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

Claude Sonnet 4.5

anthropic.com

Post reply on HN
Print view View original

511–520 of 819 posts

Re: Claude Sonnet 4.5

#511

Post by dang »

emp17344 wrote: post #172
senordevnyc wrote: post #125

Earlier quoted context omitted.

HN is such a negative and cynical place these days that it's just not worth it. I just don't have the patience to hear yet another anti-AI rant, or have someone who is ideologically opposed to AI nitpick its output. Like you, I've found AI to be a huge help for my work, and I'm happy to keep outcompeting the people who are too stubborn to approach it with an open mind.

[flagged]

"Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith."

https://news.ycombinator.com/newsguidelines.html

Re: Claude Sonnet 4.5

#513

Post by gejose »

Implicated wrote: post #329
SirMaster wrote: post #316

Earlier quoted context omitted.

But isn't the end goal to be able to get useful results without so much prompting? I mean in the movies for example, advanced AI assistants do amazing things with very little prompting. Seems like that's what people want. To me, the fact that so many people basically say "you are prompting it wrong" is knock against the tech and the model. If people want to say that these systems are so smart at what they can do, the…

> But isn't the end goal to be able to get useful results without so much prompting? See below about context. > I mean in the movies for example, advanced AI assistants do amazing things with very little prompting. Seems like that's what people want. Movies != real life > To me, the fact that so many people basically say "you are prompting it wrong" is knock against the tech and the model. If people want to say that…

> But you're comparing the LLMs to humans

Didn't the parent comment compare Sonnet vs Codex with GPT5?

Re: Claude Sonnet 4.5

#515

Post by deevus »

simonw wrote: post #204

I had access to a preview over the weekend, I published some notes here: https://simonwillison.net/2025/Sep/29/claude-sonnet-4-5/ It's very good - I think probably a tiny bit better than GPT-5-Codex, based on vibes more than a comprehensive comparison (there are plenty of benchmarks out there that attempt to be more methodical than vibes). It particularly shines when you try it on https://claude.ai/ using its brand n…

I was worried for a minute that the implementation wasn't production ready. Thankfully, Claude mentioned it right at the end.

Re: Claude Sonnet 4.5

#516

Post by ionwake »

atonse wrote: post #411
inopinatus wrote: post #391

Earlier quoted context omitted.

I won’t be satisfied until I get a Linus Torvalds mode. “Your idea is shit because you are so fucking stupid” “Please stop talking, it hurts my GPUs thinking down to your level” “I may seem evil but at least I’m not incompetent”

Why is this getting downvoted? It was hilarious! I actually added a fun thing to my user-wide CLAUDE.md, basically saying that it should come up with a funny insult every time I come up with an idea that wasn't technically sound (I got the prompt from someone else). It seems to be disobeying me, because I refuse to believe that I don't have bad ideas. Or some other prompt is overriding it.

This is brilliant! Can you give me some pointers?

Ie : if I make a request that seems dumb tell me custom instruction?

Re: Claude Sonnet 4.5

#517

Post by emmelaich »

inopinatus wrote: post #391
siva7 wrote: post #380

Does 4.5 still answer everything with "You're absolutely right!" or is it now able to communicate like a real programmer?

I won’t be satisfied until I get a Linus Torvalds mode. “Your idea is shit because you are so fucking stupid” “Please stop talking, it hurts my GPUs thinking down to your level” “I may seem evil but at least I’m not incompetent”

I laughed. But .. Linus calls ideas and acts stupid, not people.

Re: Claude Sonnet 4.5

#518

Post by martin-t »

Aflynn50 wrote: post #374

When I see how much the latest models are capable of it makes me feel depressed. As well as potentially ruining my career in the next few years, its turning all the minutiae and specifics of writing clean code, that I've worked hard to learn over the past years, into irrelivent details. All the specifics I thought were so important are just implementation details of the prompt. Maybe I've got a fairly backwards view…

And now wait till you realize it's all built on stolen code written by people like you and me.

GOFAI failed because paying intelligent/competent/capable people enough for their time to implement intelligence by writing all the necessary rules and algorithms was uneconomical.

GenAI solved it by repurposing already performed work, deriving the rules ("weights") from it automatically, thus massively increasing the value of that work, without giving any extra compensation to the workers. Same with art, translations and anything else which can be fed into RL.

Re: Claude Sonnet 4.5

#519

Post by j45 »

A question I have for anyone is -- has Claude Max returned to or repaired the response quality and service issues between the usage limits and performance of the model for coding and non-coding tasks?

Anecdata is welcome as it seems like it's the only thing available sometimes.

Re: Claude Sonnet 4.5

#520

Post by transcriptase »

fnordsensei wrote: post #436
baobabKoodaa wrote: post #366

Earlier quoted context omitted.

Hmmh. I believe your explanation, but I don't think that's the full story. It's also a sycophancy mechanism to maximize engagement from real users and reward hack AI labelers.

That doesn’t seem plausible to me. Not that LLMs can’t be sycophantic, but I don’t think this phrase in particular is part of it. It’s a canned phrase in a place where an LLM could be much more creative to much greater efficacy.

I think there’s something to it.

Part of me thinks that when they do their “which of these responses do you prefer” A/B test on users… whereas perhaps many on HN would try to judge the level of technical detail, complexity, usefulness… I’m inclined to believe the midwit population at large would be inclined to choose the option where the magic AI supercomputer reaffirms and praises the wisdom of whatever they say, no matter how stupid or wrong it is.

Post reply on HN