Hacker News new | past | comments | ask | show | jobs | submit
rafram | on: Listen and read USA nuclear forces Emergency Action Messages, heard on 11175 kHz
> Mostly static. The net is quiet until it isn't.

> Preformatted is what you can hear: the same shape every time.

> hearing it is all anyone outside the force can do.

> The day has a shape.

I would recommend switching to a newer Claude model.

cowlby | parent | next
Everyone worried about AI detectors and here I am thinking I can spot Claudenglish in a sentence or two.
Natsu | root | parent | next
> Claudenglish

I prefer to call it Cloddish, myself.

fosco | root | parent
I initially thought Claude was a reference to clod from warbreaker and your spelling made me think of it again, for those that read warbreaker they might understand his description is darn close to what Claude is, but alas I believe I was deftly wrong
Avamander | parent | next
All Anthropic models write like that since Opus 4.8. Opus 4.8 was still tolerable.

Unfortunately only Gemini models can write text that isn't vomit-inducing.

wyager | root | parent | next
Opus 5.5 doesn't write like this anymore
0c3ca83 | root | parent | next
It has different awfulness.
unshavedyak | root | parent
I don't find it anywhere remotely as bad. I'm not saying it's good, but jesus.. i was ready to leave anthropic lol.
wycy | root | parent | next
I did leave. Opus was just pumping out so much verbosity and wasting tokens on all that nonsense, plus I was bitter that Anthropic gates the best model behind usage credits, so I switched to ChatGPT just as Astra came out.

Then Opus 5.5 came out and I switched back to Ant after 1 month of OAI. Opus 5.5 fixed all the previous Opus 5 problems, and while Fable still requires credits, there's hardly any need to use it since Opus 5.5 is so good and so token efficient.

r_lee | root | parent
I literally left. 5.5 is so much better. I don't know how they managed to mess up 5 so bad
SJMG | root | parent
5 I couldn't bear. It was terrible AND verbose
Avamander | root | parent | next
It's less obvious but it's still there. For starters it loves to anthropomorphize everything, it excessively uses verbs that shouldn't be used with inanimate objects and concepts. Not the only issue though.
alexgoodhart | root | parent
Fable 5.1 does. Wretched
qlte | root | parent
Every other comment on LLM news in 2023:

"this is the worst it will ever be"

bragr | parent | next
>Mostly static. The net is quiet until it isn't.

Having tuned in myself with a SDR, it isn't that quiet. There's pretty steady rate of messages.

jpablo | parent | next
Which newer Claude model doesn’t do that? Fable 5.1 still writes like that for me. I have to fight against it to write proper software labels, or (the horror!) rewrite things manually.
kccqzy | root | parent | next
IMO Opus 5.5 has surpassed Fable 5.1 in terms of both writing style and actual capability. Like I would give the same task to both models and Opus 5.5 consistently produces better results and explains itself better than Fable 5.1.
D13Fd | root | parent
That's what I'm finding too. Opus 5.5 feels both consistently better than Fable and faster.
rafram | root | parent | next
Fable is inappropriate for the vast majority of tasks (yes, including yours!), and it is quite obnoxious. Opus 5.5 writes concisely and almost sounds like a human.
temac | root | parent | next
IMO the default style of Opus 5.5 is still terrible but it is way better than 5.0. If you tell its styling is horrendous it usually rewrites in an actually quite good form.
Avamander | root | parent | next
I recommend comparing what it rewrites to something that Gemini models output. I think there's still a lot that Anthropic could improve.
KerrAvon | root | parent | next
This. You can prompt Opus 5.5 into writing well.
perching_aix | root | parent
i tend to run a pass of sol 6.1 at its output, cleans up the language well and finds defects opus missed
lukan | root | parent
Ok I bite, for what concrete tasks do you get better results with Opus than with Fable?

Because if true, I see no reason to spend that extra money, but for me Fable clearly outperformed Opus on complex tasks. (Including giving the same task and compare results)

lostNFound | root | parent
I let Claude do my job pretty much (with company approval) managing the entire stack of an app.

8hs of “prompt engineering” daily for a year or so.

I find Fable immensely better than 5.5 in their capabilities and results. Opus makes mistakes, a lot and big. Both on High Effort.

I just run Fable for literally everything including daily random use. Never run out of tokens on the 100 plan.

timcobb | root | parent
Opus 5.5 is the only one that doesn't do ths, _as much_, it would still to the "it's ___ until it isn't" all day though. Can't wait for that to go away too.
| parent | next
{"deleted":true,"id":50225752,"parent":50224988,"time":1792878897,"type":"comment"}
thecopy | parent | next
I have a small ChatGPT subscription and a skill i run pre-commit post-Claude that goes through every file and rewrites all english sentences, removes comments and replaces dense terms in variable and function names. It usually reduces comments by ~80%
medellin | parent | next
That would require a brain. Claude hasn’t told them to upgrade yet.
| parent | next
{"deleted":true,"id":50228195,"parent":50224988,"time":1792900975,"type":"comment"}
0c3ca83 | parent
Welcome to hacker news. All bots all the time.