Skip to content Skip to footer
Claude can now search the web by meetpateltech

Claude can now search the web by meetpateltech

48 Comments

  • Post Author
    morisil
    Posted March 20, 2025 at 5:01 pm

    I added this functionality already some time ago in my Claudine agent:

    https://github.com/xemantic/claudine/

    It costed roughly 30 lines of code:
    https://github.com/xemantic/claudine/blob/main/src/commonMai…

  • Post Author
    msp26
    Posted March 20, 2025 at 5:03 pm

    > in feature preview for all paid Claude users in the United States. Support for users on our free plan and more countries is coming soon

    US only

  • Post Author
    ubicomp
    Posted March 20, 2025 at 5:03 pm

    Excited to see this. I've really been enjoying Claude. It feels like a different, more creative flavor of experience than GPT. I use Claude a lot for dialogues and exploring ideas, like a conversational partner. Having web access will add an interesting dimension to this.

  • Post Author
    Brusco_RF
    Posted March 20, 2025 at 5:05 pm

    Excited to see how this compares to Perplexity or Gemini. I remember that ChatGPT used to be able to search the web, but last I checked it it couldn't. I wonder why they removed that feature

  • Post Author
    danirogerc
    Posted March 20, 2025 at 5:06 pm

    Couldn't a lot of front-ends using Claude API do this already? What's new?

  • Post Author
    NBJack
    Posted March 20, 2025 at 5:08 pm

    I wonder if it will actually respect the robots.txt this time.

  • Post Author
    firloop
    Posted March 20, 2025 at 5:08 pm

    Any information on what search engine is powering it?

  • Post Author
    goatmeal
    Posted March 20, 2025 at 5:09 pm

    kagi already lets me use claude to search the web. how is this different?

  • Post Author
    hombre_fatal
    Posted March 20, 2025 at 5:09 pm

    Aside, does anyone know of an app like Perplexity for surfing the news in a foreign language (language practice)?

    Perplexity's "Explore" tab translates its news to your local language, and its curated news items are all pretty interesting, but the problem is that there are so few of them. I seem to get maybe a dozen stories in a day. I paid their subscription for a month just to listen to the news on my walk, but didn't renew because of this.

    A foreign news site like BBC Mundo (Spanish) on the other hand barely has any stories outside of a few niches. Its tech section only has a few stories per week.

    Hmm, maybe I want a sort of RSS reader that AI-translates stories for me. But I don't really want to maintain a feed myself either.

    Apple News would probably do it since they also have good curation, but afaict they still don't support foreign news sources (why???).

  • Post Author
    mvieira38
    Posted March 20, 2025 at 5:12 pm

    What's up with the geoblocking of Claude features? Not the first time it happens

  • Post Author
    itpcc
    Posted March 20, 2025 at 5:13 pm

    Now I understand why Gitlab was (is?) attacked[0] by those hideous bots.

    [0] https://news.ycombinator.com/item?id=43422413

  • Post Author
    pcj-github
    Posted March 20, 2025 at 5:14 pm

    Does not really say /how/ it's performing a web search… Is it tapping into it's "own" corpus of material or calling out to some other web search engine?

  • Post Author
    punkpeye
    Posted March 20, 2025 at 5:17 pm

    There is already a 100 ways of doing it using MCP

    https://glama.ai/mcp/servers?searchTerm=search

    What's the benefit of bringing native integration?

  • Post Author
    light_triad
    Posted March 20, 2025 at 5:17 pm

    Good news. I integrated Claude with a scrapper to get info from pages and it was not giving hallucinations 99% of the time. Hope this works out of the box now.

  • Post Author
    blensor
    Posted March 20, 2025 at 5:18 pm

    Funny thing is that I have the obsidian-mcp-tools installed and today claude-desktop just starting fetching stuff from the web through that because it exposes a fetch tool to claude.

    So this limitation is a bit arbitrary anyway.

  • Post Author
    ProofHouse
    Posted March 20, 2025 at 5:20 pm

    Awesome, but I also do want to say it’s pretty sad it took this long straight up. Literally no excuse. But I’m glad they finally got to a feature that was launched more than a year ago on competitors.

  • Post Author
    McNutty
    Posted March 20, 2025 at 5:22 pm

    I haven't used Claude yet, but heard many good things. So I'm surprised to see that they're so far behind on this feature.

  • Post Author
    ignoramous
    Posted March 20, 2025 at 5:28 pm

    These are interesting times.

    It wasn't long ago that a uni senior who worked for a decade+ on Google Search told me that it was hopeless anyone tries to compete with Google not because it sees a tonne of signals that helps with IR but because of its in-house AI/ML.

    It turns out that the org that built the ultimate AI/ML that runs rings around anything that came before it for NLP (and thus IR) was a sister team at Google Translate.

    It isn't inconceivable that a kid might be able to build a Google-quality web search, scalability aside, on CommonsCrawls data in a weekend. As someone who built re-ranking algorithms for a search engine built atop Yahoo! and Wikipedia (REST/SOAP) APIs back in the late 2000s as a side project (and experienced the launch and subsequent iterations of Echo/Alexa up close at Amazon), the current capabilities (of even the open weight multi-modal models) seem too good to be true.

    Google itself though is saved by its enormous distribution advantages afforded by Chrome (3B to 5B users) and Android (3B+), aside from its search deals with Apple and other browser vendors.

  • Post Author
    fourside
    Posted March 20, 2025 at 5:32 pm

    I’ll be interested in trying it. My admittedly limited experience with this on ChatGPT has been disappointing. ChatGPT falls for the SEO content that has taken over the web.

    As an example, I recently travelled abroad to a popular vacationing spot and asked ChatGPT for local recommendations on what to do. When it gave me answers directly, they were pretty solid. But when it “searched the web” instead, the answers were awful. Every single result it suggested had terrible ratings. It did this repeatedly. One of those times I asked it to pick something with better ratings and it sort of improved but not by much.

    Of course this is another tool and maybe Claude uses better sources or a better algorithm, but in this case where there was a concrete number tied to the results, that while not perfect, aims to rate the quality of a result, it still did not filter out low quality answers. I’m not sure I trust these LLMs to do any better when there aren’t such ratings available. The available input data is just not very good, and now LLMs are being used to feed that low quality, SEO machine.

  • Post Author
    mediumsmart
    Posted March 20, 2025 at 5:38 pm

    thats great – the web he has been trained on or the one from Google?

  • Post Author
    tttym
    Posted March 20, 2025 at 5:44 pm

    It's like a line of platforms waiting for their own agents for web search

  • Post Author
    rgbrgb
    Posted March 20, 2025 at 5:47 pm

    Is there a way to access the new web browsing capability via API?

  • Post Author
    deadbabe
    Posted March 20, 2025 at 5:51 pm

    Is no one concerned about LLMs just feeding people SEO ads as content?

  • Post Author
    ConanRus
    Posted March 20, 2025 at 5:52 pm

    finally

  • Post Author
    jetrink
    Posted March 20, 2025 at 5:55 pm

    > 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 particular, it is supposed to lead to fewer instances of inventing facts out of thin air. Is my understanding out of date?

  • Post Author
    tantalor
    Posted March 20, 2025 at 5:58 pm

    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?

  • Post Author
    beezle
    Posted March 20, 2025 at 5:59 pm

    At this point it is probably easier to poison web pages for AI crawlers in a way that does not taint the human experience.

  • Post Author
    ilaksh
    Posted March 20, 2025 at 6:01 pm

    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.

  • Post Author
    tgtweak
    Posted March 20, 2025 at 6:02 pm

    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.

  • Post Author
    bfeynman
    Posted March 20, 2025 at 6:04 pm

    why does perplexity exist anymore? They were one of anthropic's biggest customers and had been finetuning claude models for search for a while.

  • Post Author
    NewJazz
    Posted March 20, 2025 at 6:04 pm

    Bizarre that they choose to publish this right as a thread criticizing AI crawlers gets bumped off the front page.

    https://news.ycombinator.com/item?id=43422413

  • Post Author
    tcdent
    Posted March 20, 2025 at 6:07 pm

    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 interesting that it affects the performance of generative systems, nonetheless.

  • Post Author
    CalChris
    Posted March 20, 2025 at 6:08 pm

    I find myself Googling less often these days. Frustrated with both the poor search results and impressed with the quality of AI to do the same thing and more, I think search's days are numbered. AOL lasted as an email address for quite some time after America Online ceased to be a relevant portal. Maybe Gmail will as well.

  • Post Author
    joshstrange
    Posted March 20, 2025 at 6:14 pm

    Massive props to Anthropic for announcing a feature _and_ making it available for everyone right away.

    OpenAI is so annoying in this aspect. They will regularly give timelines for rollout that not met or simply wrong.

    Edit: "Everyone" = Everyone who pays. Sorry if this sounds mean but I don't care about what the free tier gets or when. As a paying user for both Anthropic and OpenAI I was just pointing out the rollout differences.

    Edit2: My US-bias is showing, sorry I didn't even parse that in the message.

  • Post Author
    g42gregory
    Posted March 20, 2025 at 6:25 pm

    Anybody knows if this search will works inside Cursor? Do we need to do anything to make 3.7-thinking to search the web?

  • Post Author
    nimish
    Posted March 20, 2025 at 6:35 pm

    So what's perplexity's raison detre at this point?

  • Post Author
    scudsworth
    Posted March 20, 2025 at 6:39 pm

    "claude can now ddos random websites . . . more so"

  • Post Author
    douglee650
    Posted March 20, 2025 at 6:41 pm

    You know what Claude can't do? Successfully vibe me a solution to:

    """
    i need a bashrc command that will map the alias "logg" to open macvim to the file at ~/log.txt, then execute the macro defined by "<leader>z"
    """

    Note <leader>z ends with user in insert mode, Claude provides solution below but puts me in edit mode. (I still have to press "i")

    alias loggg='mvim ~/log.txt -c "normal <leader>z"'

  • Post Author
    hansmayer
    Posted March 20, 2025 at 6:42 pm

    So, referring specifically to the example they show on the front-page, what value does this bring actually? The best example they could come up with is Typescript migration ? Really? Weren't the LLMs supposed to be a superior alternative to searching the web? Why do we need to produce more CO2 to do the same we could have done at the fraction of the cost, of course at the time when the google search was still working?

  • Post Author
    wewewedxfgdf
    Posted March 20, 2025 at 6:47 pm

    I'm waiting for Claude's API to support projects with file uploads like its web UI.

  • Post Author
    ralusek
    Posted March 20, 2025 at 6:47 pm

    Best models for search, in order:

    OpenAI Deep Research

    Grok Deep Search

    Gemini Deep Research

    Grok + Search

    Gemini + Search

    ChatGPT + Search

    These are just my opinions, but I do use this feature all the time. Haven't used Claude enough to get a sense of where it would fit in.

  • Post Author
    gcanyon
    Posted March 20, 2025 at 6:56 pm

    Funny, I literally just two days ago asked Claude to provide an outline of the functionality of a product, giving it the web site. It of course refused. So I downloaded the text of the site and passed that in, and got mediocre results.

    The results based on giving the source URL directly were better. Still a bit generic and high-level and vague, as LLMs tend to be, but better than the text-download version a couple days ago. And of course much easier to generate!

  • Post Author
    ForTheKidz
    Posted March 20, 2025 at 6:58 pm

    Great, now we just need a decent search engine.

  • Post Author
    artembugara
    Posted March 20, 2025 at 7:06 pm

    Search the web is apparently using SERP.

    It’s just breaks my head. We’ve build LLMs that can process millions of pages at a time. But what we give them is a search engine that is optimized for humans.

    It’s like giving a humanoid robot access to a keyboard with a mouse to chat with another humanoid robot.

    Disclaimer: I might be biased as we’re kind of building the fact search engine for LLMs.

  • Post Author
    jsight
    Posted March 20, 2025 at 7:22 pm

    I really want these to be able to find and even redisplay images. "Search all the hotels within 5 miles of this address and show me detailed pictures of the rooms and restrooms"

    Hotels would much rather show you the outside, the lobby, and a conference room, so finding what the actual living space will look like is often surprisingly difficult.

  • Post Author
    sylware
    Posted March 20, 2025 at 7:23 pm

    What I really would like to know: do they use a web crawler with an AI strapped to the mouse and keyboard of a javascript-ed web engine?

  • Post Author
    Taters91
    Posted March 20, 2025 at 7:29 pm

    so can I

  • Post Author
    greatNespresso
    Posted March 20, 2025 at 7:30 pm

    Woaw, so excited about this! Has anyone tried it out already?

Leave a comment

In the Shadows of Innovation”

© 2025 HackTech.info. All Rights Reserved.

Sign Up to Our Newsletter

Be the first to know the latest updates

Whoops, you're not connected to Mailchimp. You need to enter a valid Mailchimp API key.