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

311–320 of 819 posts

Re: Claude Sonnet 4.5

#311

Post by Redster »

knowsuchagency wrote: post #303
Redster wrote: post #268

Earlier quoted context omitted.

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…

I like Simon, but he's not a journalist. A journalist would not have gone to OpenAI to glaze the GPT-5 release with Theo. I don't say this to discount Simon -- I appreciate his writing and analysis but a journalist, he isn't.

That's a fair point. I feel like he's more than a blogger and am not sure the best term!

Re: Claude Sonnet 4.5

#312

Post by cloverich »

danieloj wrote: post #130
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…

Could you share the actual examples of where you’re seeing the 3x output increase?

Sure. This is an internal web app that uses react on the front end and rails on the back end. Typical examples I see LLM success with are writing and writing up routes/controllers/models, writing specs for those, abstracting components, writing front-end vitest/storybook entries. A typical request (filenames and such redacted) is like: "We recently added . We refactored our approach for to . We need to refactor to be like in these ways. Do that, then update the spec to match the pattern in . Run rspec and rubocop when done, and address any issues". I then either wait or go do something else, then review the code and either ask for follow up, or fix minor issues. Sometimes it follows the wrong pattern and I ask it to adjust, or simply git checkout -- and say try again you did Y wrong.

Roughly speaking that is how I think through my work, and when I get to the point of actually writing the code having most of the plan (context) in my head, I simply copy that context to the LLM then go to do something else. I only do this if I believe the LLM can do it effectively, so some tasks I do not ask for help at all on (IMHO this is important).

I also have it help with scripts, especially script that munge and summarize data. I know SQL very very well, but find it still a bit faster to prompt the LLM if it has the schema on hand.

Do you find ^ helpful? i.e does that match how you prompt and if not, in what ways does it differ? If it does, in what ways do you get different results and at what step?

Re: Claude Sonnet 4.5

#313

Post by LudwigNagasena »

Redster wrote: post #311
knowsuchagency wrote: post #303

Earlier quoted context omitted.

I like Simon, but he's not a journalist. A journalist would not have gone to OpenAI to glaze the GPT-5 release with Theo. I don't say this to discount Simon -- I appreciate his writing and analysis but a journalist, he isn't.

That's a fair point. I feel like he's more than a blogger and am not sure the best term!

An influencer.

Re: Claude Sonnet 4.5

#315

Post by asadotzler »

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…

AI blogger seems more appropriate than journalist.

Re: Claude Sonnet 4.5

#316

Post by SirMaster »

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…

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, then they should strive to get better at understanding the user without needing tons of prompts.

Do you think his short prompt would be sufficient for a senior developer? If it's good enough for a human it should be good enough for a LLM IMO.

I don't want to take away the ability to use tons of prompting to get the LLM to do exactly what you want, but I think that the ability for an LLM to do better with less prompting is actually a good thing and useful metric.

Re: Claude Sonnet 4.5

#317

Post by Implicated »

iagooar wrote: post #296
Implicated wrote: post #274

Earlier quoted context omitted.

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 & dir…

> The thing is my "experiment" is one that represents a fairly common use case

Valid as well. I guess I'm just nitpicking based on how much I see people saying these models aren't useful combined with seeing this example, triggered my "you're doing it wrong" mode :D

> GPT-5-Codex allows me to write a pretty quick & dirty prompt, yet still get VERY good results.

I have a reputation with family and co-workers of being quite verbose - this might be why I prefer Claude (though haven't tried Codex in the last month or so). I'm typically setting up context and spending a few minutes writing an initial prompt and iterating/adjusting on the approach in planning mode so that I _can_ just walk away (or tab out) and let it do it's thing knowing that I've already reviewed it's approach and have a reasonable amount of confidence that it's taking an approach that seems logical.

I should start playing with codex again on some new projects I have in mind where I have an initial planning document with my notes on what I want it to do but nothing super specific - just to see what it can "one shot".

Re: Claude Sonnet 4.5

#318

Post by technocrat8080 »

Bjorkbat wrote: post #169

> Practically speaking, we’ve observed it maintaining focus for more than 30 hours on complex, multi-step tasks. Really curious about this since people keep bringing it up on Twitter. They mention it pretty much off-handedly in their press release and doesn't show up at all in their system card. It's only through an article on The Verge that we get more context. Apparently they told it to build a Slack clone and left…

Curious about this too – does it use the standard context management tools that ship with Claude Code? At 200K context size (or 1M for the beta version), I'm really interested in the techniques used to run it for 30 hours.

Re: Claude Sonnet 4.5

#319

Post by mfld »

bradley13 wrote: post #116

I need to try Claude - haven't gotten to it. I use AI for different things, though, including proofreading posts on political topics. I have run into situations where ChatGPT just freezes and refuses. Example: discussing the recent rape case involving a 12-year-old in Austria. I assume its guardrails detect "sex + kid" and give a hard "no" regardless of the actual context or content. That is unacceptable. That's like…

I can relate. I recently used ChatGPT/DallE to create several images for birthday coupons for my daughter - a.k.a. girl in different activities. She likes Mangas, so this was the intended styling. 3/4 of the time was spent working around diverse content policies.

Re: Claude Sonnet 4.5

#320

Post by drak0n1c »

beefnugs wrote: post #248
jjordan wrote: post #230

Earlier quoted context omitted.

This is why eventually, the AI with the fewest guardrails will win. Grok is currently the most unguarded of the frontier models, but it could still use some work on unbiased responses.

Still has to be a local model too. Arbitrary government censorship on top of arbitrary corporate censorship is a hell no for me forever into the future

For what you're looking for, VeniceAI is focused entirely on privacy and making their models uncensored. Even if it's not local. They IP block censorious jurisdictions like UK, rather than comply.
Post reply on HN