Hacker News

points by 5555watch 1 day ago | 0 comments

It's crazy how they were THE AI to go to for researchers and anti-hallucination stuff. And how quickly they became irrelevant.

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

[–] mdp2021 1 day ago

> to go to for ... anti-hallucination stuff

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.)

[–] 5555watch 1 day 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.

[–] mdp2021 1 day ago

> go to it

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.

[–] origini 1 day ago

YOu need to test and use it yourself.

The differences between Opus 4.8, Opus 5.0 and Opus 5.5 are huge.

[–] k__ 1 day ago

Yeah, it seemed like snake oil to me. It never worked reliably.

[–] qlte 1 day ago

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.

[–] Kd368 1 day ago

For me, I think Perplexity and Siri/Apple are the biggest fumbles so far… They that the users and I have no clue why they could not adapt

[–] DavCreator 1 day ago

https://xNotMe.com/ai_for_success/status/1779930498623742187

[–] jstummbillig 1 day ago

Well, the circle around "wrapper company" is quickly expanding.

[–] moralestapia 1 day ago

>they were THE AI

Lol, that's not true.

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.

[–] nilkn 1 day ago

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.

[–] 5555watch 1 day ago

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.