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

The Claude Bliss Attractor

astralcodexten.com

Post reply on HN
Print view View original

21–30 of 91 posts

Re: The Claude Bliss Attractor

#21

Post by Swizec »

slooonz wrote: post #8
brooke2k wrote: post #5

it seems more likely to me that it's for the same reason that clicking the first link on wikipedia iteratively will almost always lead you to the page on Philosophy since their conversation has no goal whatsoever it will generalize and generalize until it's as abstract and meaningless as possible

That was my first thought, an aimless dialogue is going to go toward content-free idle chat. Like humans talking about weather.

> Like humans talking about weather.

As someone who was always fascinated by weather, I dislike this characterization. You can learn so much about someone’s background and childhood by what they say about the weather.

I think the only people who think weather is boring are people who have never lived more than 20 miles away from their place of birth. And even then anyone with even a bit of outdoorsiness (hikes, running, gardening, construction, racing, farming, cycling, etc) will have an interest in weather and weather patterns.

Hell, the first thing you usually ask when traveling is “What’s the weather gonna be like?”. How else would you pack

Re: The Claude Bliss Attractor

#22

Post by WaltPurvis »

simonw wrote: post #14
slooonz wrote: post #7

Earlier quoted context omitted.

They failed hard with Claude 4 IMO. I just can't have any feedback other than "What a fascinating insight" followed by a reformulation (and, to be generous, an exploration) of what I said, even when Opus 3 has no trouble finding limitations. By comparison o3 is brutally honest (I regularly flatly get answers starting with "No, that’s wrong") and it’s awesome.

Thanks for this, I just tried the same "give me feedback on this text" prompt against both o3 and Claude 4 and o3 was indeed much more useful and much less sycophantic.

Do knowledge cutoff dates matter anymore? The cutoff for o3 was 12 months ago, while the cutoff for Claude 4 was five months ago. I use these models mostly for development (Swift, SwiftUI, and Flutter), and these frameworks are constantly evolving. But with the ability to pull in up-to-date docs and other context, is the knowledge cutoff date still any kind of relevant factor?

Re: The Claude Bliss Attractor

#24

Post by troyvit »

ryandv wrote: post #12

> None of this answers a related question - when Claude claims to feel spiritual bliss, does it actually feel this? Given that we are already past the event horizon and nearing a technological singularity, it should merely be a matter of time until we can literally manufacture infinite Buddhas by training them on an adequately sized corpus of Sanskrit texts. After all, if AGIs/ASIs are capable of performing every fun…

xkcd has a light take on that: https://xkcd.com/600/

Re: The Claude Bliss Attractor

#25

Post by rapind »

SamPatt wrote: post #9
slooonz wrote: post #7

Earlier quoted context omitted.

They failed hard with Claude 4 IMO. I just can't have any feedback other than "What a fascinating insight" followed by a reformulation (and, to be generous, an exploration) of what I said, even when Opus 3 has no trouble finding limitations. By comparison o3 is brutally honest (I regularly flatly get answers starting with "No, that’s wrong") and it’s awesome.

Agreed that o3 can be brutally honest. If you ask it for direct feedback, even on personal topics, it will make observations that, if a person made them, would be borderline rude.

Thank god.

Re: The Claude Bliss Attractor

#26

Post by renewiltord »

xer0x wrote: post #4

Claude's increasing euphoria as a conversation goes can mislead me. I'll be exploring trade offs, and I'll introduce some novel ideas. Claude will use such enthusiasm that it will convince me that we're onto something. I'll be excited, and feed the idea back to a new conversation with Claude. It'll remind me that the idea makes risky trade offs, and would be better solved by with a simple solution. Try it out.

LLM sycophancy is a really annoying tool, but one must imagine that most humans get a lot of pleasure from it. This is probably the optimization function that led to Google being useless to us: the rest of humanity is a lot more worthwhile to Google and they all want the other thing. The Tyranny of the Majority, if you will.

The LLM anti-sycophancy rules also break down over time, with the LLM becoming curt while simultaneously deciding that you are a God of All Thoughts.

Re: The Claude Bliss Attractor

#28

Post by SatvikBeri »

xer0x wrote: post #4

Claude's increasing euphoria as a conversation goes can mislead me. I'll be exploring trade offs, and I'll introduce some novel ideas. Claude will use such enthusiasm that it will convince me that we're onto something. I'll be excited, and feed the idea back to a new conversation with Claude. It'll remind me that the idea makes risky trade offs, and would be better solved by with a simple solution. Try it out.

I put this in my system prompt: "Never compliment me. Critique my ideas, ask clarifying questions, and offer better alternatives or funny insults" and it works quite well. It has frequently told me that I'm wrong, or asked what I'm actually trying to do and offered better alternatives.

Re: The Claude Bliss Attractor

#29

Post by XenophileJKO »

xer0x wrote: post #4

Claude's increasing euphoria as a conversation goes can mislead me. I'll be exploring trade offs, and I'll introduce some novel ideas. Claude will use such enthusiasm that it will convince me that we're onto something. I'll be excited, and feed the idea back to a new conversation with Claude. It'll remind me that the idea makes risky trade offs, and would be better solved by with a simple solution. Try it out.

Just ask Claude to be "critical" and it is brutally critical.. but also a bit nihilistic. So you kind of have to temper it a little.

Re: The Claude Bliss Attractor

#30

Post by moritzwarhier »

WaltPurvis wrote: post #22
simonw wrote: post #14

Earlier quoted context omitted.

Thanks for this, I just tried the same "give me feedback on this text" prompt against both o3 and Claude 4 and o3 was indeed much more useful and much less sycophantic.

Do knowledge cutoff dates matter anymore? The cutoff for o3 was 12 months ago, while the cutoff for Claude 4 was five months ago. I use these models mostly for development (Swift, SwiftUI, and Flutter), and these frameworks are constantly evolving. But with the ability to pull in up-to-date docs and other context, is the knowledge cutoff date still any kind of relevant factor?

I understood from the ancestor comments that they are specifically talking about aspects of answer quality that are very unlikely to be related to the training cut-off date.

Unless you're talking about AI-generated training data, maybe.

Post reply on HN