I used to love Claude, but the latest models are slowly ruining it • Hacker News Board

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

#61

Post by JumpCrisscross » Sun, Jul 12, 2026, 4:10 AM UTC

gunalx wrote: post #46

BlueGh0st wrote: post #35

Earlier quoted context omitted.

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.

> Møre...konsistent

Wat.

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

#62

Post by vkou » Sun, Jul 12, 2026, 5:04 AM UTC

skybrian wrote: post #27

vkou wrote: post #22

Earlier quoted context omitted.

> There's nothing dystopian about that. It'll be dystopian when that'll become your only source of information, and we're working on getting there. If you want to be horrified, look at what students (in school and post-secondary) are doing these days. It's insane to offload your thinking and knowledge to a machine owned by other people, but you have to if you want to keep up with the rat race.

It’s probably a good idea to know how to use AI tools, but they certainly don’t have to be your only source of information.

More and more people producing information are moving more and more of their work to the LLM, and are strangling the ones who aren't.

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

#63

Post by pseudohadamard » Sun, Jul 12, 2026, 9:14 AM UTC

visarga wrote: post #9

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?"

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.