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

How I Use Kagi

flamedfury.com

Post reply on HN
Print view View original

311–320 of 338 posts

Re: How I Use Kagi

#311

Post by lukan »

lostlogin wrote: post #294
lukan wrote: post #104

Earlier quoted context omitted.

"I do not accept simply doing nothing." You can also donate to the Ukrainian army directly. Or to amnesty international. Or a tons of other options instead of collective punishment. What is the ordinary russian against the war supposed to do? They don't even have a real option of leaving the country as most other states don't want them because they are russian. In my opinion this helps Putin in his propaganda that th…

Do you support any sanctions against Russia?

Yes. Sanctions for military goods. Nothing against the civilian population.

Re: How I Use Kagi

#312

Post by dcow »

cosmicgadget wrote: post #310
dcow wrote: post #293

Earlier quoted context omitted.

No, you can’t without being a hypocrite. It sure is convenient to take a moral stance when it has no real impact on your life and just throws others under the bus. But try applying your morality consistently and you will find it’s effectively impossible. So ultimately you’re just picking issues to complain about based on the current political climate, not actually taking a fundamental principled moral stance on an is…

> No, you can’t without being a hypocrite. I literally said this. Please read. > a company that does a minuscule amount of business with a Russian company Should be easy to excise then.

Not if it provides value. And Kagi thinks it does.

Please demonstrate or reason that Kagi buying Yandex’s search index (1) does harm and (2) does more harm than good.

Re: How I Use Kagi

#313

Post by dcow »

lostlogin wrote: post #289
dcow wrote: post #242

Earlier quoted context omitted.

What makes you so certain the US is less bad than Russia?

I’m deeply skeptical of the US. But how are the US and Russia behaving the same way? Can you give an equivalent US atrocity to what’s happening in Ukraine right now?

I think you might be experiencing a “living through it” bias.

Re: How I Use Kagi

#314

Post by radlad »

rpdillon wrote: post #219
radlad wrote: post #82

Earlier quoted context omitted.

> I don't find moral stands particularly compelling, because they're an excuse to indulge in single-factor analysis, and make complex decisions using only the most basic criteria. I don't think this follows. While some people may use morals as an excuse to indulge in single-factor analysis, it's also entirely possible to use a moral stance as just one of many facets of evaluation. > Is it really a net win to boycott…

> it's also entirely possible to use a moral stance as just one of many facets of evaluation. Agreed. I'd need to see evidence of that, though. People are lazy, and they hide behind moral stances that are completely impractical to avoid having to think through the complex moral realities of the decisions we make. I don't have a lot of patience for this. If it's part of a multi-faceted analysis, then I'd expect to see…

I've debated replying at all, but I am genuinely perplexed by this comment as a response to the quoted text:

> It's not your decision. Your decision is whether or not to pay Kagi for their service. Kagi produces a product that tries to provide the best value, and doesn't surveil you.

Did I imply it was my decision? I don't think I did. In fact, I pointed out that I don't even have the data available to me to evaluate the decision against the decision-making axis I provided (how much value is Yandex providing to the search results?) I am struggling to understand what you're trying to get across here besides contrarianism.

The hard fact of the matter is that you are obviously right: I cannot make decisions for Kagi. This was never in question. I can share my feedback with them and vote with my money.

> Kagi produces a product that tries to provide the best value, and doesn't surveil you.

This is another unprovable statement.

Re: How I Use Kagi

#315

Post by Ar-Curunir »

cosmicgadget wrote: post #309
xigoi wrote: post #279

Earlier quoted context omitted.

The point is, if you boycott Yandex because of Russia, then in order to be morally consistent, you should also boycott Google and Bing. At that point, what search engines do you have left?

I was pretty explicit about saying that moral consistency is better but there is a valid position that is inconsistent but still aims to reduce human suffering. And that handwaves the equivalence of the US and Russia as well as their relationships with corporations.

You are literally living through a fascist takeover of the United States, and said corporations are happily participating as long as they get a share of the pie.

I know that HN is an American website, and it is difficult for people in America to view the US negatively, but outside the US you will find a lot of people that don't really see much difference between Russia attacking Ukraine, and the US bombing the living fuck out of Afghanistan and Iraq, or the complete support that US (and its corporations!) have been providing to Israel in its genocide in Gaza.

It is okay to want to boycott one and not the other, but one cannot then turn around and scold others for not engaging in that boycott on a moral basis.

Re: How I Use Kagi

#317

Post by nucleardog »

BlackjackCF wrote: post #25
J_McQuade wrote: post #4

I always feel really grotty about evangelising for products, but I switched to Kagi about six months ago and it really is a better experience. In almost all cases, the search results are as good as or better than Google, and I don't have to scroll through an increasing number of misleading ads to see them. I'm a happy customer. When I first switched, I would often click the button to run the search on google for quer…

I wasn’t really sure about paying for Kagi but I was convinced when I couldn’t find some meme video I saw only a year ago using Google, DDG, Bing, etc., but found it almost immediately using Kagi. I hadn’t realized how bad most search providers had gotten.

Pretty much the same boat as far as "a single experience sealed the deal".

Had been having this recurring weird behaviour with the Apple TV. Every time it happened I'd spend a little while trying to search for it and figure out what was going on. The results were consistently completely irrelevant and useless. This had been ongoing for months.

First time it happened after I started my Kagi trial I tried looking for an answer with Kagi. Second result nailed it. Understood what was going on, pressed one button and put it back.

Then knowing the answer I went back and tried the exact same search with Google. I did find the answer... somewhere at result 50+ well past a link to Google Books offering me an article in a 2008 copy of Men's Health Magazine.

Didn't even use up the rest of my free trial. Subscribed right there and haven't looked back.

I don't know that Kagi's always better, but I've yet to run into anything where it's substantially _worse_. I haven't had a single instance where I've exhausted Kagi and tried Google and found a result there instead.

Re: How I Use Kagi

#318

Post by nucleardog »

testfrequency wrote: post #147
lomlobon wrote: post #137

Earlier quoted context omitted.

Probably they are using 'Kagi Assistant', which is essentially kagi acting as an intermediary to the major LLMs. You get a catalog and a monthly quota. Pretty handy. You can also make your assistants use the same custom 'lenses' you do to constrain their searches.

Interesting. The lenses sound similar to “Spaces” on Perplexity, where you can segment searches to a specific prompt every go and upload files etc for context. Safe to assume that’s a pretty common feature now, maybe I should look at Kagi again - it’s been a few years since I’ve last peeked at it.

The lenses are more about what results will be returned by Kagi's search. They were originally (and still are) a search feature you can use in regular searches.

For example, one of their default lenses is "Academic". It searches research institutions/scientific journals/universities/etc. So as an example, if I search "ulcer risk of ibuprofen":

The "Academic" lens returns the NIH with "Research summaries -- Preventing peptic ulcers"[0] and ScienceDirect with a paper on "The gastrointestinal effects of nonselective NSAIDs and COX-2-selective inhibitors"[1].

Searching without the lens, I get Healthline's "Ibuprofen and Ulcers: Why They Happen and How To Avoid Them"[2] and Medical News Today's "Ibuprofen ulcers: Effects, symptoms, causes, and more"[3].

You can apply these lenses to searches the AI assistant performs separately from the prompts/context/etc. So, for instance, I can set up an "assistant" based on Claude called "Research" restricted to the "Academic" lens. When I ask that assistant questions and it performs a web search, only results from the academic lens (research institutes, universities, etc) will be returned to the AI.

You could do similar with, e.g., setting up an assistant for "Coding with Python" and creating a lens that's restricted to the Python documentation, one for "Local Knowledge" that's restricted to sites from your region, "Recent Developments" that only considers sites published in a certain timeframe, "eBooks" that only returns epub results, etc.

Your prompt/etc is configured separately as part of the "assistant" you're using. So you could have a research assistant with a prompt that asks it to approach the problem step-by-step and evaluate the veracity of the sources, a coding assistant whose prompt includes the language/framework, etc. But there's nothing stopping you hooking your "research assistant" up to your "Coding with Python" lens.

[0] https://www.ncbi.nlm.nih.gov/books/NBK310269/ [1] https://www.sciencedirect.com/science/article/abs/pii/S00490... [2] https://www.healthline.com/health/ibuprofen-ulcer [3] https://www.medicalnewstoday.com/articles/ibuprofen-ulcers

Re: How I Use Kagi

#320

Post by nucleardog »

zargon wrote: post #121
jwr wrote: post #12

Unfortunately, Kagi works with Russian companies and pays them money, which in my book is a no-no. I do not want any of my money to contribute to the Russian economy in any way, because I know what is happening to people in Ukraine. (I was a Kagi subscriber, no more, because of this)

This is like people who vigorously criticize Mozilla's moral failings while using Google Chrome. Heaven forbid we choose the option that is 2% evil instead of the one that is 98% evil.

Pretty much. Like everyone's saying... an absolute moral stance here is pretty much impossible to take.

Do I like that I'm contributing some cents a month into the economy of a country that's invaded another and sent people in that have literally raped infants to death? Uh, no.

Do I like that I'm contributing some cents a month to a company headed by someone that contributes to anti-gay causes and is a COVID skeptic and amplified COVID denial? Also no.

Are those contributions worse than using Google and contributing to their damage of society and the internet?

Are those contributions worse than using one of the AI providers who will gobble up power at absurd rates and contribute meaningfully to the slow death of the planet?

Are those contributions a meaningful concern compared to the fact that I work remotely creating value for a US company whose tax dollars end up going to support Israel and the genocide they're committing in Gaza?

I honestly have no idea. But I can't really see how "not using Yandex" is the absolute stance that everyone should be expected to take, all things considered.

Post reply on HN