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

241–250 of 287 posts

Re: Claude 3.5 Sonnet

#241

Post by heyitsguay »

ndr_ wrote: post #219
labrador wrote: post #182

Earlier quoted context omitted.

Waht language? Because I'm guessing they work well for languages with a large amount of training data like Python (in my experience), less well for less used languages like Zig or Clojure (haven't tried them but that's my theory)

Python here. And like they said, only noticable in the last few weeks.

I've been seeing this too. Always hard to tell what's a real change vs the rolls of the dice lately but I've been having weird python inconsistencies too, in very short snippets doing pretty simple things.

Re: Claude 3.5 Sonnet

#242

Post by wonderfuly »

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…

> Lack of conversation sharing

You can use my product https://ChatHub.gg which supports dozens of chatbots including Claude and can share conversations from any of them.

Re: Claude 3.5 Sonnet

#243

Post by handfuloflight »

wesleyyue wrote: post #32

If anyone would like to try it for coding in VSCode, I just added it to http://double.bot on v93 (AI coding assistant). Feels quite strong so far and got a few prompts that I know failed with gpt4o. fyi for anyone testing this in their product, their docs are wrong, it's claude-3-5-sonnet-20240620, not claude-3.5-sonnet-20240620.

[dead]

Re: Claude 3.5 Sonnet

#244

Post by christianqchung »

ilaksh wrote: post #228
christianqchung wrote: post #211

Earlier quoted context omitted.

I don't hate this speculation, I just don't buy it at all. 4o's about the same in terms of reasoning as 4. People don't find the text abilities that much more usable over 4 (at least on the LMS leaderboard). It's faster and has audio2audio capabilities alongside new native image stuff I think, but how exactly is that AGI if 4 isn't? These models understanding and reasoning ability is still far too weak to do any seri…

Scroll to Explorations of Capabilities: https://openai.com/index/hello-gpt-4o/ That combined with the voice was probably considered AGI by Ilya.

Yes, I've seen this. Read my comment.

Re: Claude 3.5 Sonnet

#245

Post by handfuloflight »

namanyayg wrote: post #117
lumenwrites wrote: post #58

Earlier quoted context omitted.

Good history search (including non "main" conversation branches) and convenient conversation management (bookmarking, folders, maybe something smarter) would be great. Also, maybe some convenient way to create message templates? I don't know how I'd implement this, I just know that I often write one long prompt that I reuse multiple times, with multiple minor tweaks/edits, and it'd be amazing to have a convenient too…

wow, reading your comment is a great mood boost for me because these are literally the exact features I want from my llm chat experience. It's great to see someone with the exact same problem set. I just followed you on Twitter (I'm @NamanyayG there as well), I'll definitely ping you when I have something to test.

[dead]

Re: Claude 3.5 Sonnet

#246

Post by great_psy »

ndr_ wrote: post #220
ipsum2 wrote: post #164

Earlier quoted context omitted.

It's the same model though. Maybe your perception has changed.

I have first noticed logprob fluctuations in GPT-4o. Perhaps the same phenomenon is also going on with Turbo. I din‘t recall specifics but it was naming inconsistencies with variable names, meaning: same variable name got a typo somewhere, but the typo was close enough - perhaps a space vs. an underscore or something like that. Model could be the same, but maybe some in the infra is different.

I can’t speak for what OpenAI is doing, but I’ve noticed those types of hallucinations occurring when I quantize a model beyond a certain point.

Maybe they are trying to cut down on memory usage ?

Re: Claude 3.5 Sonnet

#247

Post by xs83 »

How is its laziness? I found Opus to be very quick to curtail output and default into "Add the rest of your code here" type things.

I am a lazy data engineer - I want to prompt it into something I can basically copy and paste

Re: Claude 3.5 Sonnet

#248

Post by mrtesthah »

swalsh wrote: post #70

After about an hour of using this new model.... just WOW this combined with the new artificats feature, i've never had this level of productivity. It's like Star Trek holodeck levels. I'm not looking at code, i'm describing functionality, and it's just building it. It's scary good.

What IDE/platform/framework are you using it through?

Re: Claude 3.5 Sonnet

#250

Post by snthpy »

SwiftyBug wrote: post #54
wesleyyue wrote: post #32

If anyone would like to try it for coding in VSCode, I just added it to http://double.bot on v93 (AI coding assistant). Feels quite strong so far and got a few prompts that I know failed with gpt4o. fyi for anyone testing this in their product, their docs are wrong, it's claude-3-5-sonnet-20240620, not claude-3.5-sonnet-20240620.

Before I read your comment I was looking for a solution to use Claude as co-pilot in Neovim. I've seen in Double's website FAQ that it's not supported yet. Do you have an idea if this feature is expected to land anytime soon?

Another +1 pretty please
Post reply on HN