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

Claude 3.5 Sonnet

anthropic.com

Post reply on HN
Print view View original

81–90 of 287 posts

Re: Claude 3.5 Sonnet

#81

Post by jamesponddotco »

impulser_ wrote: post #18

Anthropic is the new king. This isn't even Claude 3.5 Opus and it's already super impressive. The speed is insane. I asked it "Write an in depth tutorial on async programming in Go" and it filled out 8 sections of a tutorial with multiple examples per section before GPT4o got to the second section and GPT4o couldn't even finish the tutorial before quitting. I been a fan of Anthropic models since Claude 3. Despite the…

One thing Anthropic did that I loved and think was very smart was building a prompt generator[1] into the developer console. The generator is tuned to generate prompts the way Claude prompts are supposed to be, which improves responses. And you can use it to improve your user prompt as well, not just your system prompt, which make responses even better.

You can see examples of the prompts it generates here[2]. It significantly improved my experience with LLMs; I haven't touched GPT4 in quite a while, and GPT4o didn't change that.

[1]: https://docs.anthropic.com/en/docs/build-with-claude/prompt-...

[2]: https://sr.ht/~jamesponddotco/llm-prompts/

Re: Claude 3.5 Sonnet

#83

Post by javier_e06 »

This is impressive. I spend some time polishing my questions though. Poor questioning produces verbose replies.

There is no need to nail it on the first reply. Unless is pretty obvious.

If I ask how to install Firefox in Linux it can reply with: "Is this for Ubuntu? What distro are talking about?"

This is more human like. More natural. IMO.

Re: Claude 3.5 Sonnet

#84

Post by infecto »

heymijo wrote: post #73

Anyone want to make a case for Anthropic being undervalued? $7.5 billion raised at an $18.4 billion valuation for Anthropic. $11.3 billion raised at an $80.0 billion valuation for OpenAI.

Along with the revenue already mentioned I would also argue that the approaches taken differ. OpenAI was quick to get business in the door with the appropriate contracts. Anthropic at least initially, was very coy, wanting you to talk to a sales person, describe your use cases etc.

Re: Claude 3.5 Sonnet

#85

Post by rubymamis »

throwup238 wrote: post #75
rubymamis wrote: post #56

Earlier quoted context omitted.

A fellow Qt/QML developer here (get-plume.come). Sounds interesting, what are you building?

An AI chat interface ironically. All of the chat apps are slow as heck electron so I figured there's a market for an actually usable desktop app, especially one that can inline code files and create a RAG index of local documents. Plume looks great! I'm curious how you implemented the markdown formatted text editing component - I need to implement something similar for the chat input.

So funny! I thought about building the same thing for the exact same reason! And the block editor I created for Plume is a great candidate for that.

I implemented the editor from scratch. The model is a C++ QAbstractListModel and the view is in QML. I'm writing a blog post about the implementation, it should pop up soon on my personal website (https://rubymamistvalove.com). But I can (and wish) to send you a draft soon, if you would like.

Re: Claude 3.5 Sonnet

#86

Post by gotrythis »

netsec_burn wrote: post #79

Opus remained better than GPT for me, even after the release of GPT-4o. VERY happy to see an even further improvement beyond that, Claude is a terrific product and given the news that GPT-5 only began its training several weeks ago I don't see any situation where Anthropic is dethroned in the near term. There are only two parts of Anthropic's offering I'm not a fan of: - Lack of conversation sharing: I had a conversa…

What I understand is that it's GPT 6 that just went into training, and that GPT 5 is complete and being delayed until after the U.S. election.

Re: Claude 3.5 Sonnet

#87

Post by boredemployee »

impulser_ wrote: post #18

Anthropic is the new king. This isn't even Claude 3.5 Opus and it's already super impressive. The speed is insane. I asked it "Write an in depth tutorial on async programming in Go" and it filled out 8 sections of a tutorial with multiple examples per section before GPT4o got to the second section and GPT4o couldn't even finish the tutorial before quitting. I been a fan of Anthropic models since Claude 3. Despite the…

Never tried anything other than Open AI GPT family models and some toy LLMs, but GPT4o sucks compared to GPT4 (imho). I'll try Claude and compare.

Re: Claude 3.5 Sonnet

#89

Post by prasoonds »

3l3c7r1c wrote: post #15
prasoonds wrote: post #8

This is amazing - I far prefer the personality of Claude to GPT-4 series models. Also, with coding tasks, Claude-3-Opus and been far better for me vs gpt-4-turbo and gpt-4o both. Looking forward to giving it a spin. Seems like it's doing better than GPT-4o in most benchmarks though I'd like to see if its speed is comparable or not. Also, eagerly awaiting the LMSYS blind comparison results!

For coding Claude Opus-3 provides far more mature code and good at finding bugs (when present with the error code) compared to GPT-4-Turbo and GPT-4o. Last few days I've been using both for some python+pyspark project. Not sure how come in their comparison GPT-4o is showing that good!

100% agree here. Claude is especially good at larger context sizes and retains coherence way longer than GPT-4 series of models

Re: Claude 3.5 Sonnet

#90

Post by infecto »

mamoul wrote: post #11
swalsh wrote: post #3

Anthropic has been killing it. I subscribe to both chatgpt pro and claude, but I spend probably 90% of my time using Claude. I usually only go back to open ai when I want another model to evaluate or modify the results.

a Kagi Ultimate subscription gets you access to both (plus others) for $25/mo

This is only via API though. There is a level of magic that Claude.ai and ChatGPT bring to the table that makes it worthwhile.
Post reply on HN