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

291–300 of 819 posts

Re: Claude Sonnet 4.5

#291

Post by rvz »

emp17344 wrote: post #196
stavros wrote: post #183

Earlier quoted context omitted.

Well, here's an even more insane claim: I'm infinity times more productive, as I just wouldn't even start projects without the LLM to sidestep my ADHD. Then, when the LLM invariably fucks up, I step in and finish things myself! Here are a few projects that I made these past few months that wouldn't have been possible without LLMs: * https://github.com/skorokithakis/dracula - A simple blood test viewer. * https://www.…

> I'm infinity times more productive, as I just wouldn't even start projects without the LLM to sidestep my ADHD. 1 is not infinitely greater than 0.

Also, not invented here syndrome (NIH) is cool again.

Given that most of the 'vibe-coded' projects that I have seen that are worse versions of software that have been tested and stand the test of time.

Re: Claude Sonnet 4.5

#292

Post by Snuggly73 »

simonw wrote: post #252
magicalist wrote: post #232

Earlier quoted context omitted.

> I told it to Give me a zip file of everything you have done so far—you can explore the contents of the file it made me in this Gist. For those who don't have time to dig into the gist, did it work and do a good job? I assume yes to at least nominally working or you would have mentioned that, but any other thoughts on the solution it produced?

I was impressed. Integrating it into my project would require me to spend a bunch more time reviewing it, but it did a better job than I was expecting. The tests it wrote were a particularly useful exploration of the problem space: https://gist.github.com/simonw/f9d0f870e8d1af399a7f366a7f87b...

Ignoring the tests, the first change was adding a single parent id column and the second "more complex" refactoring added few more hash columns to the table (after you've specified that you wanted them, i.e. not an open-ended question)

Its a very impressive model, but I think we have different views on what is complex.

Re: Claude Sonnet 4.5

#293

Post by lexarflash8g »

Just tested this on a rather simple issue. Basically it falls into rabbits holes just like the other models and tries to brute force fixes through overengineering through trial and error. It also says "your job should now pass" maybe after 10 prompts of roughly doing the same thing stuck in a thought loop.

A GH actions pipeline was failing due to a CI job not having any source code files -- error was "No build system detected". Using Cursor agent with Sonnet 4.5, it would try to put dummy .JSON files and set parameters in the workflow YAML file to false, and even set parameters that don't exist. Simple solution was to just override the logic in the step to "Hello world" to get the job to pass.

I don't understand why the models are so bad with simple thinking outside the box solutions? Its like a 170 iq savant who can't even ride public transporation.

Re: Claude Sonnet 4.5

#294

Post by FlyingSnake »

stavros wrote: post #183
Mathiciann wrote: post #156

Earlier quoted context omitted.

I am almost convinced your comment is parody but I am not entirely sure. You want proof for critical/supportive criticism? Then almost in the same sentence you make an insane claim without backing this up by any evidence.

Well, here's an even more insane claim: I'm infinity times more productive, as I just wouldn't even start projects without the LLM to sidestep my ADHD. Then, when the LLM invariably fucks up, I step in and finish things myself! Here are a few projects that I made these past few months that wouldn't have been possible without LLMs: * https://github.com/skorokithakis/dracula - A simple blood test viewer. * https://www.…

> dang can we please get a bit better Markdown support?

Great use case for an LLM to make these changes as HN is open source. It’ll also tell us if LLMs can go beyond JS slop.

Re: Claude Sonnet 4.5

#295

Post by beydogan »

peterdstallion wrote: post #157

I am a paying subscriber to Gemini, Claude and OpenAI. I don't know if it's me, but over the last few weeks I've got to the conclusion ChatGPT is very strongly leading the race. Every answer it gives me is better - it's more concise and more informative. I look forward to testing this further, but out of the few runs I just did after reading about this - it isn't looking much better

Me too. I have Claude Max and 2 ChatGpt accounts for Codex.

I was a huge claude fan but recently find myself using only codex. When it gets stuck, I try Claude for some simple tasks, sometimes ask same questions in parallel, Claude Code with Opus performs really bad comparing to codex.

Re: Claude Sonnet 4.5

#296

Post by iagooar »

Implicated wrote: post #274
iagooar wrote: post #258

Anecdotal evidence. I have a fairly large web application with ~200k LoC. Gave the same prompt to Sonnet 4.5 (Claude Code) and GPT-5-Codex (Codex CLI). "implement a fuzzy search for conversations and reports either when selecting "Go to Conversation" or "Go to Report" and typing the title or when the user types in the title in the main input field, and none of the standard elements match, a search starts with a 2s de…

I'm not trying to be offensive here, feel the need to indicate that. But that prompt leads me to believe that you're going to get rather 'random' results due to leaving SO much room for interpretation. Also, in my experience, punctuation is important - particularly for pacing and grouping of logical 'parts' of a task and your prompt reads like a run on sentence. Making a lot of assumptions here - but I bet if I were…

I think that is an interesting observation and I generally agree.

Your point about prompting quality is very valid and for larger features I always use PRDs that are 5-20x the prompt.

The thing is my "experiment" is one that represents a fairly common use case: this feature is actually pretty small and embeds into an pre-existing UI structure - in a larger codebase.

GPT-5-Codex allows me to write a pretty quick & dirty prompt, yet still get VERY good results. It not only works on first try, Codex is reliably better at understanding the context and doing the things that are common and best practice in professional SWE projects.

If I want to get something comparable out of Claude, I would have to spend at least 20mins preparing the prompt. If not more.

Re: Claude Sonnet 4.5

#297

Post by neuronexmachina »

schmorptron wrote: post #32

Oh wow, a lot of focus on code from the big labs recently. In hindsight it makes sense that the domain the people building it know best is the one getting the most attention, and it's also the one the models have seen the most undeniable usefulness in so far. Though personally, the unpredictability of the future where all of this goes is a bit unsettling at the same time...

I think coding is also the area where companies are most likely to buy large team licenses.

Re: Claude Sonnet 4.5

#298

Post by furyofantares »

Kuinox wrote: post #106
furyofantares wrote: post #101

Earlier quoted context omitted.

It's more for fun than as a benchmark.

It also measure something llms are good probably due to cheating.

I wouldn't say any LLMs are good at it. But it doesn't really matter, it's not a serious thing. It's the equivalent of "hello world" - or whatever your personal "hello world" is - whenever you get your hands on a new language.

Re: Claude Sonnet 4.5

#299

Post by cloverich »

Mathiciann wrote: post #156
cloverich wrote: post #108

Please y'all, when you list supportive or critical complaints based on your actual work, include some specifics of the task and prompt. Like actual prompt, actual bugs, actual feature, etc. I've had great success with both ChatGPT and Claude for years, am around 3x sustained output increase in my professional work, and kicking off and finishing new side projects / features that I used to simply not ever finish. BUT t…

I am almost convinced your comment is parody but I am not entirely sure. You want proof for critical/supportive criticism? Then almost in the same sentence you make an insane claim without backing this up by any evidence.

> You want proof for critical/supportive criticism? Then almost in the same sentence you make an insane claim without backing this up by any evidence.

Nearly every critical reply to my comment bases that criticism on the lack of examples and details I included for my claim which is the very thing I am suggesting we do (i.e. they are, ironically, agreeing with me?). I am sorry I thought that intentional bit of irony would help make the point rather than derail the request.

Re: Claude Sonnet 4.5

#300

Post by jama211 »

emp17344 wrote: post #236
sebastiennight wrote: post #228

Earlier quoted context omitted.

It... literally is? Or otherwise, can you share what you think the ratio is?

No, 1 is 1 more than 0. There’s a certain sense in which you could say that 1 is infinitely greater than 0, but only in an abstract, unquantifiable way. In this case, it doesn’t make sense to say you’re “infinitely more productive” because you’re producing something rather than nothing.

I just read it as a turn of phrase that says exactly that, that it means they produce something rather than nothing.
Post reply on HN