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

261–270 of 758 posts

Re: Claude can now search the web

#262

Post by exe34 »

jimbokun wrote: post #254
_heimdall wrote: post #131

Earlier quoted context omitted.

That could very well be because the jobs are effectively useless. By no means does that mean the people are, nor is what the income allows them to do. But most jobs sure do seem pointless.

Unfettered capitalism is pretty good at figuring out which is which. It’s pretty core to Elon Musk’s animating philosophy: get as many jobs as possible then see if there’s any negative impact. Not as appropriate in a government setting where the impact goes far beyond personal profit and loss.

if a CEO can run 7 companies and still play monopoly with the ship of government, then maybe CEOs aren't really that useful.

Re: Claude can now search the web

#263

Post by wickedsight »

yoyohello13 wrote: post #125
Almondsetat wrote: post #111

Earlier quoted context omitted.

>looks at the top X hits and then interprets it to be the correct answer. LLMs are truly reaching human-like behavior then

The longer I've been in the workforce, the more I realize most humans actually kind of suck at their jobs. LLMs being more human like is the opposite of what I want.

Ugh... I've been in IT for over a decade now and many of the vacancies I see, I don't consider myself/my CV good enough. Then I work with the people who get hired for these jobs and see how low they set the bar, even though their CV might tick all the boxes.

Re: Claude can now search the web

#264

Post by lee-rhapsody »

NavinF wrote: post #256
mavamaarten wrote: post #114

Earlier quoted context omitted.

Oh yeah this is very much the case. Every time I ask ChatGPT something simple (thinking it'd be a perfect fit for an LLM, not for a google search) and it starts searching, I already know the "answer" is going to be garbage.

Try their Deep Research or grok's DeepSearch. Both do many searches and read many articles over a couple of minutes

The "Deep" search features hallucinate like crazy, I've found.

Re: Claude can now search the web

#265

Post by enterpriss »

KoolKat23 wrote: post #233
HankWozHere wrote: post #124

Earlier quoted context omitted.

Kagi Assistant allows you to do search with LLM queries. So far I feel it bears reliable results. For instance - I tried couple of queries for product suggestions and came back with some good results. Whilst it’s a premium service , I find the offering to be of good value.

I have a subscription, please could I ask how you do this? I only know of the append ? Feature.

https://kagi.com/assistant

Re: Claude can now search the web

#266

Post by wickedsight »

macrolime wrote: post #260
tcdent wrote: post #102

Searching the web is a great feature in theory, but every implementation I've used so far looks at the top X hits and then interprets it to be the correct answer. When you're talking to an LLM about popular topics or common errors, the top results are often just blogspam or unresolved forum posts, so the you never get an answer to your problem. More of an indicator that web search is more unusable than ever, but inte…

Deep search/deep research in grok, chatgpt, perplexity etc works much better. It can also do things like search in different languages. Wonder about something in some foreign country? Ask it to search in the local language and find things you won't find in English.

> Ask it to search in the local language and find things you won't find in English.

Yeah, this is one of my favorite use cases. Living in Europe, surrounded by different languages, this makes searching stuff in other countries so much more convenient.

Re: Claude can now search the web

#267

Post by CooCooCaCha »

yoyohello13 wrote: post #125
Almondsetat wrote: post #111

Earlier quoted context omitted.

>looks at the top X hits and then interprets it to be the correct answer. LLMs are truly reaching human-like behavior then

The longer I've been in the workforce, the more I realize most humans actually kind of suck at their jobs. LLMs being more human like is the opposite of what I want.

People suck at intellectual tasks but for stuff like locomotion and basic planning we humans are geniuses compared to machines. There isn't a robot today that could get in a car, drive the the grocery store, pick stuff off the shelf, buy it, and bring it back home. That's so easy it's automatic for us.

Re: Claude can now search the web

#268

Post by jimbokun »

TheDudeMan wrote: post #78
mvdtnz wrote: post #68

Earlier quoted context omitted.

No thank you, when I define a robots.txt file I expect all automated systems to respect it.

But this isn't automated. This is user-driven.

It’s clearly not. The human user is not requesting the resource. The AI is.
Post reply on HN