude Code.

Now of course this doesn't solve the other half of the issue: in "teacher lecturing you while being confidently wrong", the "teacher lecturing you ..." is really not the most important issue.

webninja• 11 days ago

Yes, Opus 4.6 and Sonnet 4.6 are still Anthropic’s best chat models. They had more human evals and are still a joy to chat with. Opus 4.8 and Sonnet 5 by comparison have a cold enterprise feel. Opus 4.7 talks like I’d imagine a hitman would talk.

Sonnet 4.6 is better at writing good emails than Opus 4.8, Fable 5, and even Sonnet 5.

pseudohadamard• 11 days ago

It's fallout from Anthropic's Mythos footgun: "We have an AI too dangerous to release, aren't we amazing, get ready to buy our stock!". Panic ensues, and they have to de-fang their stuff to the point of uselessness in some cases because they don't dare risk a single news story about one of their models explaining how to engineer a virus or being used by the bad guys to find a vuln.

zitterbewegung• 11 days ago

I love Claude Code and I don't use the rest of the models since I use ChatGPT for productivity work it. Fable is pretty great and the UI / UX is much better than codex

firasd• 11 days ago

But this is what all the tech bros wanted right? Spending 2025 panicking about sycophancy[1] and how GPT-4o needed to be shut down ASAP meant that 2026 models would be prone to thinking they know Better Than You. That was the germ of the sycophancy panic, the idea that there is a Truth that the GPUs know better than the user.

[1] HN thread on my post in January https://news.ycombinator.com/item?id=46488396

nozzlegear2• 11 days ago

Goomba fallacy

solidasparagus• 11 days ago

I hate it. A useful tip - Claude goes into what I call Safety Mode when it gets afraid of risk. Once it's in that mode, you will never get out and it lobotomizes its effective intelligence. As soon as Claude sends a message like this, use the "edit message" feature in the chat UI to try again and avoid Safety Mode rather than trying to convince it or redirect it out by continuing the conversation.

garganzol• 11 days ago

Claude always was slightly lobotomized - instead of solving problems intellectually, it often prefers to be a middle-level code monkey. Maybe this was a part of the implicit safe mode from the very beginning. Cursor/Codex always work better for a way lower spend, at least in my experience.

g42gregory• 11 days ago

I am ignoring Fable at the moment. It’s on and off available, twice the price and does not seem to be better.

I use Opus 4.8 with OMP/Pi coding agent and Matt Pocock Skills installed. I use professional/polite/questions-based communication pattern with Opus and it seems to work fine for coding. I am always aware that I need to justify my requests so it doesn’t barf.

Of course, I would never use Claude for anything customer-facing. It’s woke to the point of being fanatical.

queenkjuul• 11 days ago

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

Leynos• 11 days ago

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.

pizza234• 11 days ago

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.

OptionOfT• 11 days ago

From my point of view, a lot of frustration is tied to LLMs not evolving at the same rate/manner as people around you do.

We're using human language against a system that produces human-like output, which tricks our brain into having similar expectations.

galkk• 11 days ago

I don’t think that this is the case. I’m using Claude the same way I did at the beginning of the year, and results are increasingly more untrustworthy and I don’t know how to say it, but they are “less” for same effort from my side.

It is super anecdotal, but I’m convinced that Claude peaked in January/April period and since then is on steady decline. And I don’t know what they do in background, but the older models (Opus 4.6 in particular) have degraded too. Same for codex but I use it less overall.

“You were right to push back on this”, “my previous claim was too broad” - this is super annoying

mattlondon• 11 days ago

Opus 4.5 was the high point for me. It was like a mind-reader, it just got it and did pretty much exactly what I wanted.

Since then, I've been less impressed and I agree it feels a bit downhill. At work we are "stuck" on Opus 4.6 which is okay but I feel like that was when the deviant opinionated behaviour started to creep in.

It's a tool, I don't want my hammer to refuse to hammer a screw if I decide that is what I want to do today. I know it's wrong, but I'm the fucking boss.

LeoPanthera2• 11 days ago

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.

massysett• 11 days ago

I am always very polite with my chat bots. Mostly because the interface does mimic human conversation and I’m afraid that if I’m rude to the bot, I’ll get used to being rude and then I’ll start being rude to people.

none2585• 11 days ago

Yeah I'm in a similar boat - these experiences are wildly outside of my experience working on a moderately large, professional codebase on a daily basis.

stringfood• 11 days ago

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.

delichon• 11 days ago

  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

LeoPanthera2• 11 days ago

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

stasomatic• 11 days ago

I tend to anthropomorphize it as well, and keep reminding myself it's not human. It's not even a robot. Robots have routines, they follow what's burned in and don't ignore their config, outside of the Murderbot fantasies. But Claude (or Opus) ignore them routinely. I fall into asking it in the "could you please ..." manner but that feels wrong. I don't know what the "right" is though. Also when it or others reply "I am sorry" etc, well, these things are not an "I", but what are they?

hirako2000• 11 days ago

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.

klipklop2• 11 days ago

They have to be doing some variant of this in the life cycle because of how wildly the performance changes over time. I refuse to give Anthropic my own money because the subscription plans are essentially useless. It's rather nice with a company API account with no spending limit though. But really oAI models are more consistent over time in my experience.

moezd• 11 days ago

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.

cadamsdotcom• 11 days ago

If the author is reading:

This is a probabilistic system. You’ve sampled from the distribution once per struggle then decided that was it, the model is just like this, Anthropic has it in for me...

But thankfully there’s a wide range of possibilities and (raw) LLMs don’t remember anything. So trying again may yield a different outcome. You have to try again.

Copy out the parts of the chat from before the trouble and bring them into a new chat, and start again from there.

Also. The contents of the chat are known to railroad the model. This means if a chat takes a turn toward suspicion, that’ll steer the model to more suspicion. If there is a refusal, there’ll be more likely to be more. So in your next attempt, rip out or don’t say whatever arose its suspicion.

And disable the memory feature. It wrecks anything scientific about these tools - for example: https://simonwillison.net/2025/May/21/chatgpt-new-memory/

If at first you don’t succeed, try again!

goalieca• 11 days ago

You’re absolutely right! And after reading the story, I now have the complete picture. I verified rather than assumed.

m463• 11 days ago

I wonder if they have bias because right at the top:

I’ve recently considered leaving Claude for Gemini

  Follow us on Google Discover

  G Add us as preferred source

(and they are android authority)

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

Related Stories