Could it be related to the anagram it's planting?
If it's wasting inference attempting to also fit in some anagram, it would make sense why answers are so dogmatic.
Why does Opus 5 feel worse to work with?
551–560 of 915 posts
Re: Why does Opus 5 feel worse to work with?
#552Earlier quoted context omitted.
As a native speaker, I have to ask it to rephrase 5-10 times a day. Sometimes I actually get mad and I tell it “I can’t answer that because I don’t know what the fuck load-bearing indirection means”. I’ve gotten so frustrated that I’ve ended a session and started over.
As a Polish speaker I communicate with Claude using my native language and it does the same things. Most annoying and slowing down things are: - acronyms and shortcuts - it makes it's own and start using it without introduction - exotic names of variables or functions - it uses them as examples or analogies, but when I ask what they mean and where are they from it gives me answer that it came from C language or some…
It defines and introduces a lot of concepts/acronyms in the thinking blocks which we normally don't read.
Re: Why does Opus 5 feel worse to work with?
#553Earlier quoted context omitted.
Oh, that's interesting - because that's absolutely what's happening in my experience. If I look at the thinking (which seems to have become unavailable in Opus 5 a lot of the time, but was present - and often useful - in 4.8/4.6) you're right - it's having the discussion with itself, and seems unable to distinguish that discussion from discussions with me. BUT it also seems to be related to the length of the chat - t…
Interesting. So if the LLM is having a discussion with itself, am I paying for the tokens it uses for that?
Yes, those tokens cost money|credits|whatever too.
Re: Why does Opus 5 feel worse to work with?
#554I have utterly abandoned Anthropic as a customer because of these writing style / behavior changes. It is insufferably bad, and it is impacting code quality.
Switched over to Codex 5.6, and dude, we are BACK.
Re: Why does Opus 5 feel worse to work with?
#555Earlier quoted context omitted.
The second bullet point, down to the comma in the middle of the sentence, is what has been driving me absolutely batty of late. It's a surefire tell that I cannot seem to beat out of my outputs. It CONSTANTLY does it, even when you say not to. Between that and the insistence on "this, not that" structure makes me want to install the caveman skill and use it even for non-code workflows.
This load bearing concern belt and braces.
Provenance
Re: Why does Opus 5 feel worse to work with?
#556Earlier quoted context omitted.
"hunk" is git terminology. When you use `git add --patch` (which you probably should, if you use `git add` at all) you get prompted "Stage this hunk [y,n,q,a,d,e,?]?" which is self-explanatory (?) and the hunk refers to whatever change git is highlighting at the moment.
I wondered how far back the usage of that term went. I was familiar with it in patch, so I did a little digging and found it in the v1.3 (1985!) source by Larry Wall: https://groups.google.com/g/mod.sources/c/xSQM63e39YY
You need to go back a few more hundreds of years, hunk is an old term that just means "small piece of something larger".
It has been in common usage in computing since long before 1985 .. for a really interesting and obscure way hunk has been used:
Re: Why does Opus 5 feel worse to work with?
#557The single biggest annoyance with Opus 5 is that it writes too elliptically. Sentences that orbit a point, then jump to it like it's a revealed insight. Unnecessarily abstract phraseology. Constantly using inanimate nouns as the subjects in sentences in order to unlock variety in verb choice, especially when it helps construct a sentence where the real action can 'land' like a surprise at the end. It is definitely mo…
Everything that claude writes fits into the same aesthetic structure. The aesthetic is that of an expert slowly revealing an insight to the user. The actual content doesn't matter. - "Introduction that rephrases your prompt." - "3 paragraphs, with one section of bullet points" - "The Twist" - "The Bottom Line" It's really obvious once you see it. Every single prompt, from a quantum physics question to a mundane obser…
anyone know how they would train a model to have this proclivity ?
Re: Why does Opus 5 feel worse to work with?
#558Earlier quoted context omitted.
Sure. I should have been more precise about what is 'real intelligence' here. What I mean is that blindsight's scramblers are aliens that cannot share human values. Their structure is completely different to ours, their qualia (or whether they even have it) is impossible for us to understand. In short, they do not have a soul. When Claude does this "slowly revealing a dramatic insight" thing that it does, it does tha…
I think I understand what you are trying to convey but I fear you've made the same mistake again, this time with "soul" instead of "intelligence." I think what you are getting at is that they are deterministic automata. They are machines. We have introduced randomness to add variation but it is an artificial randomness that simply perturbs the path traversed. When we choose words it isn't because of a token distribut…
I agree, and yet it is reasonable to ask if these notions of "context" (sorry!) - namely feelings, external world, body, senses, etc - are somehow distinct from an LLM's notions of context. Today they certainly capture different things, but given the right representations, why couldn't these human notions also be captured as "context"?
The idea of memory does not seem to resolve this: if you allow the machine to "compact" its context, then you've given it a system which is analogous to our own evolving state. (Though this is undoubtedly still less expressive and meaningful than the one we have evolved as humans.)
One idea I've wondered about is our human capacity to induce subsequent mental states: I can effectively decide how I want to feel and take actions to create that feeling. It's not clear whether models exhibit any degree of privileged introspection into their own states. Is this important? I don't know. (Non)determinism also does not seem to resolve it; it's my understanding that there are plenty of philosophers and researchers who think that human behavior is deterministic, or that the question of determinism does not matter.
Re: Why does Opus 5 feel worse to work with?
#559Earlier quoted context omitted.
Everything that claude writes fits into the same aesthetic structure. The aesthetic is that of an expert slowly revealing an insight to the user. The actual content doesn't matter. - "Introduction that rephrases your prompt." - "3 paragraphs, with one section of bullet points" - "The Twist" - "The Bottom Line" It's really obvious once you see it. Every single prompt, from a quantum physics question to a mundane obser…
Perhaps this is related to their new "invisible watermark" concept which would probably require rather contrived language patterns to make possible.
I think opus was released before they included it on model. Its hard to say, but from what Ive read it doesn’t seem like it would have that drastic of an effect.
I had the same thought though.
Re: Why does Opus 5 feel worse to work with?
#560Earlier quoted context omitted.
I'll say everything indicates we've hit or are near peak for the masses at least (unless you start paying 50x more) but to each his own. 4.6 was best for us and right now yeah OpenAI and others are edging forward, but slower while prices are increasing industry wide as much as 20x, time to completion is increasing wildly and i'm sure they'll do the same over at OpenAI as their compute constraints also start to take a…
Literally nothing indicates we've hit a peak, but I guess I'm discussing this with someone who thinks every iteration since Opus 4.6 had zero ROI so there's probably not much common ground here.
Four years ago LLMs were sometimes amazing, sometimes wrong, sometimes a huge time sink when it's almost there and you try to herd the tokens but it's like herding cats.
Just today I had the exact same experience. Every single testimonial is the same as I described above, just emphasizing a different bit to defend or attack LLMs or to make a case for nuance.
The two differences have been: (1) the 1.5 trillion dollar data center build out (2) everyone and their cats now has an opinion on "AI" and data centers. Software is not super amazing, nor are new useful features coming out super fast - It's about the same as 4 years ago plus 4 years of average long term progress as we've seen since 1990s,