411–420 of 1001 posts
One thing that is quite unfortunate with the state of SEO and the web in general today is that when I asked "what are the latest versions of common programming languages and when were they released?" a large amount of the sources were "13 Tools You Should Learn Now" and the like. This might be a solvable problem within the search API they provide to the LLM, but for now I wouldn't trust current LLMs to be able to fil…
One thing that is quite unfortunate with the state of SEO and the web in general today is that when I asked "what are the latest versions of common programming languages and when were they released?" a large amount of the sources were "13 Tools You Should Learn Now" and the like. This might be a solvable problem within the search API they provide to the LLM, but for now I wouldn't trust current LLMs to be able to fil…
Been thinking about this a lot [1]. Will this fundamentally change how people find and access information? How do you create an experience so compelling that it replaces the current paradigm? The future promised in Star Trek and even Apple's Knowledge Navigator [2] from 1987 still feels distant. In those visions, users simply asked questions and received reliable answers - nobody had to fact-check the answers ever. C…
We need to stop adopting this subscription model society mentality and retake _our_ internet. Internet culture was at one point about sharing and creating, simply for the sake of it. We tinker'd and created in our free time, because we liked it and wanted to share with the world. There was something novel to this.
We are hackers, we only care about learning and exploring. If you want to fix a broken system, look to the generations of old, they didn't create and share simply to make money, they did it because they loved the idea of a open and free information super highway, a place where we could share thoughts, ideas and information at the touch of a few keystrokes. We _have_ to hold on to this ethos, or we will lose what ever little is left of this idea.
I see things like kagi and is instantly met with some new service, locked behind a paywall, promising lush green fields of bliss. This is part of the problem. (not saying kagi is a bad service) I see a normalized stigma around people who value privacy, and as a result is being locked out, behind the excuse of "mAliCiOuS" activity. I see monstrous giants getting away with undermining net neutrality and well established protocols for their own benefit.
I implore you all, young and old, re(connect) to the hacker ethos, and fight for a free and open internet. Make your very existence a act of rebellion.
Thank you for reading my delirium.
I've heard people find RAG not to work very well, is that accurate? Is it just about using the right embeddings?
I suppose ideally you just put the sources in the context window, which becomes limiting with large amounts of text?
This is probably Google's Altavista moment, by making their results crappier by the year in search of Ad dollars everyone has felt that there is a potential for search to be better and once that becomes available they'll be in a continious game of catch-up. Yes, Google has their own AI divisions, tons of money and SEO is to blame for part of their crappiness. But they've also _explicitly_ focused on ad-dollars over a…
With ChatGPT, I can give a thumbs up or thumbs down; this means that OpenAI will optimize for users thumbs up.
With Google, the feedback is if I click on an Ad; this means that Google optimizes for clickbait.
Earlier quoted context omitted.
Hello bot. This is a search functionality not a new model.
Maybe you don't understand how this works? It's able to query the relevant documentation, put it in its context and then use that to generate code. It's extremely relevant to giving existing models superior functionality.
Been thinking about this a lot [1]. Will this fundamentally change how people find and access information? How do you create an experience so compelling that it replaces the current paradigm? The future promised in Star Trek and even Apple's Knowledge Navigator [2] from 1987 still feels distant. In those visions, users simply asked questions and received reliable answers - nobody had to fact-check the answers ever. C…
Solving this problem will require us to stop using the entire web as a source of information. Anyone can write anything and put it up on the web, and LLMs have no way to distinguish truth from fantasy. Limiting responses to curated information sources is the way forward. Encyclopedias, news outlets, research journals, and so on. No, they're not infallible. But they're infinitely better than anonymous web sites.
Genuine question: is there a present or planned value proposition for people like me who already have decent search skills? Or are these really for children/elders who (without making any normative claim about whether this is a good thing or not) can't be arsed to perform searches themselves? Does someone else have good search skills but mingle traditional search engines with LLMs anyways? Why? I use LLMs every day b…
I think it’s pretty clear that LLMs can process a document/article/web page faster than any human in order to answer a given question. (And it can be parallelized across multiple pages at once too). The main hard part of searching isn’t formulating queries to write in the Google search bar, it’s clicking on links, and reading/skimming until you find the specific answer you want. Getting one sentence direct answers is…
If we assume that people want a 'direct answer', then of course a direct answer is better. But maybe some of us don't want a 'direct answer'? I want to know who's saying what, and in which context, so I can draw my own conclusions.
Hopefully ChatGPT's version works very well. Phind was more of a kludge to demonstrate what combining chat AI and search can do.