[HN Gopher] Show HN: HN Update - Hourly news broadcast of top HN...
___________________________________________________________________
Show HN: HN Update - Hourly news broadcast of top HN stories
I feel like it was inevitable, with the recent buzz around
NotebookLM. I'm just surprised that it hasn't been done yet.
Author : yunusabd
Score : 586 points
Date : 2024-10-20 07:10 UTC (1 days ago)
(HTM) web link (hnup.date)
(TXT) w3m dump (hnup.date)
| seungwoolee518 wrote:
| Wow... Really great.
|
| Can you add some historical archive to listen n hours ago (or
| morning briefing like) summary as a feature?
| yunusabd wrote:
| Thanks! An archive shouldn't be too hard to implement.
|
| Would a morning briefing include more of a curated selection of
| news, like the most interesting/most discussed news of the day?
| Currently I just take the top 5 posts from the main page.
| seungwoolee518 wrote:
| Yeah. You're right.
|
| My morning routine is Checking HN with Coffee. So with your
| service I can minimize some time to click around and figure
| out what the root cause is.
| yunusabd wrote:
| I was actually listening to it while making breakfast as
| well, so the idea of an extended morning briefing resonates
| with me. I'll look into it, thanks for the follow-up!
| vulcan01 wrote:
| If you do this, it might be interesting to publish this
| as a podcast. Hourly is too frequent for a podcast, but
| daily would be pretty good.
|
| (Podcasts are just RSS feeds.)
| yunusabd wrote:
| Sounds good, I'll get back to you about that!
| cancelself wrote:
| Podcast/RSS seems like ideal distribution tool?
| tkgally wrote:
| I could easily see listening to such a summary once or twice
| a day. Considering the pace at which HN is updated, how about
| two to four somewhat longer episodes per day, with an archive
| of the past week so that people can catch up? You might also
| want to focus on certain types of stories, such as those with
| more upvotes or comments.
|
| In any case, it's a great idea, and I enjoyed listening to
| the current episode.
| Terretta wrote:
| Not just the top five, more like
| http://www.daemonology.net/hn-daily/ which also ensures
| newness.
|
| Because of that, catching up on several days will also be
| unique stories.
| yunusabd wrote:
| That's a real useful resource. Thanks!
|
| I was looking into using the algolia API to get the top 10
| posts of the last day, but those won't be unique over the
| span of several days.
| supafastcoder wrote:
| A daily update on the best posts of the last 24 hours would
| be amazing: https://news.ycombinator.com/best
| pan69 wrote:
| Nice. Would it be possible to add a link to the actual submission
| as it is being discussed?
| yunusabd wrote:
| Definitely! I was thinking to just show a list of all the links
| under the player, would that work for you?
| shannifin wrote:
| Was thinking the same thing. Very fun idea, nice work!
| pekim wrote:
| That would be great. Highlighting each one as it's talked
| about would be even better.
| synthoidzeta wrote:
| Really neat! How was the waveform visualization achieved?
| karencarits wrote:
| Looks like https://wavesurfer.xyz/
| yunusabd wrote:
| Yep! First time using it, seems really solid and does the
| job.
| mirrorchair01 wrote:
| This is really great stuff, love the added "news-station" type
| music! If something like this we're to be monetized would there
| be any issues regarding copyright?
| yunusabd wrote:
| Thank you! And that's a really good question. Since it's
| summarizing the articles, I would assume that there shouldn't
| be any issues regarding copyright. Regarding the comments that
| it's using, I think HN generally has some rights to them,
| although again it's more of a summarization. Generally HN seems
| cool about these things.
|
| Now, if you were to scan the homepage of the BBC and create a
| news broadcast from it, they probably wouldn't be too happy
| about that, understandably. I have no idea how this would fare
| in court though.
| ewalk153 wrote:
| Did you add the "hi mom" bit at the end, or was that organic?
| yunusabd wrote:
| I added it to the prompt for this exact situation. So it
| was "hard-coded". Tbh it would have been a bit scary if
| that happened organically. Kind of like animals recognizing
| themselves in the mirror levels of self-awareness.
| andai wrote:
| Brilliant idea. I think this has real value as well: as I get
| older, I find that I have less energy for reading, but I also
| notice I often miss really cool stuff that was briefly on the
| front of HN.
|
| I like that it summarizes the comments too. There are often real
| gems buried in there. (I assume you're only taking a few top
| ones?)
|
| I think a great improvement could be made with personalization.
| Most of what's on the front page isn't personally relevant to me,
| and there's a lot of cool stuff on the new submissions page that
| never catches on. So it would be nice if a system could learn
| what kind of stories I personally respond to, and show me (a
| summary of?) those -- even if they aren't currently trending.
|
| Last.fm came out 20 years ago (proving you don't even need AI for
| amazing recommender systems), but it seems personalizing your
| experience never really caught on. (Yeah, the YouTube algorithm
| kind of does this, but you unfortunately have no real control
| over it.)
| a13n wrote:
| agreed on energy for reading. do you think it's that we're
| getting older or that the friction associated with consuming
| information is just getting lower and lower over time?
| andai wrote:
| So my energy levels have declined noticeably from age 20 to
| 30. I thought it was mostly my own chronic health issues
| causing accelerated aging, but many of my friends are making
| similar complaints.
|
| I did notice far before this point (e.g. age 10 to 20) that
| my patience for reading had gone down significantly. If I had
| to guess I'd say that in my case it's due to an underlying
| anxiety that started in early teens and never left me.
| Drowning it out seems to require something more stimulating
| than reading (on paper).
|
| (Perhaps meditation or therapy (shadow integration?) would
| help here. I've certainly had glimpses of inner peace during
| times when I was meditating regularly. One insight from this
| time: "holy crap, I always thought I needed to struggle
| harder, but it turns out I just needed to learn how to
| relax...")
|
| I can get through audiobooks but I can only consume them
| while traveling or doing chores. If I'm sitting down, the
| restlessness is too high and I can't concentrate on the book.
|
| I also have ADHD and heard similar things from others with
| ADHD, so I'm not sure to what degree this translates to
| others.
| conductr wrote:
| I never had ADHD or related attention problems. However, I
| find the way interwebs has evolved over years and to
| basically trained our brains to be so focused on super
| short pieces of simply digestible content has basically
| turned me off of longer form content. I've noticed my
| preference for immediate gratification has increased
| significantly. It feels like I'm developing an attention
| disorder in my middle age years.
| card_zero wrote:
| I read a huge amount every day, lots of news articles,
| chapters of whatever book, random material of interest,
| people's comments and questions. I rarely read anything
| "long-form", however, because it has a strong tendency to
| be a giant self-indulgent bloviating pile of shit. There
| are exceptions: I've read every story on damninteresting,
| because it's true to its name. (Hi Alan. Post something
| new.)
|
| I've nearly finished Moby Dick, but I don't know why,
| it's dreadful, I wouldn't recommend it to anyone. I guess
| it's historically interesting.
|
| Possibly you guys are not losing the will or energy to
| read, you're merely discovering that the things you think
| you ought to read are terrible. Try only reading what you
| like. So what if it's short? Maybe your preference is
| right.
| globular-toast wrote:
| I can't read long form content from a phone screen or
| computer monitor. I really don't like it. It might be the
| scrolling, or maybe the type of screen, or conditioning
| to expect instant gratification. I do, however, read
| 20-30 books a year, both paper and on an ereader.
|
| I think it's super important to make reading a habit so
| one must identify what doesn't work for them and try
| something else. You lose so much if you don't read.
| andai wrote:
| Yeah, reading on a screen is ass. What eReader do you
| use?
|
| I got a Kobo recently and I don't like it much. It's much
| duller than my last one, which is either due to the color
| screen having less contrast or me misremembering.
|
| Kobo's main selling point was that it's not botnet, but I
| couldn't even turn the thing on without making an online
| account...
| globular-toast wrote:
| I use a Kobo Clara HD. I think Claras are the second
| cheapest ones. No colour. I find the contrast about as
| good as a cheap paperback book. Not as good as good
| quality printing on acid-free paper, but that's OK.
|
| I actually prefer lower contrast, it gives me less eye
| fatigue and I've specifically chosen low-contrast themes
| on my computer for as long as I can remember.
|
| I think there is a way to not create the account if you
| really don't want to. I put KOReader on mine straight
| away and never use the built-in software. That also
| incidentally has an option to adjust the contrast.
| waldothedog wrote:
| Wanted to share that I also had intense anxiety/depression
| well into my thirties but was able to finally sort it out a
| few years ago.
|
| I think your phrase "learn how to relax" is spot-on. I was
| chronically under-slept and chronically over-focused on
| school, university, career, side-hustle(s), etc.--without
| much great effect I might add. My brain was so wound up
| from a decade-plus of hyper-vigilance that I had actually
| forgotten how to relax.
|
| Obviously, I am not you and n=1, but hopefully it is
| encouraging to know that you might not always need to drown
| it out.
| progmetaldev wrote:
| When it comes to online reading, there are quite a few things
| that cause me fatigue that I don't feel I used to experience.
| Advertisements have been there for a long time, but often
| these are woven into the content, either as literal text
| placed in the article, or as visual ads that you need to
| scroll through to continue reading the article. Relying on
| different JavaScript and CSS techniques to "enhance" the user
| experience often cause me issues when I'm just trying to
| focus on reading. Those include overriding scrollbars,
| dynamic loading of content when the text is small enough to
| have been included in the page, and displaying some kind of
| alternative action when highlighting text. I'll often
| highlight text to keep track of where I'm reading, and some
| sites will pop up a dialog with share actions, or the ability
| to add annotations, etc. This is distracting and makes it
| more difficult to follow along with a longer article.
|
| I'm 45, and got my start on BBS pre-internet, but I feel like
| if I find an article without the distractions I mentioned
| above, I actually have more energy to complete an article
| than I did in my 20's and 30's. Having access to the article
| without distractions helps me to focus, and when I focus, I
| tend to consume more content than I normally would. Most
| likely one of the reasons we're drawn to HN.
| andai wrote:
| You've just made me realize why I usually avoid clicking
| the actual article link on HN. It's usually a very
| unpleasant experience, unless it's clear that it's a
| smaller website.
| mylastattempt wrote:
| Perhaps a small help for you might be "reader mode" or
| "focus mode" or whatever your browser of choice calls it.
|
| It's usually embedded in the url bar (probably a hotkey for
| it), and gives you only the text. A major step forward in
| not having to subconsciously ingest and then choose to
| ignore all the ads, related links, etc.
| progmetaldev wrote:
| Thank you, I'm not sure why I always seem to forget that
| feature. Although I don't like the Google lock-in, on
| certain sites I can also visit the AMP version of the
| page, and have fewer ads while also getting the images.
| andai wrote:
| Partly lower energy in general, though it would be
| interesting to try a "low information diet" and see what
| effect that has.
|
| If you're eating snacks all day, you won't have a healthy
| appetite for proper meals.
|
| I noticed on vacation I spend far less time online, and a lot
| more time reading books.
| yunusabd wrote:
| Thanks for the comment, I'm really enjoying the discussion it
| has sparked.
|
| Yes, I'm just taking the top comments, along with a few child
| comments, in order to not exceed the context window of the
| model.
|
| Regarding personalization, there's definitely lots of
| potential. HN can be so random though, sometimes you find
| things that you didn't even know you needed (intellectually). I
| guess as with most recommender systems, it's about a balance
| between exploration and exploitation. Maybe an MVP could filter
| for specific keywords and add those posts to the model input.
| pests wrote:
| > Yeah, the YouTube algorithm kind of does this, but you
| unfortunately have no real control over it.)
|
| You do, indirectly. Just need to curate your last watched
| videos.
|
| Sometimes I feel like I got put into a certain genre or bubble
| or if things autopplay a when I sleep I'll not ice my front
| page being taken over.
|
| I just go delete some of those videos from my recent list I can
| see visible improvement.
|
| Or just start a few video on the topic you want to see and then
| it's all you'll be recommended.
| Fnoord wrote:
| This is possibly an interesting extension [1]. I just
| generally don't follow recommendations. But my kids love it,
| and they use my account (Premium, else they get all kind of
| inappropriate ads (which is even illegal)), so I have to be
| careful. So the other day I wanted to look into what the
| other political side had to say about something. You know, as
| a matter of broadening my view to gain some understanding.
| Boy, did I regret, as I was getting sucked into some kind of
| conspiracy bubble. My wife asked me what on earth I watched.
| So I ended up trying to have YouTube profile me as little as
| possible (via settings). Didn't fully solve it, but it is
| much more clean now. And if I do watch something which I
| don't want to be remembered: private browsing mode. I do this
| for porn, but unfortunately they do profile my IP address (so
| I should use a VPN).
|
| [1] https://addons.mozilla.org/en-
| US/firefox/addon/regretsreport...
| andai wrote:
| I just deleted my account and switched to an old account and
| the quality of my recommendations improved by an order of
| magnitude.
|
| It's probably because I last used that one 10+ years ago when
| it seems things were a little more lighthearted (at least in
| my digital world). Going back to that recommendations page in
| current year was a truly magical experience.
|
| Of course it didn't last though, within a few weeks algorithm
| was onto me, and went back to showing me the same stuff as on
| my old account.
| neilv wrote:
| > _as I get older, I find that I have less energy for_
|
| Side comment: When a person says something like that, they
| might be speaking of only themself, but there's a different
| parsing that many will hear.
|
| Ageism is a real problem in our field, and one thing we can do
| is to not accidentally feed it.
| tusharnaik wrote:
| > Yeah, the YouTube algorithm kind of does this, but you
| unfortunately have no real control over it.
|
| Wouldn't that argument hold true even if it was implemented
| here?
| anonzzzies wrote:
| > as I get older, I find that I have less energy for reading,
|
| As I get older (50 now), I have 0 patience for anything else
| than reading; it's _much_ faster than listening and rereading
| stuff I didn 't get the first time is easier and faster. I
| listen to stuff (including zoom/calls) to stuff that doesn't
| hold much importance/value; maybe it triggers something, then I
| go read about it instead.
| nxpnsv wrote:
| Actually, I used to love reading, but the last years I've
| felt exactly like I had no energy to read any more, and have
| switched to audiobooks and podcasts. I then checked my eyes,
| and it turns out I need glasses. So as you get older, check
| your eyes!
| anonzzzies wrote:
| I have had glasses since I was 7... A year after my father
| brought home a 'portable computer' (luggable) [0] with a
| tiny monochrome screen. Not sure if that was related, but I
| guess it could be as the screen was very tiny (see pic
| below).
|
| [0] https://en.wikipedia.org/wiki/Osborne_1
| nxpnsv wrote:
| But he... what? :)
| keyaray wrote:
| Apparently, has no patience for writing too...;p
| nxpnsv wrote:
| Very retro cool though, destroying your eyes in style!
| dguest wrote:
| I think people have different definitions of "reading":
|
| - Skimming: In my day job this is 95% of "reading". I think
| this is unavoidable, since (even if the material is well
| written) there's very little chance that two consumers need
| the same information. In papers I read the abstract, jump to
| the conclusions, maybe go back to the intro if I'm confused,
| or check out the methods if that's what matters to me. I get
| frustrated with any medium where skimming isn't possible, and
| similar when search isn't possible.
|
| - Reading as in reading a book: this is more for fun or to
| cool down. Video / podcast seems like a drop-in replacement
| here. I don't read HN this way. Does anyone?
|
| I think people who create content should be aware of this
| dichotomy. If you are communicating with experts, make sure
| your information is well structured. If you are writing
| literature focus more on the flow.
| anonzzzies wrote:
| > I don't read HN this way. Does anyone?
|
| I skim HN, when I like something, I dive in & read it
| carefully and sometimes even implement it. The rest is just
| chewing gum; nice maybe but not serious.
| hunter2_ wrote:
| > Last.fm came out 20 years ago (proving you don't even need AI
| for amazing recommender systems)
|
| What makes that recommender system not AI? Wikipedia say it
| uses "collaborative filtering" which Gemini says is a form of
| AI. AI started nearly 70 years ago.
| pugio wrote:
| Love it. Reminds me of the also useful Hacker News Recap from
| wondercraft but it looks like that stopped updating as of October
| 1st (https://www.wondercraft.ai/our-podcasts/hacker-news).
|
| Would be great to have a playback speed button as well. (I can't
| sit through any audio at 1x.)
| yunusabd wrote:
| Same boat re: audio speed. I actually speed up the voice in the
| backend by 1.16x . Above that I was getting too many artifacts
| in the audio. The nice thing about doing it at that point is
| that I can handle the music and the voice separately, i.e. the
| speed of the music stays unchanged.
|
| Speeding it up in the player will also speed up the music,
| which is not very zen. But I guess I'll just add it to the
| player and let people decide how fast they want to go.
| yunusabd wrote:
| I added a basic speed setting, hope 3x is enough ;)
| pugio wrote:
| Excellent, thank you. This is something I can listen to!
| knowaveragejoe wrote:
| I like this idea a lot. Archived entries would be nice as others
| have suggested. It would also be nice to be able to control
| playback speed.
| yunusabd wrote:
| I added a basic speed setting, have a look! Also looking into
| the archive idea, which will be a bit more involved, since my
| current infra is kind of minimalist.
| srik wrote:
| Neat! Personally hourly feels a bit much but a daily briefing
| that can fit inside a commute or on a short walk would be
| perfect. Might be the first ai podcast I'd subscribe to.
| yunusabd wrote:
| That seems to be the general consensus, I think it makes sense
| to move in that direction and beef it up a little.
| olup wrote:
| I did https://radio-hn.pages.dev/ last year in the same idea,
| just once per day. Posted it somewhere here at the time.
| yunusabd wrote:
| Interesting, I actually did a search before submitting mine,
| but I narrowed it down to the last year only. Yours being 2y/o
| didn't show up. You were ahead of your time!
| olup wrote:
| There was also https://news.ycombinator.com/item?id=35831177
| some times after mine. Indeed a bit before the one year
| period from now.
| yunusabd wrote:
| Interesting, thanks for sharing! Looks like this one has
| stopped publishing since the end of September though.
| andai wrote:
| Damn, looks like you beat NotebookLM by a year and a half!
|
| Is the code for this available? I'm particularly curious how
| you did the multiple speakers and voices.
|
| NotebookLM has the issue that they keep switching sides, like
| one will be the student and the other the teacher on a subject,
| but then they'll suddenly switch in a way that makes no sense.
| olup wrote:
| I did not release the code but it's incredibly basic, and I
| believe OP's one is just the same.
|
| You collect N links from HN api with any heuristic you want,
| then scrape those urls - preferably using pupeteer-based
| tooling or online equivalent (think Jina).
|
| I then ran each url's content in an LLM to get a summary,
| then from all the results ask a LLM to create the
| conversation (and give it a tone). Then decide on the voices
| and characters and feed each turn into 11labs (or any tts).
| And finally, concatenate all audio parts, add music and
| effects.
|
| If I remember correctly, mine could perform all that from a
| single Cloudflare worker. The catch is it can become a bit
| pricey because of the TTS. I remember toying with making it a
| product (podcast everything) and quickly discovered there's a
| couple of company already offering this.
|
| NotebookLM is slightly different on the TTS front, I think
| they are using the amazing model google showed off a year or
| so ago (without giving it public access) that can generate
| actual multi speakers conversations with "hums" and cutting,
| and talking at the same time.
|
| Added : someone just made a python lib for the usecase (also
| found on HN 5 days ago)
| https://github.com/souzatharsis/podcastfy
| andai wrote:
| Thanks!
| kelsey98765431 wrote:
| Frankly this is super fantastic. Thank you. Any possibility to
| make this longer, and split it into sections with updates on
| previous stories at the end? I love this concept a lot.
| yunusabd wrote:
| Thank you! Most of the people here seem to prefer a longer
| form, so I think I'll move in that direction.
|
| > split it into sections with updates on previous stories at
| the end
|
| So basically, if a story comes up that has been reported on
| before, it references the older story and gives some context
| and the update? Something like "just last week, the Internet
| Archive had been the victim of another cyber-attack, in which
| [...]"?
| cchance wrote:
| Next step heygen avatar's doing desk presentations with small
| videos overlayed to show the websites etc.
| 8organicbits wrote:
| "although details remain sparse due to issues extracting content
| from the linked resource"
|
| Unfortunate that it adds stuff like this, which doesn't seem
| helpful to the listener.
| yunusabd wrote:
| Yep, some pages can't be read for some reason or another. I
| already added support for PDFs, I guess I'll handle more error
| cases as they pop up.
| yunusabd wrote:
| Did anyone notice it reporting about itself now? This will
| definitely go into the archive :)
| liamYC wrote:
| Haha yes!!
| gitaarik wrote:
| Haha indeed, got it as a last story
| personjerry wrote:
| "First up a webgpu wifi simulator has emerged, although details
| remain sparse due to trouble extracting data from the linked
| resource"
|
| Sounds about right
| yunusabd wrote:
| Yeah, if you look at the page source, there's actually no text
| in the document body. At one point I will have to use a JS-
| capable browser, to capture pages like this one.
| jonahx wrote:
| The AI voice is good. What are you using to generate it?
| yunusabd wrote:
| It's openAI's voice generator.
| fullstackchris wrote:
| Not affilliated, but if you want a large selection of
| _really_ good text to speech voices, check out eleven labs.
| Only problem is it's not cheap :/
| celltalk wrote:
| How much each hourly update costs? OpenAI pricing table says
| $15.000/M characters.
| breck wrote:
| Fun stuff. It does feel like NotebookLM (and others) are hurtling
| us toward a future that seems inevitable: all content is public
| domain, and people consume it in many transformed ways.
|
| Those that get ahead of the curve and make their content publicly
| available and semantically well structured will see their ideas
| thrive.
|
| Here's my user test:
| https://news.pub/?try=https://www.loom.com/embed/9e8b8d454ee...
| yunusabd wrote:
| Thanks for the video, it's really interesting to see a user
| test like this!
| syntaxing wrote:
| This is awesome, I wish it did a rolling 8 hour instead that is
| updated once a hour if that makes sense.
| yunusabd wrote:
| So the best of the last 8 hours, with a new episode every hour?
| I think that makes sense, you could check in every 8 hours or
| so and have a fresh set of stories.
| wg0 wrote:
| Unrelated but reminds me of GTA V's radio channels in cars. The
| news talking about what you just did.
| frays wrote:
| Great idea! I've always wanted to catch up with tech news while
| walking/driving, particularly from HN.
| the_arun wrote:
| Fantastic idea! I really liked extracting meta information from
| Comments as well. Good luck!
| cylinder714 wrote:
| Wow--this is indistinguishable from an NPR piece.
| neonsunset wrote:
| This is so good! I could use that mixed in together with a
| spotify station for modern Radio experience. I miss the days
| where you could just do something else and listen to the radio
| host. Streaming partially supplanted it but not to the same
| extent, sadly.
| throwaway0665 wrote:
| Pretty neat but it seems to make stuff up. It took a meta comment
| from this post[1] about the website formatting and suggested the
| community was worried the C++ memory safety proposal would make
| code hard to read on mobile. It is hard to trust the other
| summaries after hearing that.
|
| 1: https://news.ycombinator.com/item?id=41899828
| yunusabd wrote:
| True, that is not a good look.
|
| > This formatting and font mixing is difficult to read on
| mobile.
|
| I guess for us it's obvious that it's a meta comment, but I can
| understand the confusion. Still, it could have figured out that
| "readability on mobile" doesn't really apply to C++, a
| programming language.
|
| I'll add a section to the prompt reminding it that comments can
| be meta or even non-factual (gasp), so that it doesn't try to
| shoehorn meaning into comments like this one.
| Zopieux wrote:
| AI making stuff up? Unbelievable.
| andai wrote:
| Apparently you can add "don't make stuff up" to the prompt and
| it helps. I'm not sure the exact phrasing but probably
| something like only using what's in the text given.
| hammock wrote:
| Next step- create an HNN news network with chyrons and AI news
| anchors that you can have running on the TVs in your office 24/7
| the way banks have CNBC and Bloomberg News running
| noman-land wrote:
| I hate it but I also love it.
| laidoffamazon wrote:
| Im reminded of the talking heads in Batman Beyond that were
| presumably AIs.
| sen wrote:
| I would actually use that, especially if it had hourly
| summaries of the days news like some real news networks do, so
| you don't have to watch all day but could just chuck it on when
| convenient.
|
| The best part about these AI-reads-content things is the
| potential to let users do things like choose the voice, the
| talking speed, etc. As a non-American I hate listening to those
| American talking-head news channels because it's jarring for me
| when I'm used to my own accent, even if I do want to catch up
| on some current events or something.
| ag8 wrote:
| I started listening to it after this very submission became #1 on
| HN, so it was very meta to listen to it talk about how it might
| be making stuff up...
|
| Great project!
| n2d4 wrote:
| Hah! Here's what it had to say about itself this hour:
|
| > In a more self-referential turn, we examine the launch of HN
| Update itself. This initiative aims to provide hourly news
| broadcasts, summarizing top stories from Hacker News. While
| listeners appreciate the concept of curated news, there are
| concerns about the accuracy of the summaries and the potential
| for bias in representation. Community discussion suggests that
| while the value of such a service is evident, trust in the
| accuracy of the content remains a critical issue.
| kcrwfrd_ wrote:
| > in a more self-referential turn
|
| :o wow, the AI is becoming self-aware!
| yunusabd wrote:
| Tbf, there's a section in the prompt for this exact
| situation. Worth it just for this little wow moment.
| zhobbs wrote:
| is the prompt available somewhere?
| dash2 wrote:
| My version added "and yes, to our listeners... hi mom!"
|
| Very cute and kind of impressive.
| ugh123 wrote:
| Actually makes me think if its possible to embed prompts into
| story headlines and/or content to do nefarious things...
| waldothedog wrote:
| Enjoyed this a lot! Particularly enjoyed the meta update about
| this thread. There are some neat suggestions here, but if this
| could come up on my podcast feed as-is I would listen to it.
| tristenharr wrote:
| Would be cool to create embeddings for historical HN posts, and
| then use a users favorite posts to personalize the post selection
| by averaging the embedding vectors for a users favorite posts
| then doing a cosine similarity search to select stories most
| likely to be of interest to a user.
|
| Although it would be even better to use a users like history, but
| I'm not sure if/how those can be accessed.
|
| Speaking of, I'm curious how other folks use embeddings. I know
| you can average multiple embeddings together, but is anyone else
| doing other translations and having success? Thinking of King -
| Man + Women = Queen, It seems a lot of the time I see questions
| being directly used as inputs for semantic search/RAG. I wonder
| if it might make sense to create a large set of question-answer
| pairs and embed them and then determine the average translation
| to move from "question space" to "answer space", then when you
| embed questions you apply the translation on the embedding to
| move it into "answer space" before performing RAG, or maybe this
| would just add too much noise?
| vunderba wrote:
| hmmm, I can't speak to people using _word2vec_ in conjunction
| with RAG, but the other use case is actually pretty common.
| (you don 't need to generate answers though in my experience).
|
| For each document intended for ingestion into a vector
| database:
|
| - Use an LLM to generate a list of possible questions that the
| document is capable of answering (essentially equivalent to
| generating a quiz)
|
| - Map these question embeddings back to the original documents
|
| - Store document, document chunks, question 1, question 2, etc.
| into the vector database
|
| So now when a person queries your RAG, you have the direct link
| from user query -> doc chunks, but additionally the
| transitionary link from user query -> similar query -> doc
| chunk.
| withinboredom wrote:
| This assumes that favorites have some kind of meaning.
| Favorites are public (IIRC) and I basically use them to track
| and share interesting/funny comments. Upvotes on the other
| hand, are private and are more inline with the things I care
| about.
| andai wrote:
| I wonder if dang uses embeddings, or it just comes naturally.
| graycat wrote:
| Sounds good. Listened to some of it -- good.
|
| Suggestion, have better audio:
|
| (1) Enunciate the words more clearly.
|
| (2) To help with (1), slow down and speak fewer words per minute.
|
| (3) At the end of a sentence, don't drop voice volume and
| enunciation clarity.
| nurettin wrote:
| I wonder what it will do when it encounters a (year) postfix.
| interestingsoup wrote:
| This is so neat. I been wanting to build something for HN and
| can't believe I didn't think of this. It was also cool too hear
| the update with a mention of HN Update as well considering it's
| treanding! :)
| nilslice wrote:
| cool. and, a neat side effect of catching this late is that the
| HN Update broadcast I heard (labeled "10/20/2024, 9:59:47 PM",
| assuming Pacific time) included & described itself in the audio.
| at the time of writing, it's a top story currently on the front
| page!
| nabaraz wrote:
| On a related note, what are some cheaper alternative to Open AI's
| text to speech? Last I checked it came out to ~$9/day for their
| text-to-speech.
| TekMol wrote:
| Why is it that some people can accept - even like - music behind
| a voice that tells something?
|
| I strongly dislike it. It makes it harder to listen to the voice.
|
| Am I the only one?
| confused_boner wrote:
| should add option to turn off background music
| pegasus wrote:
| Not at all, I feel the same. In fact, last time I had that
| reaction was yesterday, listening to an audiobook which was
| employing the same dubious technique.
| anonzzzies wrote:
| No, it's pretty annoying really; I don't know why people do
| that. I don't like it on youtube/podcasts either. It adds
| nothing at all at best and distracts at worst.
| flakes wrote:
| Totally agree.
|
| There used to be a commercial that would play on Canadian TV
| stations. It showed the view of a river, once with calm and
| tranquil sounds and then played again with ominous sounds like
| from a horror movie. When you are presented the river with
| tranquil sounds, you are happy and calm. When you are presented
| the river with eerie sounds, you dislike it. The message at the
| end of the video was to inform Canadians to think more
| critically about the media they consume, and to question if
| they are being led down a forced narrative rather than being
| given facts to question for themselves.
|
| When I see modern day Reddit, Instagram, Facebook, etc, almost
| all of the videos are backed by music which is trying to bias
| the user. It makes me uncomfortable.
| andrewstetsenko wrote:
| +1
| yunusabd wrote:
| Thanks for the feedback, looks like you're not the only one.
| Personally I enjoy it, but I can understand that some might
| find it distracting.
|
| I just need to figure out a way to implement a toggle for the
| music, while also playing nicely with the playback speed etc.
| mmoustafa wrote:
| I enjoy it as well. Makes it easier to listen for me, voice
| alone is droning.
| johnneville wrote:
| the music is more distracting at higher speeds for me and i
| usually listen at 1.5x when walking or at the gym. you could
| have the music be a separate audio track where the playback
| speed doesnt impact it and the toggle plays it simultaneously
| with the vocal track or not.
| yunusabd wrote:
| The issue is that the voice track will be shorter than the
| music track if you speed it up. So you'll have the music
| playing until the end, but the voice track ending before
| that. It's definitely possible, just a bit more complex to
| implement. Maybe when I have the feature to mute the music,
| I can just mute the music when the speed is changed?
| weinzierl wrote:
| No, you are not the only one, background music is pretty common
| though.
|
| Often the background music is just too loud compared to the
| voice. Professional productions use a technique called
| _ducking_ , where the music is dynamically made quiet in
| relation to the volume of the voice.
|
| Personally, I prefer no background music at all, and I wonder
| if there is a case to made for the professionally balanced
| case?
| riiii wrote:
| It causes sensory overload for me, I abhor it.
| digitcatphd wrote:
| This is probably the coolest use case I have seen of HN API
| alwinaugustin wrote:
| This is awesome. I like it
| Guest9081239812 wrote:
| Lots of positive feedback here, but after a quick listen, I'm not
| a fan. To summarize my thoughts...
|
| 1. The experience just feels too sluggish. For example, I opened
| the HN homepage, skimmed all of the headlines, read the comments
| on the top post, and it probably took about 30 seconds. I was
| done, feeling like I got all the information from HN that I
| needed, with the intention of checking for new posts later in the
| day. This tool took an entire minute to brief me about a single
| post.
|
| 2. It's not very practical. Usually 1 or 2 posts catch my
| attention on the HN homepage each day. This tool is most likely
| going to give me information about the wrong posts. You could
| improve this with some type of algorithm that learns what
| information I listen to and what I skip, but it's not ideal. Or,
| perhaps I could click the headlines I'm interested in, and a
| custom audio summary is generated.
|
| 3. Lastly, I think it removes the human experience of HN. I like
| to read exactly what people are posting. Everyone is unique, and
| it's interesting to see how people interact, along with their
| choice of words and tone. Erasing all of that and listening to a
| robotic summary just sucks the soul straight out of the
| community. It reduces the connection to the people here, which I
| think is the best aspect of the site.
|
| Thanks for sharing though, it's interesting to see this idea
| brought to fruition.
| lynx23 wrote:
| You're mostly hinting at a very obvious shortcoming of
| synthesized speech: Its sequential. The phenomenon is most
| obvious if you look at screen readers using speech synthesis.
| Its a fundamental problem of the medium, which some devs will
| discover independently, now that tts has a new surge.
| loveparade wrote:
| Agree and I would add,
|
| 4. Skimming HN is useful in text-format because you can go
| deeper on something that catches your eye by following the
| link. The podcast format removes this because you can't click
| on something you hear and dive deeper into it. Skimming without
| the ability to dive into something is not useful, see next
| point.
|
| 5. High-level summaries are not my use case for HN, or any
| social media. They don't provide real value, just the illusion
| of value. What I want to dive deep into stories I am curious
| about. That can be done with TTS, but I would need to curate my
| feed first, and then use the podcast format to dive deeper into
| my curated stories.
|
| I almost feel like this product would be more useful if you
| remove the LLM aspect and instead let me paste a list of HN
| threads into it and just TTS all of them, including the full
| comments. Then I could listen to this long-form content while
| driving or doing something else.
| fragmede wrote:
| Or lean into it and have it speech-to-text as well you can
| interrupt it when it's reading a post you don't like so it
| can move onto the next one.
| highwaylights wrote:
| I think it's a case of this not fitting your use case.
|
| It wouldn't replace reading the front page for me but I could
| really see it replacing a podcast on my morning walk.
| Especially given the absence of news spin or adverts. I'll
| definitely be giving it a try tomorrow.
| Guest9081239812 wrote:
| I think you're right here. I'm forgetting about
| "entertainment".
|
| This will never replace my visits to HN because it's not
| efficient. Unless it uses neurolink to beam the information
| into my mind, that's always going to be the case. It fails in
| that way.
|
| However, let's consider a podcast. You get 5 people that are
| entertaining, knowledgeable about technology, well spoken,
| and have differing opinions, and get them to spend 30 minutes
| talking about the top HN posts. It's slow, they would most
| likely not even discuss my favourite posts, but yet, I would
| consider listening. Is it possible to replicate that with AI?
| Could AI digest the content and all of the comments, and turn
| it into an entertaining and educational discussion and debate
| between a few different AI voices?
|
| I think it's possible, and it changes the idea from being an
| inefficient method of summarizing content, to a form of
| entertainment. That could be the right direction to go with
| this kind of project. However, even if AI perfectly
| replicates a great podcast, how would I feel listening to it?
| I think this question applies to most AI content. How
| important is the human process in the content we consume? Do
| people only care about the end result, or do they want read a
| book written by a person, view photos taken by a person,
| listen to songs performed by a person, and listen to a
| podcast by real people?
| highwaylights wrote:
| This isn't what I had in mind, but now that you've
| suggested it I would absolutely listen to this. In fact,
| I'm convinced having read it that this is where we're going
| good or bad (I can see a lot of YouTube gurus suggesting
| this as the new get-rich-quick scheme for "creators"). A
| high quality version of this would absolutely work though
| if that can be achieved.
|
| I was thinking more in terms of the way you can get morning
| news briefs on a nest hub. The AI summarising the top posts
| on HN would have value to me as something to listen to in
| the morning not because I expect a really interesting
| debate, but mostly just to get a quick update on what the
| buzz is on HN on a given day so I can decide if I want to
| pick up the thread from any of those topics when my day
| starts at the desk.
| hunter2_ wrote:
| > the new get-rich-quick scheme for "creators"
|
| I wonder if the person executing the scheme would still
| be referred to as a "creator" in this case: they're
| creating a creator, and it's not so useful to have the
| same label for multiple layers (factory factories all the
| way down?). I could see possibly "engineer" (taken from
| "prompt engineer") or other technical terms being used
| instead of art terms.
| highwaylights wrote:
| Senior Bullshit Engineer
| afavour wrote:
| I don't want to overindex this point because at the end of
| the day this is just a fun hack project... but I do think
| it's worth considering the behaviors our work encourages.
|
| Much like I think the 24 hour news cycle is detrimental to
| just about everything, an _hourly_ HN summary strikes me as
| excessive. No one needs that much HN in their lives. But as
| you say, a daily summary you listen to the place of a
| podcast? That feels like the right fit.
| bloomingkales wrote:
| Depends. There's no such thing as too much news during ww2
| or Industrial Revolution.
|
| This is news about how news as we know it is going away,
| and there's more news on that coming 24/7. And that's just
| the news on the news.
|
| Idea for OP:
|
| If you treat an HN post and it's comments as a hivemind,
| you could do something like 'Interview with the Hivemind:
| (insert post topic)", have the AI ask interview questions
| where the hivemind can respond from the entire thread. This
| is to get any post into some kind of known podcast format.
|
| If you intersperse talk about Big Foot throughout that
| interview for no good reason, you could become the #1
| podcast in the world.
| wholinator2 wrote:
| What do you mean there's no such thing as too much news
| about war or capitalism (my interpretation of ww2 and
| industrial revolution)? I can't imagine your saying that
| interspersing your entire life with hourly updates on the
| deaths of millions of people is a... good? healthy?
| survivable thing? What about every 15 minutes? What about
| every second of every day? "No such thing" is certainly a
| strong phrase.
|
| I can certainly say that consumption of news above around
| 1-2 hours a day in myself and everyone I've had the
| pleasure to discuss this with is an increasingly bad
| thing. Especially war! If you spend all of your time just
| consuming news about things when do you have time to do
| things like live a fulfilling life or enjoy peaceful
| human existence. Continuous news is the opposite of
| peace.
|
| Maybe you're saying in general rather than in one
| person's life but i'd counter that a mass amount of news
| in general _is directly_ a mass amount of news in a mass
| amount of people's lives. Why would there be tons and
| tons of news unless people were actively consuming more
| and more of it?
|
| How many hours a day do you spend reading current events
| and news? Why don't you spend more? Your answer to that
| question is my rebuttal
| etewiah wrote:
| Wow this is awesome. I've actually been working on something
| very similar. In my case though I focus on individual stories.
| Like the commenter above I feel audio doesn't work so well for
| general overview.
|
| I haven't done a showHN yet because it's not quite ready but
| you can see where it's at here:
|
| https://news.gipety.com/hn/10842381/k/218/s/three-years-as-a...
|
| I think it would be quite a nice way to give a second life to
| classic episodes of past showHNs and askHNs.
| dsmurrell wrote:
| I like your project a lot! Please release it.
|
| I've been 'summarising' a lot of articles using NotebookLM's
| new feature and publishing them as podcasts episodes here:
| https://open.spotify.com/show/0C8DGPdYwZQ1cbvQsnvO6t
|
| I've been using their service to easily draw out the key
| points and if the episode is a good one then I publish it on
| the feed.
|
| I do think that for specific content, that a lot of gold is
| stored within the comments sections and reading those
| actually gives more insight than the article itself so I've
| been planning on doing a few which draw off comments from
| either a reddit or hacker posts which link out to some post.
| I'll probably do one from reddit first. Probably science
| focused.
| etewiah wrote:
| Thanks - I hope to be able to release it in the next few
| days.
|
| Finding the right content to use for the podcast is quite
| important and I'm trying to figure out if there is a way to
| involve the community. Currently I host the audio files and
| GitHub and anyone is invited to contribute to that.
|
| I checked out your Spotify and there is some good content
| there but I imagine it will be hard to rank on there.
|
| Would you be interested in collaborating? I am based in the
| UK and I have some ideas around location based podcasts as
| well.
| brandonchi wrote:
| I like it too. I enjoyed listening to it for 15 min
| straight.
| etewiah wrote:
| Great to hear - thanks. I will add several more over the
| coming days.
| fragmede wrote:
| Re: 3. The problem with reading HN on your phone is that it's
| generally frowned upon to do it while driving a car.
| smusamashah wrote:
| https://gist.github.com/SMUsamaShah/e7c9ed3936ba69e522f8cb38...
| This userscript (can use as a bookmarklet) lets you catchup to
| all _unseen_ stories quickly. Open HN, click bookmarklet, any
| new stories will be appended with a "(NEW)". Old stories, will
| show much their rank was changed. Can set a flag to hide seen
| stories, or set comment and points threshold to hide/show old
| stories.
|
| To me it makes it very quick to catchup. I just go over a few
| pages and can quickly see every new story that I have not _seen
| yet_.
| Hashex129542 wrote:
| Excellent Idea
| devops000 wrote:
| I see lots of generated content with AI, would be interested how
| much of this is actually listened by a real human after the first
| days of excitement.
| mazzystar wrote:
| Last week I had a similar idea as you. I created a webpage called
| https://zeli.app that automatically helps you parse the content
| of posts from the HN homepage, rewrite the titles, and generate
| abstracts.
|
| So, I ended up with these post fragments, and I tried feeding
| these title + abstract lists to Claude 3.5 Sonnet to string them
| together into a 5-minute English podcast, emphasizing on making
| these fragments flow cohesively.
|
| Honestly, I wasn't completely satisfied with the results because
| the topics switched too quickly, and each post only had 2-3
| sentence introductions, making it sound less interesting.
|
| Anyway, it was exciting to find someone with a similar idea as
| me, but I still think the lack of interesting content is the main
| issue.
| mazzystar wrote:
| Sample here:
|
| "Tech enthusiasts, welcome to 'Claude's Crazy Tech Emporium'!
| I'm your old friend Claude. Today, we're taking you on a
| fantastic tech journey, from the maze of subscription services
| all the way to nuclear-powered data centers. Fasten your
| seatbelts, we're taking off!
|
| First, let's talk about those love-hate subscription services.
| Ever tried to unsubscribe and couldn't find the exit? Like
| being stuck in a maze, looking everywhere but finding no way
| out. Don't worry, the U.S. Federal Trade Commission has heard
| our cries! They've recently introduced the 'Click to Cancel'
| rule. Imagine canceling a subscription as easily as deleting an
| ex's contact. Ah, the sweet taste of freedom! But don't get too
| excited, because...
|
| Amazon is tempting us again! They've just launched a series of
| new Kindles, including their first color Kindle and the all-new
| Kindle Scribe. Now you can not only read color e-books but also
| write and draw on them. It's the perfect gift for those who
| love doodling in paper books! But book lovers, beware, this
| isn't a license to scribble in library books. Speaking of
| which...
|
| Have you heard about the 'Transition Year' in the Irish
| education system? It's like a 'dream school year' for students!
| During this year, students can try various courses, from
| aeronautics to art, from programming to car maintenance. Isn't
| this like a real-life 'Hogwarts'? I even wonder if they have a
| course on 'How to Create Magic Books on Kindle'. But if you
| really want to experience magical technology, then...
|
| You must check out the Apple Vision Pro! Someone recently used
| this device that looks like it came straight out of a sci-fi
| movie on a plane. Imagine wearing this high-tech headset,
| watching 3D movies at 30,000 feet - fellow passengers might
| think you're a time traveler from 2050. Just a reminder, don't
| scream out loud if you're watching a horror movie, or the
| flight attendant might think you've spotted a UFO! Speaking of
| unidentified objects...
|
| Recently, someone benchmarked so-called 'AI PCs'. The results
| show that these computers might not be as intelligent as we
| imagined. It seems AI still prefers to roam in the cloud,
| reluctant to move into our computers permanently. Maybe AI
| thinks our computers are too cramped? But don't worry,
| because...
|
| Amazon is finding a new home for AI! They've recently quietly
| invested in a nuclear power developer. Looks like they're
| planning a 'nuclear' upgrade for their data centers! Imagine,
| every tweet you send might have a hint of nuclear energy. Don't
| worry, this won't turn your phone into a mini nuclear reactor.
| Although, if it did, we'd never have to worry about low battery
| again, right?
|
| Finally, let's look at the 'nuclear' war in the WordPress
| community. The dispute between Matt Mullenweg and WP Engine is
| more dramatic than 'Game of Thrones'. It seems even in the
| open-source world, court intrigue is unavoidable. Developer
| friends, besides coding, learn some workplace politics too. But
| remember, in the programming world, the one with the most
| beautiful code usually wins, not the one best at playing
| politics.
|
| Well, that's the end of our 'Crazy Tech Emporium' tour. From
| the maze of subscription services to nuclear-powered data
| centers, to power games in the open-source world, we've
| experienced quite a lot, haven't we? I hope you've had a good
| laugh and learned something on this crazy journey. I'm Claude,
| see you next time! Remember, in this crazy tech world,
| curiosity and a sense of humor are the best survival tools.
| Bye-bye!"
| andai wrote:
| Lack of interesting content?
| etewiah wrote:
| I like what you've done with zeli!!
|
| It is a shame it did not get so much traction when you did your
| showHn.
|
| One thing that I think would be useful alongside your summaries
| would be tags for each item. Have you considered that?
| Timwi wrote:
| I have two super nitpicky things to say.
|
| 1) The website is slightly wide on my phone, so it wiggles left
| and right when I scroll. I usually fix this by pinch-zooming out
| the tiny amount necessary to align it to my viewport width, but
| your website apparently suppresses zooming.
|
| 2) The AI announces itself as having the name "Jane Doe". What's
| the point in this? I know that American news with real anchors do
| this (having the anchor announce their own name), but this is not
| universal so it feels foreign to me. Since AIs don't have names,
| it feels like this was shoehorned in just to sound like American
| commercial news.
| yunusabd wrote:
| Thanks for the feedback!
|
| 1) That's strange, I don't do anything to prevent zooming.
| Although I could provoke a situation where I interacted with
| the player and it somehow captured all subsequent touch inputs,
| so zooming was blocked. Maybe that's what happened? Reloading
| the page should fix it.
|
| 2) I like it because it adds a bit of personality. And I felt
| like the generic name "Jane Doe" would be fitting for an AI.
| Kind of hinting at the fact that it _seems_ like a human, but
| it 's not. Also low-key telling you that the whole thing is AI
| generated, in case you don't pick up on it immediately.
| Adachi91 wrote:
| Interesting project, I think it would be nice to also have a
| volume slider as well as a speed slider. I manually set the
| volume via wavesurfer.media.volume = 0.10; to keep from hurting
| my ears.
| yunusabd wrote:
| I just had the biggest "duh" moment. Thanks for bringing it up.
| yunusabd wrote:
| Now with state-of-the-art volume control for all your volume-
| control needs!
| redbell wrote:
| Pretty interesting project. I have a special, yet weird,
| emotional attachment to these HN-based projects because they act
| like _extensions_ or _add-ons_ that could improve HN in one
| dimension.
|
| While I don't feel like using this tool when I sit in front of my
| computer or when starting _doom scrolling_ on my phone, I
| certainly would like to use it when I need to _quickly_ check HN
| while being busy.
|
| Some quick feedback:
|
| 1. First, regarding the UI/UX: - The title and
| subtitle don't tell much about the app. - In the audio
| track, while you can see the progress of the playing audio, it
| doesn't show the total time nor the current time. - It
| would be useful to highlight the audio track into segments, each
| one representing a story. - It would make sense to mention
| how many stories are being summarized (seems to be 5 right now).
|
| 2. For a better use case, I believe it would make more sense to
| have this tool as a mobile app or a PWA to easily access it even
| from your car's infotainment system while driving.
|
| 3. Tightly linked to (2), having this tool as a mobile app and
| making it available as a _widget_ , with a _Play_ button, would
| reduce the number _taps_ needed to play the broadcast.
|
| I hope this serves as a _constructive critic_.
| yunusabd wrote:
| Thanks a lot, all very good points!
| pjmq wrote:
| It was pretty cool to hear the broadcast reference this. 100%
| think it should be more concise and have a greater depth of
| personality.
| cengizhanbasak wrote:
| I would love to have a transcript of the generated podcast.
| ck2 wrote:
| vaguely related someone also made a Hacker News bot on Bluesky
|
| https://bsky.app/profile/newsycombinator.bsky.social
| crossroadsguy wrote:
| Is there a way to filter out certain type of stories/submissions?
|
| Or is there any HN filter or web-reader (if any) that can help me
| do that? I know HN doesn't do submission tags but still if
| something allows some kind of "type/kind" hiding/removal.
| cthellla wrote:
| its actually been done, but in slightly different manner
|
| https://t.me/hninsights/836?comment=441
| ProllyInfamous wrote:
| Can you make one of the playback speeds 1.25x (it jumps from 1.0x
| to 1.5x)?
| gigatexal wrote:
| I would like this except for it to be a daily podcast of the
| unique set of links and things that made it to the front page
| with more than 5 comments ordered by points and then comments and
| then have that read out to me with a summary of the comments. Now
| that. That would be amazing.
| bangaroo wrote:
| i think this is cool, i'm happy you did it... i really listen to
| podcasts for the hosts, though. i think the banter and the
| personality and the perspective are things that i really enjoy.
| getting to know people through what they choose to talk about or
| how they frame things is part of the whole charm.
|
| if i want a fast rundown of HN, i'll read HN. you did make me
| kind of crave a 15 minute weekdaily "morning news" style podcast
| with some tech journalists that runs down the most talked about
| HN posts, though.
| mvdtnz wrote:
| AI slop generator.
| aanet wrote:
| Fantastic idea, good implementation. Very valuable and useful!
|
| Do not listen to the chattering nabobs of negativity in the
| comments!
|
| Your impl is valuable; gives a quick summary of top-n stories.
| Useful for somebody who dips in/out of HN now and then. It may
| not be for everyone (indeed, as various commenters have
| suggested), but its useful for me. And it;s a great example of
| marrying AI-generated summary with podcast style quick 5-min
| summary. Just like listening to BBC news summary.
|
| A few suggestions: - perhaps make it personalizable (based on HN
| user?) or atleast provide an option to summarize top 15 (or 10 or
| 20?) stories - offer a way to go beyond the first page of HN -
| offer a way to summarize the most-commented stories
|
| Good job! Happy to contribute if its on Github
| nostoneunturned wrote:
| Amazing, I would love to do a version of this for more niches.
| Any pointers on how you built this?
| tarwich wrote:
| I'd love to see a list of the articles covered so as I'm
| listening I could jump to an article and get more data.
| ugh123 wrote:
| Can the speed slider support .1 increments? I'd prefer 1.2x :)
|
| Also, it would be useful to have an index of Stories on the side
| for each segment and possibly locators within the horizontal
| audio segment where index/story items are located.
| rstat1 wrote:
| Not sure this is something I'd regularly use just because I
| prefer reading the news to listening to it, but I still found it
| pretty cool.
___________________________________________________________________
(page generated 2024-10-21 23:01 UTC)