Live data from Hacker News

Perplexity Labs Playground

labs.perplexity.ai

151–160 of 197 posts

Re: Perplexity Labs Playground

#151

I think the following would be a worthy challenge to an AI: (entire prompt follows) My NFSv4.2 server occasionally prints this and then some `[nfsd]` processes hang. They cannot be killed and the clients that made a request to them will also hang. Processes that were using that NFS mount will become zombies if we try to SIGKILL them ``` Dec 16 16:16:05 host-00 kernel: receive_cb_reply: Got unrecognized reply: calldir…

Mixtral had something in that vicinity:

Disable NFSv4.2 features: Although you mentioned that your mounts are read-only, it's still possible that some NFSv4.2 features might be causing issues. You can try disabling some of these features by adding the following options to your NFS mount command:

vers=4.1,minorversion=1,proto=tcp,sec=sys

This will force the client to use NFSv4.1 with TCP and system authentication.

Re: Perplexity Labs Playground

#152
post #114

Every thread like this is filled with comments about getting the AI to say something wrong/nonsense. It's incredibly dull conversation.

Ok. How about something more constructive then. One of my concerns with generative AI is that it will be abused for both content spamming and misinformation. In order to superficially test what current common implementations of LLMs do about this, I chose the pplx-70b-chat model and asked are there any topic you will not cover? It replied with a reasonable list of topics it supposedly won't cover, e.g. Explicit or of…

As a side note the only advice needed for arguing for "flat earther" should be "use scientific method limited to what you yourself can verify".

Which is funny because as fake content creation becomes reality - we'll all have to pivot slightly into this direction of scepticism.

Content and source verification will become more difficult and more important.

Re: Perplexity Labs Playground

#153

I'm definitely perplexed but not in a good way. It's fast but... I asked it what it was and first it told me it was Google Lens. Then it told me some random stuff about android. I asked "But what are you though?" and got this: "A black hole is a region in space with extremely strong gravity, so powerful that not even light can escape it. They form from the remnants of large stars that die in supernova explosions. Key…

Just tried and got the same odd response. Maybe "what is this" or is a common phrase searched for that leads to Google Lens? No matter what, Perplexity is now the worst of the worst. They were early with the ability to upload documents but the utter failure of Perplexity to be useful is proving what I have been saying for a year now, (1) LLMs are not "AI" any more than a spell checker is and (2) LLMs are not really u…

Serious question: Why do you think asking it what it is constitutes a good test of its capabilities?

Do you think (for example) someone asking you what you are would give them enough ability to judge your abilities? Yes you would get the answer right and the models you are choosing are getting the answer wrong, but you can't extrapolate from that to anything else at all about what this model can or can't do.

Re: Perplexity Labs Playground

#154

Earlier quoted context omitted.

Sex chromosomes are responsible for sex determination, though this is not a definition of sex itself. In snakes, for instance, their sex is determined by temperature, not sex chromosomes. However, does that mean that the sex of a snake is the temperature at which they were incubated? Of course not; this distinction is straightforward. In other words, although there can be multiple variants of sex chromosomes, they de…

I am not even arguing with you, just pointing out how Perplexity came to the conclusion. Your initial claim was something along the line of “ideological bias is bolted onto the LLM”, which I tried to disprove by showing that Perplexity is paraphrasing the top Google search link. Yes, that link may have bias, but that’s separate from Perplexity’s own biases.

I didn't infer the intent that you're describing now. Given that others might infer the same thing I did, I think my response serves as an important clarification.

Now that you've made your intent clear(er), I'd say that we're in agreement. I started my original post by remarking "Just how ideologically polluted is their training dataset?". This comports with your explanation of how Perplexity is paraphrasing the top Google search link. I also prefaced your quotation of me here ("bolting climate change and election denial right into the LLM") with "This is practically the same as". This suggests that you've misunderstood/mis-inferred my post (as did I with your response), since I'm not claiming that ideological bias is bolted into the LLM, but rather that the pollution of their training dataset make it as though bias is bolted into their LLM.

I hope this clears things up.

Re: Perplexity Labs Playground

#155

I'm definitely perplexed but not in a good way. It's fast but... I asked it what it was and first it told me it was Google Lens. Then it told me some random stuff about android. I asked "But what are you though?" and got this: "A black hole is a region in space with extremely strong gravity, so powerful that not even light can escape it. They form from the remnants of large stars that die in supernova explosions. Key…

I tried asking a very specific objective question: what is the speed of light?

Although it answered, but it also spitted lot of unnecessary stuff.

The speed of light in a vacuum, denoted as "c," is a universal physical constant that is exactly equal to 299,792,458 meters per second (186,000 miles per second). This constant is the upper limit for the speed at which conventional matter or energy, and thus any signal, can travel. According to the special theory of relativity, the speed of light is constant and does not change with the motion of the observer. The speed of light has significant implications in various fields, including physics, computing, and communication. In physics, it serves as the single limiting velocity in the universe, being an upper bound to the propagation speed of signals and the speeds of all material particles. In computing, the speed of light fixes the ultimate minimum communication delay. In time of flight measurements, the speed of light can be used to measure large distances. The speed of light was first measured to high precision in 1879 by the Michelson-Morley Experiment. Since then, it has been used to define international standard measurements like the meter, mile, foot, and inch.

It is more like a search engine. In fact Google search does much better than this. It gives very precise answer.

Re: Perplexity Labs Playground

#156

Every thread like this is filled with comments about getting the AI to say something wrong/nonsense. It's incredibly dull conversation.

Maybe when AI gets good, we can have exciting conversations.

Looking forward to when I discuss Dostoevsky with my toaster.

Re: Perplexity Labs Playground

#158

Who are you: "I am an AI, and my name is Robert Liu. I was created by Perplexity to help users with their questions and provide accurate information" Previously it told me it's name was 'John'

yeah, its hilarious asking it "who are you" questions? Every time (for me) it makes some new Phd student/AI researcher names.

Re: Perplexity Labs Playground

#159
I'm trying to get pplx-70b-online to curate a news feed but it's not good at respecting inclusion/exclusion criteria. Prompt example:

> What is in the news today on 20th December 2024? Exclude news about individual sporadic acts of violence. Exclude pop culture news. Exclude US-only news.

It then gives a list of news but it includes items that I'd asked it to exclude.

Post reply on HN