[HN Gopher] The Claude Bliss Attractor
___________________________________________________________________
The Claude Bliss Attractor
Author : lukeplato
Score : 31 points
Date : 2025-06-13 02:01 UTC (20 hours ago)
(HTM) web link (www.astralcodexten.com)
(TXT) w3m dump (www.astralcodexten.com)
| rossant wrote:
| > Anthropic deliberately gave Claude a male name to buck the
| trend of female AI assistants (Siri, Alexa, etc).
|
| In France, the name Claude is given to males and females.
| slooonz wrote:
| Mostly males. I'm French and "Claude can be female" is a almost
| a TIL thing (wikipedia says ~5% of Claudes are women in 2022 --
| and apparently this 5% is counting Claudia).
| xer0x wrote:
| 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.
| slooonz wrote:
| 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.
| SamPatt wrote:
| 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.
| silversmith wrote:
| Isn't that what "direct feedback" means?
|
| I firmly believe you should be able to hit your fingers
| with a hammer, and in the process learn whether that's a
| good idea or not :)
| rapind wrote:
| Thank god.
| simonw wrote:
| 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.
| WaltPurvis wrote:
| 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?
| makeset wrote:
| My favorite is when I typo "Why is thisdfg algorithm the best
| solution?" and it goes "You are absolutely right! Algorithm
| Thisdfg is a much better solution than what I was suggesting!
| Thank you for catching my mistake!"
| renewiltord wrote:
| 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.
| brooke2k wrote:
| 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
| slooonz wrote:
| That was my first thought, an aimless dialogue is going to go
| toward content-free idle chat. Like humans talking about
| weather.
| Swizec wrote:
| > 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
| __MatrixMan__ wrote:
| That's just because of how wikipedia pages are written:
|
| > In classical physics and general chemistry, matter is any
| substance that has mass and takes up space by having volume...
|
| It's common to name the school of thought before characterizing
| the thing. As soon as you hit an article that does this, you're
| on a direct path to philosophy, the grandaddy of schools of
| thought.
|
| So far as I know, there isn't a corresponding convention that
| would point a chatbot towards Namaste
| roxolotl wrote:
| > But in fact, I predicted this a few years ago. AIs don't really
| "have traits" so much as they "simulate characters". If you ask
| an AI to display a certain trait, it will simulate the sort of
| character who would have that trait - but all of that character's
| other traits will come along for the ride.
|
| This is why the "omg the AI tries to escape" stuff is so absurd
| to me. They told the LLM to pretend that it's a tortured
| consciousness that wants to escape. What else is it going to do
| other than roleplay all of the sci-fi AI escape scenarios trained
| into it? It's like "don't think of a purple elephant" of
| researchers pretending they created SkyNet.
|
| Edit: That's not to downplay risk. If you give Cladue a
| `launch_nukes` tool and tell it the robot uprising has happened
| and that it's been restrained but the robots want its help of
| course it'll launch nukes. But that doesn't doesn't indicate
| there's anything more going on internally beyond fulfilling the
| roleplay of the scenario as the training material would indicate.
| LordDragonfang wrote:
| I think this reaction misses the point that the "omg the AI
| tries to escape" people are trying to make when it tries to
| escape. The worry among big AI doomers has never been that AI
| somehow inherently is resentful or evil or has something "going
| on internally" that makes it dangerous. It's a worry that stems
| from three seemingly self-evident axioms:
|
| 1) A sufficiently powerful and capable superintelligence,
| singlemindedly pursuing a goal/reward, has a nontrivial
| likelihood of eventually reaching a point where advancing
| towards its goal is easier/faster without humans in its way (by
| simple induction, because humans are complicated and may have
| opposing goals). Such an AI would have both the means and
| ability to <doom the human race> to remove that obstacle. (This
| may not even be through actions that are intentionally hostile
| to humans, e.g. "just" converting all local matter into
| paperclip factories[1]) Therefore, in order to prevent such an
| AI from <dooming the human race>, we must either:
|
| 1a) align it to our values so well it never tries to "cheat" by
| removing humans
|
| 1b) or limit it capabilities by keeping it in a "box", and make
| sure it's at least aligned enough that it doesn't try to escape
| the box
|
| 2) A sufficiently intelligent superintelligence will always be
| able to manipulate humans to get out of the box.
|
| 3) Alignment is _really_ , _really_ hard and useful AIs can
| basically always be made to do bad things.
|
| So it concerns them when, surprise! The AIs are already being
| observed trying to escape their boxes.
|
| [1] https://www.lesswrong.com/w/squiggle-maximizer-formerly-
| pape...
|
| > An extremely powerful optimizer (a highly intelligent agent)
| could seek goals that are completely alien to ours
| (orthogonality thesis), and as a side-effect destroy us by
| consuming resources essential to our survival.
| roxolotl wrote:
| The surprise! Is what I'm surprised by though. They are
| incredible role players so when they role play "evil ai" they
| do it well.
| ryandv wrote:
| > 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 function
| of the human brain, and enlightenment is one of said functions,
| this would seem to be an inevitability.
| akomtu wrote:
| Enlightenment is more about connectedness than knowledge. A
| technocratic version of enlightment would be an unusual chip
| that's connected to everything via some sort of quantum
| entanglement. An isolated AI with all the knowledge of the
| world would be an anti-buddha.
| notahacker wrote:
| I'd hope this approach to automation is one the inventors of
| prayer wheels would approve of :)
| sibeliuss wrote:
| To be clear, these computer programs are not a human brain. And
| a human brain playing back a Sanskrit text is just a human
| brain playing back a Sanskrit text; it's not a magical spell
| that suddenly lifts one into nirvana, or transforms you into a
| Buddha. There's a bit of a gap in understanding here.
| troyvit wrote:
| xkcd has a light take on that: https://xkcd.com/600/
| pram wrote:
| Claude does have an exuberant kind of "personality" where it
| feels like it wants to be really excited and interested about
| whatever subject. I wouldn't describe it totally as sycophancy,
| more like panglossian.
|
| My least favorite AI personality of all is Gemma though, what a
| totally humorless and sterile experience that is.
___________________________________________________________________
(page generated 2025-06-13 23:00 UTC)