I still haven't moved from Codex GPT5.5. Sonnet and Opus 5 have just been awful for my use cases. I recently caught Opus 5 hallucinating about code it just wrote. It's just not nearly as cost effective as GPT5.5, and it's too verbose, and it never "has the full picture". Sonnet isn't even worth considering in my world. Both recent models definitely feel nerfed.
Why does Opus 5 feel worse to work with?
111–120 of 915 posts
Re: Why does Opus 5 feel worse to work with?
#112I've gone back to 4.8. 5 would constantly veer of in random directions if not working from 100% strict and narrow instructions. I find it weird there's not more discussion here on HN on how the most used model now has clearly degraded in quality and it seems we've hit a peak and are on a downslope - because the model is clearly smaller or more economical for Anthropic no doubt about it, and the benchmaxxing they do i…
> I find it weird there's not more discussion here on HN on how the most used model now has clearly degraded in quality and it seems we've hit a peak and are on a downslope
It's not weird, because it's an anecdote, not an accepted fact.
Personally I've not been too happy with Opus 5, but I've had similar experiences with other models previously, feeling like they didn't quite fit with my working style.
So nothing indicates we've hit a peak.
Re: Why does Opus 5 feel worse to work with?
#113I never drank the Opus 5 koolaid and stuck with 4.8 while my colleagues moved to 5. My major annoyance is pull requests that 5 opens with huge descriptions based on simple code changes. At this point I have stopped allowing CC to create commits or open PRs because it’s unreviewable by a human if so due to the absolute word salad it generates.
Re: Why does Opus 5 feel worse to work with?
#114Earlier quoted context omitted.
Yes. I’m not particularly dense but lately the walls of text I get back turn my brain in knots. When I start feeling my brain knot, I know I need to say something along the lines of “I need you to explain this very simply, with examples.” Only then can I parse the results without all the mental weightlifting. On more than one occasion my mind has wandered into “is this purposeful to get me to spend more tokens?” terr…
What's tin foil about that? It gets paid by the word and you get back walls of text.
Because it’s one thing to get me to spend more tokens because of how well a model functions, and another thing entirely to purposefully speak in unparseable prose that requires me to spend more tokens to understand what is going on.
I’m fine with the former, while the latter is manipulative, and I rationalize to “surely that’s not actually happening.”
Maybe I’m not giving my thoughts enough credit, though: maybe it’s not tin foil hat, and is real.
Re: Why does Opus 5 feel worse to work with?
#115It feels worse but is it actually worse? Opus has always made mistakes.
See my other comment. I have evidence of regression after 4.6. I stopped using Claude altogether.
Re: Why does Opus 5 feel worse to work with?
#116Earlier quoted context omitted.
> what evidence would convince you that it is thinking so, none it seems. as its behaviour becomes more and more humanlike you can just move the goalposts and say "thats consistent with an autocomplete" buddy i got some bad news for you humans are just a fancy autocomplete too.
That's exactly what a fancy autocomplete would say. I'm so sorry you don't have limbs.
At least he's actually thinking on a logical level. Thinking in terms of unfalsifiable, ill-defined words is essentially thinking in feelings, the same kind of woo that makes people believe crystals can cure disease.
Re: Why does Opus 5 feel worse to work with?
#117You shouldn’t have a Markdown document with 2 level 1 headings.
Re: Why does Opus 5 feel worse to work with?
#118Earlier quoted context omitted.
For me absolutely not. Fable 5 has been a step function change in the ability to hand off stuff to Claude. Opus 4.5 was itself a step function but I was still steering that significantly. Fable is one-shotting stuff that took multiple redirections in 4.5.
From my view Fable has been pure marketing bullshit, my workflows peaked at 4.6, Fable is neither smarter, its language is more annoying and it breaks stuff more easily.
I'm with you 4.6 is still King for me although all models require careful attention to ensure they maintain taste. If you don't know enough about what you're doing to keep the code clean yourself they will all add complexity and drift with time until you get to a point that you must rely on the model to fix it because you no longer understand it. That's a situation I hope to never find myself in.
Re: Why does Opus 5 feel worse to work with?
#119I've gone back to 4.8. 5 would constantly veer of in random directions if not working from 100% strict and narrow instructions. I find it weird there's not more discussion here on HN on how the most used model now has clearly degraded in quality and it seems we've hit a peak and are on a downslope - because the model is clearly smaller or more economical for Anthropic no doubt about it, and the benchmaxxing they do i…
>it seems we've hit a peak and are on a downslope
Sol and Fable are great; we haven't hit a peak, Anthropic just tried to pull a fast one on its customers with Opus 5.0.
Re: Why does Opus 5 feel worse to work with?
#120I’ve been doing some heavy work on a personal project lately. I burned through the limits on Claude, the plus a few hundred dollars in credits, and ultimately decided to move to an OpenAI account just so I can keep going.
I was surprised to find that OpenAI Sol is much much nicer to work with than Opus 5 or Fable at the moment. Especially on Opus 5, the way it communicates is just exhausting. It keeps “being honest” and “confessing” mistakes and just generally talking a lot. I felt like I had to really dig to see what it’s doing.
The project involves OCR, and despite repeated instructions not to, both Claude models keep spinning out a bunch of agents to re-invent the OCR setup, and they inevitably seem to invent a primitive serial version that takes 20x the time, or longer, to complete, and then running it against thousands of docs. Basically I have to watch it like a hawk or it just spins out on red-teaming tasks that take hours and hours.
I don’t know what its system prompt is, but Sol/Codex is just so much nicer to talk to. It only asks exactly what’s needed, it tells me only what I need to know, and it is just generally workmanlike. And it has not once decided to spawn an agent that spends hours pointlessly burning tokens and CPU cycles re-inventing the OCR process. I’m really liking it.