In theory maybe, in some tentative hope that the RAG would patch the hallucination problem - but the LLM showed such a low effective equivalent IQ that its usage was always incredibly frustrating. (It could have improved recently - I am not sure. Some tests have indicated it as especially dumb even not long ago.)
Oh yes, I don't disagree, but in my recollection, the pitch and the hype was always about how they never create fake sources and fake citations, at the time when that was a problem.
You would go to it, but results showed much more work was needed - also in RAG. Which became a general focus in the community, for the many problem it may solve and the many it could help fixing. Some found better formulas for RAG, others swamped. Perplexity made it a flag, but in a factual large company. And the problem with "fake sources and citations" is still there, while mitigated in the full complex systems - hallucination is still a benchmarked effect in LLM ANNs, and blunders from excessive trust are still recorded.
I still remember an HN post back when Perplexity was still the current hotness where the top comment about whatever AI news was analyzing MSFT stock with price history and key milestones, and cited Perplexity as their source. With some meta commentary about how easy research is now that tools like Perplexity are available.
Literally every cited number was flat out wrong. Some people replied to point out the mistakes but as I recall no one called out the Perplexity elephant in the room specifically.
I'll have to find it again, it was such an absurdly ironic scenario it felt like performance art or something.
They always were a "literally who". A lot of paid propaganda on blogs and even shills that were coming to sites like this, on Twitter, etc... were writing stuff for pennies per post (lmao) about how much they used it for this and that but it was all lies.
But people were not using them, regular non-tech folks have ZERO awareness of their brand.
There was a very brief period in the early days where Perplexity actually was pretty useful. I believe I even had a paid subscription to it for maybe half a year at that time. The main value it had then is that ChatGPT didn't yet incorporate web search, or early on after it did its searches were will really limited. There's no reason for Perplexity to exist now. I'm confident they and their investors are keeping it going mainly because no one wants to be the first major AI startup wipeout.
We used to have a lot of lectures of various kind, ranging from short 1-2 hour presentation of 'what's best and what to use' to three-day workshops on academic AI tools, etc. And Perplexity was always mentioned, alongside Scopus AI, Google Scholar AI, etc...
Besides some testing, I've never used it too for different reasons - I don't like my chat history and questions stored at some third party vendor that's just a startup.
Oh damn this is much cooler than I expected! For some reason skimming through channels is more enjoyable than click a video I'd probably wouldn't click on
After clicking an entry, below, "What Hacker News says", we see comments with mentions and surrounding text. It's now squashed, maybe you can add a function to expand on click, to see the comment with newline separation if such exist. Cause very often these comments presents a list of their favorite book, and an explanation of why. When these are squashed, it's not clear which explanation is preceding or following the entry.
Also, clicking the link "On "...."" it doesn't bring to the exact comment, only that thread or topic, so you need to search for it. It could bring directly to that comment.
I've recently been trying to write a paper with an application in a field that I'm not an expert at. I gave the LLM agents to analyze the methods, the data, the outputs, plus some explanations from me what I want to say and show, and told it to write a section of the paper. It did. Then I asked like 3-4 more different frontiers to do the same.
They all do.. something[1]. They write visually great looking papers. Even good on a quick read.
But once I try porting their proposed Section ideas into the paper, I notice that for each sentence I either need to do a complete rewrite, or a deep dive into it (plus the literature), to confirm or delete that idea/sentence.
If it were my field, it would be much simpler to just write everything directly, rather than attack every sentence of LLMs. As it's not my field, it's a decent way to understand the nuances and learn, but I get increasingly disillusioned by AI writing skills.
[1]: Old and new Gemini models are too categorical, everything is a breakthrough and a marvel; Sol/Astra gets bogged down with too many details, and "it's X, not Y" garbage. For some reason, it's very defending against potential referee questions which don't add anything to the main idea; Opus 5.5 or Fable are basically the same. Maybe it's their way of anti-hallucination..
You almost have to treat these models as a monkey paw, or a maliciously compliant genie. They grant you your wish, but rarely the way you intended. You must be incredibly diligent, or accept the consequences.
I loved Gemini 3.1 Pro and it was very sad when they nerfed it at around May this year. I think it did pretty good as a chat, and quite decent on Antigravity (tried very little). Been sitting on 5.6 / Astra and Codex since. Occasionally do bring up the 3.1 Pro through the API, because I love the writing style, but keep noticing that I'm much more productive with the frontier, despite the love to Gemini.
Tried 4 Argon, and it's very much different from 3.1, felt very much the same as any other Frontier, just without the intelligence.
i dont think they've nerfed it did you use api or via subscription(which might make sense) api has been pretty stable for me.
personally i like 4 Argon, it's very clever for me in a very different way comparing to the other two (especially via api) but when it comes to the google products.. sigh. nobody who's actually working on these products really cares about them in google now (maybe notebooklm is the rare exception), they're either not dogfooding themselves or somehow intentionally poisoning the experience on purpose, or simply inqualified. poor gemini is suffering in agy i can tell, it struggles so much and wont even use simple tools properly. if you put it in any good 3rd party harness out there it's flexing way better than agy and this tells a lot.
They nerfed it heavily through the subscription, together with the UI and Pricing changes (introduced 100$ plan). Maybe it's back now, but at the time it was observable and reproducible... The API variant seems to be untouched.
If I just ask questions and do simple research without proactive local works, I'll just use the aistudio, it's probably 10x better than the Gemini app. But other than that I have my own fork based on dsh (nothing fancy I just added a few tools & fixed the thinking level param issue) I rarely use it though. Computer use is bad and i mostly use codex for that
Discord is very hard to understand for me. But the young people love it for some reason. Had to use it for some projects or hackatons, and it's still a mystery why it's so popular. No one found older links that were deeper in the chats, had to constantly tag people to see anything, random chats pushed the important information away. It was overall terrible for everyone yet everyone still loves it.
And weirdly, I then understood that there's no real global platform for a quick chat that everyone knows and CAN actively use. In universities we use Teams, but beyond that people are never active there...
But I also don't understand Twitter or Mastodon. It feels like there's so much better ways to both post stuff and reach people.
In my minimal attempts to use rsync, I always find examples where they always use a ton of flags alongside the locations. I'm not gonna learn those flags if cp can do it intuitively and with minimal extra commands. Maybe it's just me.
Also, I always have this vague fear that I'll rsync in the wrong direction, or accidentally blow away unrelated files in rsync's efforts to fully synchronize two directories (can't remember if this is a valid concern).
I'm sure these concerns would go away if I used it regularly, but I just don't. ‘cp' or ’scp’ almost always meet my needs.
Kinda like the way people are probably right that I should learn to use ’awk’, but I just can't muster the motivation.
> Also, I always have this vague fear that I'll rsync in the wrong direction
It's the same direction as cp/scp ... You could easily do it wrong, but you must be afraid to do anything other than maybe cat < source > dest because that's clear?
> or accidentally blow away unrelated files in rsync's efforts to fully synchronize two directories (can't remember if this is a valid concern).
I think you need --delete for this. As I recall, it's sometimes more tricky to get it to delete the files you wanted it to delete and you're more likely to end up with extra files than removing files you didn't intend to.
Do it once, make it your muscle memory - it's really hard for me to learn things by heart, but even I could do it :), and then you can forget about scp as well
I really like this feature of rsync (trailing "/" means copy the directory contents to the dest, no trailing "/" means copy the directory itself). Other tools, like cp, don't have any way at all to say copy the directory contents to the dest, and for those tools the result depends on whether or not the destination already exists and is a directory (you might end up with a duplicate nested directory). Rsync produces the same result whether the destination already exists or not.
Depending on the shell, `somedir/*` excludes files whose names start with "." and may expand to a literal "*" if there are no file names to expand to. Basically, globbing has more edge cases to deal with.
I remember that macOS/FreeBSD’s cp -R behaves differently depending on the trailing slash (it’s pointed out in the man page). But when I compared with GNU coreutils and busybox they did not, so it’s something to look out for.
Doesn't make sense for them to give away weights. They sell their own service using that and killing the competition (that they have a stake in) isn't in their interest either because their cloud growth is based on other companies' continuing heavy investment in this space.
But Sam Altman said back in the GPT-3.5 days that exactly this will happen to all GPT wrapper startups. [0]
[0]: https://x.com/ai_for_success/status/1779930498623742187
reply