I get what looks like a phishing page asking for my OpenAI key.

It seems like a very nice phishing page, though!

Just create a throwaway one

EDIT: suggestion for improvement: add instruction go to

https://platform.openai.com/api-keys

create a new key, and immedietaly revoke after using

good advice

Perhaps. During that time window, someone could rack up quite a bill, and get an account ban.

I prefer to keep secure tokens, well, secure.

You can also set max dollar amount on account

Hey! I followed some of the examples in the Streamlit gallery. I agree it looks like some phising page hahaha when I was trying some of the examples I used a openai key that I deleted after I was finished xD

> give me the 10 most upvoted stories of all time

> Here are the 10 most upvoted stories of all time on Hacker News:

Whisky: Wine Supercharged with the Power of Apple's Game Porting Toolkit - Score: 185 First Is the Worst: Nintendo's Color TV Game 6 and 15 - Score: 39 VectorDB: Vector Database Built by Kagi Search - Score: 198 Periodic Table of Tools - Score: 94 Apertus – Open-Source Camera - Score: 45 Write Guix package definitions in a breeze: Introducing Guix Packager - Score: 102 Grimoire: Open-Source bookmark manager with extra features - Score: 174 Updated a Complex Function Plotter that lets you sketch curves and see its image - Score: 8 They're Made Out of Meat (1991) - Score: 144 City of Boulder Open Data - Score: 45 Is there anything else you would like to know?

Next improvements for the app:

1. Being able to access the comments and ask the bot about them (e.g. give me a summary about the comments, some kind of sentiment analysis, etc.)

2. Being able to summarise the content in the URLs (this is only applicable blog posts, news articles etc, but I think it could be cool for the chatbot to parse the blog post using bs2 and being able to reason and answer questions about it)

This is worst, I have ever seen, why are you using my openai key, you gonna use this for some misuse right???

these are the functions mentioned in the repo readme.

seems theses can be done without gpt ?

~~~

Right now, NewsNerd HackerBot is able to:

- Get you the top, best, new, best, ask, show and job stories of Hacker News.

- Gets you filter the stories by any keyword / keywords you want (e.g. Give me 20 stories about Sam Altman and OpenAI)

~~~

I semi-regularly remember reading something without knowing the exact wording used for the title, particularly for terrible titles like "A new approach" (because that's the original title even though it helps nobody), so the Algolia HN search is hard to use because I need to try a lot of variants ("was that article with that shell script trick about Bash? Linux? Shell scripting in general?") and (near-)synonyms ("emission", "greenhouse", "climate", or "warming" could all be used in an article about environmental policies).

Being able to ask "give me the story from last week about global warming", and it being able to recognize "Climate change goals adjusted at government meeting" as being a match, without it matching any of the actual words, can be very helpful.

I believe that is one of the things Google silently innovated/implemented a ~decade ago, or at least I never heard anyone talk about it the way that people talk about PageRank as magic sauce, but finding such topical synonyms is key to finding more relevant results. (Or super detrimental in other cases, but the quotes operator can help turn that down.) I would be curious how they did it, given that LLM wasn't around then

I just use my browser history.

Same story: browsers also need to know what keyword was in the page title or URL to find it. (And I use HN on three devices.)

Yes, what I mean by that comment is that this interface let's you access all of this information in a chat-based fashion, You don't need to change the tab (from top to new for example), or create some manual filtering. You just ask the chatbot to perform this operations from you (and you can ask for any number of stories you want, sorted by score, etc.).

Nest steps I have in mind (would like to know your opinion about them):

1. Access comments informations (e.g. asking the chatbot to give you a summary of the sentiment analysis on the comments for a given story)

2. Access content information (e.g. suppose one story links to a news article in Xataka for example, it would be really cool for the chatbot to access the content of the webpage and being to answer questions about it)

Any thoughts?

yes, a sum for the discussions under one news, that will be useful,

when there are many discussions, it is hard to read with the current tree-style organization.

nice work.

Don't try to post something and take the openai token from the innocent people who gonna try your stupid app. @Admin please remove this app and person should be blocked from posting this kind of user tricking things. Shame on you

hahahah, you can try it locally if you want. Check the code:

https://github.com/neural-maze/talking_with_hn

But I really think you'd prefer something like an AI girlfriend. You need love bro.