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

501–510 of 819 posts

Re: Claude Sonnet 4.5

#501

Post by paul_manias »

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…

Same experience here. In the last week I've successfully managed to build a complete C++20 XPath 1.0 parser with Codex, and am now onto supporting XPath 2.0. Codex has been nailing it time and again - the only caveat is that I have to use their cloud version as local execution is buggy.

Sonnet on the other hand gets tripped up constantly due to the complexity. I'm not seeing the improvement I was hoping for with 4.5, and it's just given up on attempting to implement support for date-time functionality. Codex has nailed the same task, yet Anthropic claim OpenAI have the inferior product?

I'm pretty sad about this as I'm gunning for Anthropic and would have loved to see them at least match Codex with this new release. If OpenAI stays on this course then Claude Code is toast without an important breakthrough. It doesn't help that they're also the more expensive product and have service quality issues pushing people to quit the platform.

Re: Claude Sonnet 4.5

#502

Post by vunderba »

la_fayette wrote: post #217
rudedogg wrote: post #70

I just ran this through a simple change I’ve asked Sonnet 4 and Opus 4.1, and it fails too. It’s a simple substitution request where I provide a Lint error that suggests the correct change. All the models fail. I could ask someone with no development experience to do this change and they could. I worry everyone is chasing benchmarks to the detriment of general performance. Or the next token weight for the incorrect c…

At this point it would be an interesting idea, to collect examples, in a form of a community database, were LLMs miserably fail. I have examples myself...

Any such examples are often "closely guarded secrets" to prevent them from being benchmaxxed and gamed - which is absolutely what would happen if you consolidated them in a publicly available centralized repository.

Re: Claude Sonnet 4.5

#503

Post by iagooar »

epolanski wrote: post #414
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…

There's few issues with posts like yours: 1. Different LLMs require different prompts and information 2. They ignore LLMs non determinism, you should run the experiment several times

Oh and I agree so much. I just shared a quick first observation in a real-world testing scenario (BTW re-ran Sonnet 4.5 with the same prompt, not much changed). I just keep seeing how LLM providers keep optimizing for benchmarks, but then I cannot reproduce their results in my projects.

I will keep trying, because Claude 4 generally is a very strong line of models. Anthropic has been on the AI coding throne for months before OpenAI with GPT-5 and Codex CLI (and now GPT-5-Codex) has dethroned them.

And sure I do want to keep them competing to make each other even better.

Re: Claude Sonnet 4.5

#504

Post by xenobeb »

senordevnyc wrote: post #125
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…

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.

To me, it really depends if the post is a well reasoned criticism with something unique to add to the conversation or the standard, completely pointless, anti-AI rant that I have already read a 1000 times.

Re: Claude Sonnet 4.5

#505

Post by holtkam2 »

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…

Trust me, these “vibe coding” tools don’t speed up productivity much in the real world. At the end of the day these systems need to be maintained by humans and humans are the ones held accountable when stuff breaks. That means humans need to understand how the systems (code, infrastructure, etc) work. You can automate the code, even some decisionmaking about how the program should be organized, but you can’t automate the process of having a human develop their mental model of how & why the system works. That was always the bottleneck and still is to this day.

When everyone else has given up on software dev as a career path, you’ll be one of the few who the CEO can call upon to explain why X or Y broke, and fix it. That will make you insanely valuable.

Re: Claude Sonnet 4.5

#506

Post by sixothree »

CuriouslyC wrote: post #376
sixothree wrote: post #351

Earlier quoted context omitted.

You definitely need some context management like Serena.

Even with Serena and detailed plans crafted by Gemini that lay out file-by-file changes, Claude will sometimes go off the rails. Claude is very task-completion driven, and it's willing to relax the constraints of the task to complete in the face of even slight adversity. I can't tell you the number of times I've had Claude try to install a python computational library, get an error, then either try to hand-roll the a…

I have to agree with pretty much all of this. Specifically, I've had Claude fail at creating a database migration using tooling then go on to create the migration manually. My only reaction to anyone doing this, be it human or computer, is "You did WHAT!?".

Re: Claude Sonnet 4.5

#507

Post by dinobones »

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…

Are you paying for ChatGPT pro? Does that include codex CLI usage?

Claude Code on max plan is why I use Sonnet/Opus, but if ChatGPT pro includes codex usage I may switch.

Re: Claude Sonnet 4.5

#508

Post by dang »

catigula wrote: post #140
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 don't cross into personal attack, regardless of how wrong someone is or you feel they are.

Also, please stop posting flamebait to HN generally. It's not what this site is for, and destroys what it is for.

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

Re: Claude Sonnet 4.5

#509

Post by simonw »

lxgr wrote: post #488
simonw wrote: post #377

Earlier quoted context omitted.

They need to benchmaxxx a whole lot harder, the illustrations still all universally suck!

I fully expect a model to output a SVG made up of 1000x1000 rectangles (i.e. pixels) representing a raster image of a beautifully hand-drawn pelican riding a bicycle any day now :)

I got an amazing result from ChatGPT a while back - an SVG with a perfect illustration of a pelican riding a bicycle.

It was suspiciously good in fact... so I downloaded the SVG file and found out it had generated a raster image with its image tool and then embedded it as base64 binary image data inside an SVG wrapper!

Re: Claude Sonnet 4.5

#510

Post by michaelt »

Redster wrote: post #268
kurtis_reed wrote: post #250

Earlier quoted context omitted.

Why did you have access to a preview?

Simonw is a cheerful and straightforward AI journalist who likes to show and not just tell. He has done a good job aggregating and documenting the progress of LLM tools and models. As I understand it, OpenAI and Anthropic have both wisely decided to make sure he has up to date info because they know he'll write about it. Thanks for all your work, Simon! You're my favorite journalist in this space and I really appreci…

> As I understand it, OpenAI and Anthropic have both wisely decided to make sure he has up to date info because they know he'll write about it.

And the wisest part is if he writes something they don't like, they can cut off that advanced access.

As is the longstanding tradition in games journalism, travel journalism, and suchlike.

Post reply on HN