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

Claude Integrations

anthropic.com

Post reply on HN
Print view View original

131–140 of 266 posts

Re: Claude Integrations

#131

Post by insin »

n_ary wrote: post #30

Is this the beginning of the apps for everything era and finally the SaaS for your LLM begins? Initially we had internet but value came when instead of installed apps, webapps arrived to become SaaS. Now if LLMs can use specific remote MCP which is another SaaS for your LLM, the remote MCP powered service can charge a subscription to do wonderful things and voila! Let the new golden age of SaaS for LLMs begin and the…

It's perfect, nobody will have time to care about how many 9s your service has because the nondeterministic failure mode now sitting slap-bang in the middle is their problem!

Re: Claude Integrations

#132

Post by Balgair »

ilrwbwrkhv wrote: post #31
throwup238 wrote: post #16

The leap frogging at this point is getting insane (in a good way, I guess?). The amount of time each state of the art feature gets before it's supplanted is a few weeks at this point. LLMs were always a fun novelty for me until OpenAI DeepResearch which started to actually come up with useful results on more complex programming questions (where I needed to write all the code by hand but had to pull together lots of d…

None of those reports are any good though. Maybe for shallow research, but I haven't found them deep. Can you share what kind of research you have been trying there where it has done a great job of actual deep research.

I'm echoing this sentiment.

Deep Research hasn't really been that good for me. Maybe I'm just using it wrong?

Example: I want the precipitation in mm and monthly high and low temperature in C for the top 250 most populous cities in North America.

To me, this prompt seems like a pretty anodyne and obvious task for Deep Research. It's long, tedious, but mostly coming from well structured data sources (wikipedia) across two languages at most.

But when I put this in to any of the various models, I mostly get back ways to go and find that data myself. Like, I know how to look at Wikipedia, it's that I don't want to comb through 250 pages manually or try to write a script to handle all the HTML boxes. I want the LLM/model to do this days long tedious task for me.

Re: Claude Integrations

#133

Post by artur_makly »

on their announcement page they wrote " In addition to these updates, we're making WEB SEARCH available globally for all Claude users on paid plans."

So I tested a basic prompt:

1. go to : SOME URL

2. copy all the content found VERBATIM, and show me all that content as markdown here.

Result : it FAILED miserably with a few basic html pages - it simply is not loading all the page content in its internal browser.

What worked well: - Gemini 2.5Pro (Experimental) - GPT 4o-mini // - Gemini 2.0 Flash ( not verbatim but summarized )

Re: Claude Integrations

#134

Post by donmcronald »

n_ary wrote: post #30

Is this the beginning of the apps for everything era and finally the SaaS for your LLM begins? Initially we had internet but value came when instead of installed apps, webapps arrived to become SaaS. Now if LLMs can use specific remote MCP which is another SaaS for your LLM, the remote MCP powered service can charge a subscription to do wonderful things and voila! Let the new golden age of SaaS for LLMs begin and the…

> Now if LLMs can use specific remote MCP which is another SaaS for your LLM, the remote MCP powered service can charge a subscription to do wonderful things and voila!

I've always worked under the assumption the best employees make themselves replaceable via well defined processes and high quality documentation. I have such a hard time understanding why there's so much willingness to integrate irreplaceable SaaS solutions into business processes.

I haven't used AI a ton, but everything I've done has focused on owning my own context, config, etc.. How much are people going to be willing to pay if someone else owns 10+ years of their AI context?

Am I crazy or is owning the context massively valuable?

Re: Claude Integrations

#135

Post by 85392_school »

Balgair wrote: post #132
ilrwbwrkhv wrote: post #31

Earlier quoted context omitted.

None of those reports are any good though. Maybe for shallow research, but I haven't found them deep. Can you share what kind of research you have been trying there where it has done a great job of actual deep research.

I'm echoing this sentiment. Deep Research hasn't really been that good for me. Maybe I'm just using it wrong? Example: I want the precipitation in mm and monthly high and low temperature in C for the top 250 most populous cities in North America. To me, this prompt seems like a pretty anodyne and obvious task for Deep Research. It's long, tedious, but mostly coming from well structured data sources (wikipedia) across…

The funny thing is that if your request only needed the top 100's temperature or the top 33's precipitation, it could just read "List of cities by average temperature" or "List of cities by average precipitation" and that would be it, but the top 250 requires reading 184x more pages.

My perspective on this is that if Deep Research can't do something, you should do it yourself and put the results on the internet. It'll help other humans and AIs trying to do the same task.

Re: Claude Integrations

#136

Post by omneity »

riku_iki wrote: post #127
omneity wrote: post #122

Earlier quoted context omitted.

This assumes the team deploying the RAG-based solution has equal ability to either engineer a RAG-based system or to finetune an LLM. Those are different skillsets and even selecting which LLM should be finetuned is a complex question, let alone aligning it, deploying it, optimizing inference etc. The budget question comes into play as well. Even if text is repetitively fed to the LLM, that might happen over a long e…

> But one cannot deny RAG is a lot more accessible to teams which are likely developers / AI engineers compared to ML engineers/researchers. It looks like major vendors provide simple API for fine-tuning, so you don't need ML engineers/researchers: https://platform.openai.com/docs/guides/fine-tuning Setting RAG infra is likely more complicated than that.

You are certainly right, managed platforms make finetuning much easier. But managed/closed model finetuning is pretty limited and in fact should be named “distribution modeling” or something.

Results with this method are significantly more limited compared to all the power open-weight finetuning gives you (and the skillset needed in return).

And in either case don’t forget alignment and evals.

Re: Claude Integrations

#137

Post by tjsk »

freewizard wrote: post #119
kostas_f wrote: post #114

Anthropic's strategy seems to go towards "AI as universal glue". They want to tie Claude into all the tools teams already live in (Jira, Confluence, Zapier, etc.). That's a smart move for enterprise adoption, but it also feels like they're compensating for a plateau in core model capabilities. Both OpenAI and Google continue to push the frontier on reasoning, multimodality, and efficiency whereas Claude's recent rele…

I would expect Slack do this. Maybe Slack and Claude should merge one day, given MS and Google has their own core models.

Slack is owned by Salesforce which is doing its own Agentforce stuff

Re: Claude Integrations

#138

Post by retinaros »

omneity wrote: post #104
notgiorgi wrote: post #39

Earlier quoted context omitted.

why is finetuning talked about so much less than RAG? is it not viable at all?

RAG is infinitely more accessible and cheaper than finetuning. But it is true that finetuning is getting severely overlooked in situations where it would outperform alternatives like RAG.

fine tuning can cost 80$ and a few hours. a good rag doesnt exist

Re: Claude Integrations

#139

Post by meander_water »

Looks like this is possible due to the relatively recent addition of OAuth2.1 to the MCP spec [0] to allow secure comms to remote servers.

However, there's a major concern that server hosters are on the hook to implement authorization. Ongoing discussion here [1].

[0] https://modelcontextprotocol.io/specification/2025-03-26

[1] https://github.com/modelcontextprotocol/modelcontextprotocol...

Re: Claude Integrations

#140

Post by brumar »

donmcronald wrote: post #134
n_ary wrote: post #30

Is this the beginning of the apps for everything era and finally the SaaS for your LLM begins? Initially we had internet but value came when instead of installed apps, webapps arrived to become SaaS. Now if LLMs can use specific remote MCP which is another SaaS for your LLM, the remote MCP powered service can charge a subscription to do wonderful things and voila! Let the new golden age of SaaS for LLMs begin and the…

> Now if LLMs can use specific remote MCP which is another SaaS for your LLM, the remote MCP powered service can charge a subscription to do wonderful things and voila! I've always worked under the assumption the best employees make themselves replaceable via well defined processes and high quality documentation. I have such a hard time understanding why there's so much willingness to integrate irreplaceable SaaS sol…

Hello fellow context owner. I like my modules with their context.sh at their root level. If crafted with care, magic happens. Reciprocally, when AI derails, it's most often due to bad context management and fixed by improving it.
Post reply on HN