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

Claude can now search the web

anthropic.com

Post reply on HN
Print view View original

91–100 of 758 posts

Re: Claude can now search the web

#91

Post by visarga »

callamdelaney wrote: post #40
whalesalad wrote: post #16

Earlier quoted context omitted.

kagi is searching the web for you, and then injecting the results into the context of the prompt.

Are there any downsides to that approach? It seems like we're moving towards empowering llm's to interact with stuff as if that's better than us doing it for them - is it really? Eg say I want to build an agent to make decisions, shall I write some code to insert the data that informs the decision into the prompt, return structured data, and then write code to implement the decision? Or should I empower the llm do th…

If you want deeper search, it needs to be able to iterate, plan, reason while searching.

Re: Claude can now search the web

#92

Post by not_good_coder »

jetrink wrote: post #85

> With web search, Claude has access to the latest events and information, boosting its accuracy on tasks that benefit from the most recent data. I'm surprised that they only expect performance to improve for tasks involving recent information. I thought it was widely accepted that using an LLM to extract information from a document is much more reliable than asking it to recall information it was trained on. In part…

I have found that for RAG use cases where the source can be document or web data, hallucinations can still occur. This is largely driven by the prompt and alignment to the data available for processing and re-ranking.

Re: Claude can now search the web

#93

Post by timdiggerm »

Filligree wrote: post #87
bayindirh wrote: post #67

Earlier quoted context omitted.

So, do you mean LLMs are human-like and conscious? I thought they were just machine code running on part GPU and part CPU.

There’s a human using the LLM. In a live web browsing session like this, the LLM stands in for the browser.

Would you believe that humans turn on traditional web-crawlers as well?

Re: Claude can now search the web

#94

Post by Matl »

tantalor wrote: post #89

It says a lot about their product vision and intended market that the example query is typescript migration question. Do they not care about typical search users? Only developers?

I'd guess they showed that query because LLMs are a lot better at answering translation/migration type stuff without hallucinating too much.

Re: Claude can now search the web

#95

Post by ilaksh »

I've been using Tavily's search API for my MindRoot agents. Seems to work fairly well and much easier to set up than Google's search API.

Anyone know if there is something better? I was thinking of trying Perplexity maybe.

Re: Claude can now search the web

#96

Post by cactusplant7374 »

Brusco_RF wrote: post #13
newfocogi wrote: post #8

Earlier quoted context omitted.

ChatGPT can search the web (I just checked in my account). It appears to be available for all users (not just paid): https://help.openai.com/en/articles/9237897-chatgpt-search

I definitely tried to web search with ChatGPT a few weeks ago and it couldn't. I don't think I'm making this up. Unless I suffered a TBI.

About half my requests end up going to web search. But if you ask it for something specific like "find an X-ray image with an abnormality," then it refuses.

Re: Claude can now search the web

#97

Post by tgtweak »

Feels like a catch-up feature to chatgpt... honestly the biggest holdback for me on anthropic is the output token limit on sonnet... 8000 tokens max output is really limited (and 200k tokens in) compared to other offerings - especially considering that I suspect most sonnet users are not chat-users but api users.

Re: Claude can now search the web

#98

Post by Ukv »

bayindirh wrote: post #67
explain wrote: post #22

Earlier quoted context omitted.

robots.txt is meant for automated crawlers, not human-driven actions.

So, do you mean LLMs are human-like and conscious? I thought they were just machine code running on part GPU and part CPU.

I think they mean that it's a tool accessing URLs in response to a user request to present to the user live - with that user being a human. Like if you used some webpage translation service, or non-ML summarizer.

There's some gray area though, and the search engine indexing in advance (not sure if they've partnered with Bing/Google/...) should still follow robots.txt.

Post reply on HN