Search is primarily a portal - you know a particular resource exists, you just don't know its exact URL. You hear about this new programming language called "Frob", and you assume it must have a website. So you google "Frob language". You hear that there was a plane crash in DC, and assume (CNN/AP/your_favorite_news_site) has almost certainly written an article about it. You google "DC plane crash." LLMs aren't ever…
Ask HN: Do you still use search engines?
321–330 of 609 posts
Re: Ask HN: Do you still use search engines?
#322Earlier quoted context omitted.
You can disable the AI summary thing: https://duckduckgo.com/duckduckgo-help-pages/duckai/how-to-h...
Other way around. That disables the AI chatbot monstrosity at the top of the page. But only if you're logged in and/or don't clear your cookies. The AI word salad summaries for each individual page have no toggle (unless you count !g).
Searching 'octatrack' has the wikipedia page on the top right as a summary box thing. no ai word salad for me :shrug:
Re: Ask HN: Do you still use search engines?
#323Earlier quoted context omitted.
GPt models have a people-pleasing bias and positivity bias. If you want factual information, you have to modify your prompt. I imagine you would get very different results if you asked "are Jeeps more reliable than Toyotas", or "how do Jeeps compare to the median car in terms of reliability" My impression is that different llms are more or less people pleasing. I found grok is more willing to tell me something is a b…
I wouldn't be surprised if the training was weighted to favor text it learned from more "reliable" or "professional" resources, which in the case of products, would be official sales listings that talk about how great their product is.
Looking at the reasoning traces for for the new reasoning models you can actually see how fine tuning is moving toward having models list the assumptions around data sources, which should be trusted, list multiple perspectives and then summarize, resulting in better answers. You can do that today with non-reasoning models, but you need to prompt engineer it to ask for that explicitly. This process of identifying not just extant content, but teaching systems how to approach problem analysis (instruction tuning, reasoning traces, etc ...) will be key to influencing how the models work and increasingly how they are differentiated.
Re: Ask HN: Do you still use search engines?
#324I would use the analogy of consuming a perfectly tasty and nutritional meal crafted by chef chatgpt vs visiting a few restaurants around your neighborhood and tasting different cuisines. neither approach is wrong but you get different things and values out of each approach. Do what you feel like doing!
Last week, there was a specific coding problem I needed help with, I asked chatgpt which gave me a great answer. Except I spent a few hours trying to figure out why the function chatgpt was using wasn't being included, despite the #include directives being all correct. neither chatgpt nor google were helpful. The solution was to just take a different approach to my code, if I only googled, I wouldn't have spent that time chasing the wrong solution.
Also consider this, when you ask a question, there are a bunch of rude people (well meaning) that ask you questions like "what are you really trying to do?" and who criticize a bunch of unrelated things about your code/approach/question. a lot of times that's just annoying but sometimes that gives you really good insights on the problem domain.
Re: Ask HN: Do you still use search engines?
#325Re: Ask HN: Do you still use search engines?
#326Re: Ask HN: Do you still use search engines?
#327That’s if they can swing the immense ads machine (and by that I mean the ads organisation not the tech) and point it at a new world and a different GTM strategy.
They still haven’t figured out how to properly incentivise content producers. A lazy way would be to display ads that the source websites would display alongside the summary or llm generated response and pass on any CPM to the source.
Re: Ask HN: Do you still use search engines?
#328Search is primarily a portal - you know a particular resource exists, you just don't know its exact URL. You hear about this new programming language called "Frob", and you assume it must have a website. So you google "Frob language". You hear that there was a plane crash in DC, and assume (CNN/AP/your_favorite_news_site) has almost certainly written an article about it. You google "DC plane crash." LLMs aren't ever…
have you tried chatgpt search? you can do "DC plane crash" or "Frob" it will come up with links to the story, but it will quickly give you a summary with links to its sources. Best thing is you can follow up with questions.
But what I'm talking about is when I want to read the page for myself. Waste of time to have to wait for an LLM to chew on it.
Re: Ask HN: Do you still use search engines?
#329I still prefer tranditional search engines over LLMs but I admit, its results feels worse than it has traditionally. I don't like LLMs for two reasons: * I can't really get a feel for the veracity of the information without double checking it. A lot of context I get from just reading results from a traditional search engine is lost when I get an answer from a LLM. I find it somewhat uncomfortable to just accept the a…
One thing I don't like about LLMs is that they vomit out a page of prose as filler around the key point which could just be a short sentence. At least that has been my experience. I admit I don't use LLMs very much.
Re: Ask HN: Do you still use search engines?
#330Earlier quoted context omitted.
There is no exclusive-or between business models, there is an inclusive-or. Over time subscription models will converge to subscription with advertisements. Like newspapers did.
And streaming services. People really thought streaming would be the end of TV commercials. Ha!
Ads xor payment, or else you can fuck all the way off.