Show HN: Copilot for Your Sales Team
2 by ashgam | 0 comments on Hacker News.
Tuesday, 2 January 2024
New Show Hacker News story: latest news
Show HN: Future of Niche Search Engines
2 by rstnpce | 0 comments on Hacker News.
“Google is slowly dying.” is a phrase I hear surprisingly often these days and I think there is some truth to it. Yet, it is barely the whole truth. That being said, I wonder why this is, if it's true at all and also what the future of search engines—or gathering information in general—will look like… By now we all know that Perplexity AI, ChatGPT and all the other LLMs are able to answer your questions just like Google does (oftentimes even better, without the unnecessary clutter). But why is it that I still sometimes default to Google and its archaic keyword search instead of the conversational, human way of looking up stuff? IMO there are three reasons: 1) It’s faster. 2) It does the job. 3) It doesn’t require you to interact with it like a human(!) Let’s zoom in on the 3rd point first, because I think this is the most insightful one. To do so, I want you to think about your last interaction with an LLM… I’m sure something like this happened: You made an effort to say “please” and “thank you”. Probably you have also thought about how to prompt your chatbot in a way that “it” didn’t feel stressed out in anticipation of a superior result (“imagine yourself in a calm and focused state”). Or maybe you have even looked up the best ways to prompt your LLM to get the best result (very meta…). I can assure you, you are not alone and this happens to me all the time. I know ChatGPT has a temper more often than not and it doesn’t feel a 100% like a machine anymore (everything is a little uncertain)… To be honest with you, I don’t think this is the UX that we all want. It’s just something that we put up with in return for intel that we wouldn’t get otherwise. With simple info, however, we would never want to have these thoughts nor the delay in the answer. We just need an accurate (2) and quick result (1) (e.g., “capital of switzerland” => “bern”). Something that good ol’ Google Search does exceptionally well. But with the “Google is dying” premise defied, the big question remains: What will the future of search engines look like? Also, how are keyword search and LLMs handling requests that are in-between super simple and highly complex? Will it be a smart combination of both or something entirely different? In a shameless thrill of the shill, I’m presenting a prototype of a “niche search engine” that might partially answer this question. Kampadre allows you to search in a keyword-like fashion with quick results but AI in the background to understand what you truly want. The way it works is that you first describe your (marketing) goals (keywords or full sentence) (e.g., “i want to have more sales of product x online”). Afterwards, the request gets translated into choosing between a predefined set of filters which then outputs your desired result in no time. Like this, 'smartness', accuracy, and quickness are in balance for the optimal UX. If you wanna take a look you can try it under the link provided. Of course, this is just one way future search engines for everything in between highly complex and easy information could handle requests and serve results improved by AI. But I’m sure you have other ideas or suggestions. Thanks for reading until here!
2 by rstnpce | 0 comments on Hacker News.
“Google is slowly dying.” is a phrase I hear surprisingly often these days and I think there is some truth to it. Yet, it is barely the whole truth. That being said, I wonder why this is, if it's true at all and also what the future of search engines—or gathering information in general—will look like… By now we all know that Perplexity AI, ChatGPT and all the other LLMs are able to answer your questions just like Google does (oftentimes even better, without the unnecessary clutter). But why is it that I still sometimes default to Google and its archaic keyword search instead of the conversational, human way of looking up stuff? IMO there are three reasons: 1) It’s faster. 2) It does the job. 3) It doesn’t require you to interact with it like a human(!) Let’s zoom in on the 3rd point first, because I think this is the most insightful one. To do so, I want you to think about your last interaction with an LLM… I’m sure something like this happened: You made an effort to say “please” and “thank you”. Probably you have also thought about how to prompt your chatbot in a way that “it” didn’t feel stressed out in anticipation of a superior result (“imagine yourself in a calm and focused state”). Or maybe you have even looked up the best ways to prompt your LLM to get the best result (very meta…). I can assure you, you are not alone and this happens to me all the time. I know ChatGPT has a temper more often than not and it doesn’t feel a 100% like a machine anymore (everything is a little uncertain)… To be honest with you, I don’t think this is the UX that we all want. It’s just something that we put up with in return for intel that we wouldn’t get otherwise. With simple info, however, we would never want to have these thoughts nor the delay in the answer. We just need an accurate (2) and quick result (1) (e.g., “capital of switzerland” => “bern”). Something that good ol’ Google Search does exceptionally well. But with the “Google is dying” premise defied, the big question remains: What will the future of search engines look like? Also, how are keyword search and LLMs handling requests that are in-between super simple and highly complex? Will it be a smart combination of both or something entirely different? In a shameless thrill of the shill, I’m presenting a prototype of a “niche search engine” that might partially answer this question. Kampadre allows you to search in a keyword-like fashion with quick results but AI in the background to understand what you truly want. The way it works is that you first describe your (marketing) goals (keywords or full sentence) (e.g., “i want to have more sales of product x online”). Afterwards, the request gets translated into choosing between a predefined set of filters which then outputs your desired result in no time. Like this, 'smartness', accuracy, and quickness are in balance for the optimal UX. If you wanna take a look you can try it under the link provided. Of course, this is just one way future search engines for everything in between highly complex and easy information could handle requests and serve results improved by AI. But I’m sure you have other ideas or suggestions. Thanks for reading until here!
New Show Hacker News story: latest news
Show HN: A tool to transcribe and summarize WhatsApp audio notes and audio files
2 by oalessandr | 0 comments on Hacker News.
Hello HN, and happy new year! Towards the end of last year I finally released AudioBriefly, a tool that transcribes and summarizes your voice notes. It doesn't require installing any apps, and also works on WhatsApp. I know that there are competing services out there but the main advantages are: - Speed: we perform optimizations on the audio files to be able to transcribe them quickly - Punctuation: some of the competing services don't add punctuation to the transcription, which makes it a pain to read. - Price: we are cheaper than most competitors out there for the regular user - Web UI: some competitors only provide a whatsapp bot, while we also have a mobile-friendly web UI. - Ease of use: I've tried to make it super easy to use for anyone. If you want to try it out, I've created a discount code that makes you try the "Chatty" plan free for a month: just use the SHOWHN code at checkout. To prevent abuse the discount expires at 2024-01-08T00:00 UTC and can be redeemed for max 100 times. Looking forward to your feedback!
2 by oalessandr | 0 comments on Hacker News.
Hello HN, and happy new year! Towards the end of last year I finally released AudioBriefly, a tool that transcribes and summarizes your voice notes. It doesn't require installing any apps, and also works on WhatsApp. I know that there are competing services out there but the main advantages are: - Speed: we perform optimizations on the audio files to be able to transcribe them quickly - Punctuation: some of the competing services don't add punctuation to the transcription, which makes it a pain to read. - Price: we are cheaper than most competitors out there for the regular user - Web UI: some competitors only provide a whatsapp bot, while we also have a mobile-friendly web UI. - Ease of use: I've tried to make it super easy to use for anyone. If you want to try it out, I've created a discount code that makes you try the "Chatty" plan free for a month: just use the SHOWHN code at checkout. To prevent abuse the discount expires at 2024-01-08T00:00 UTC and can be redeemed for max 100 times. Looking forward to your feedback!
Monday, 1 January 2024
New Show Hacker News story: latest news
Show HN: I made TV Sort, a web-based game for ranking TV show episodes
12 by pocketarc | 7 comments on Hacker News.
Over this Christmas break, while discussing the best episodes of Frasier with my mother (as we tend to do when I get to see her), I thought about coming up with something that's less arbitrary than 1-10 ratings. The result is TV Sort. It just uses a sorting algorithm, but... it's human powered. When the algorithm needs to compare two items, it asks you to compare them, and with that you end up with a full, thoroughly sorted episode list. It uses TMDB, IMDB, and Wikipedia to extract episode information for any show, to help jog your memory when making episode comparisons. It was a fun little experiment. And finally, I know -exactly- what I think the best and worst episodes are.[0] Would love to hear your feedback, this is my first Show HN. ;) Edit: I wrote a whole blog post about what went into making it, if anyone wants to read more of the technical detail behind it.[1] [0]: https://ift.tt/nq21NrU... [1]: https://ift.tt/I0NBOjn...
12 by pocketarc | 7 comments on Hacker News.
Over this Christmas break, while discussing the best episodes of Frasier with my mother (as we tend to do when I get to see her), I thought about coming up with something that's less arbitrary than 1-10 ratings. The result is TV Sort. It just uses a sorting algorithm, but... it's human powered. When the algorithm needs to compare two items, it asks you to compare them, and with that you end up with a full, thoroughly sorted episode list. It uses TMDB, IMDB, and Wikipedia to extract episode information for any show, to help jog your memory when making episode comparisons. It was a fun little experiment. And finally, I know -exactly- what I think the best and worst episodes are.[0] Would love to hear your feedback, this is my first Show HN. ;) Edit: I wrote a whole blog post about what went into making it, if anyone wants to read more of the technical detail behind it.[1] [0]: https://ift.tt/nq21NrU... [1]: https://ift.tt/I0NBOjn...
New Show Hacker News story: latest news
Show HN: I Made a Lisp
4 by ventuspilot | 1 comments on Hacker News.
Hi all, powerful open-source Lisp implementations are a dime a dozen, why not try JMurmel instead? The language is inspired by Common Lisp, except it's a Lisp-1, and it is mostly a subset of CLtL-1. Jmurmel can be used standalone with or without the Repl, for "#!"-style hashbang scripts or embedded in a Java program. It features [documentation for the core language]( https://ift.tt/aFLlxUw ) as well as [documentation for the default library]( https://ift.tt/AgYC0Sv ), a REPL, an interpreter, a compiler, macros, backquotes, [turtle-]( https://ift.tt/BmQSqp7 ) and (simple) [bitmap graphics]( https://ift.tt/ihYEWxu ). It is implemented in Java (compatible with Java8..22-ea) with some library functions and macros implemented in itself. Code is on [Github]( https://ift.tt/pnG0gaI ), the latest release with a precompiled jar (or alternatively a Windows .exe-style launcher) is at [Release V 1.4.5]( https://ift.tt/693D4lV... ). A Repl example: JMurmel> ((lambda (x) (list x (list (quote quote) x))) (quote (lambda (x) (list x (list (quote quote) x))))) ==> ((lambda (x) (list x (list (quote quote) x))) (quote (lambda (x) (list x (list (quote quote) x))))) JMurmel> Any feedback is welcome and thanks for reading.
4 by ventuspilot | 1 comments on Hacker News.
Hi all, powerful open-source Lisp implementations are a dime a dozen, why not try JMurmel instead? The language is inspired by Common Lisp, except it's a Lisp-1, and it is mostly a subset of CLtL-1. Jmurmel can be used standalone with or without the Repl, for "#!"-style hashbang scripts or embedded in a Java program. It features [documentation for the core language]( https://ift.tt/aFLlxUw ) as well as [documentation for the default library]( https://ift.tt/AgYC0Sv ), a REPL, an interpreter, a compiler, macros, backquotes, [turtle-]( https://ift.tt/BmQSqp7 ) and (simple) [bitmap graphics]( https://ift.tt/ihYEWxu ). It is implemented in Java (compatible with Java8..22-ea) with some library functions and macros implemented in itself. Code is on [Github]( https://ift.tt/pnG0gaI ), the latest release with a precompiled jar (or alternatively a Windows .exe-style launcher) is at [Release V 1.4.5]( https://ift.tt/693D4lV... ). A Repl example: JMurmel> ((lambda (x) (list x (list (quote quote) x))) (quote (lambda (x) (list x (list (quote quote) x))))) ==> ((lambda (x) (list x (list (quote quote) x))) (quote (lambda (x) (list x (list (quote quote) x))))) JMurmel> Any feedback is welcome and thanks for reading.
New Show Hacker News story: latest news
Show HN: I help people reduce their stress with one comforting quote a day
2 by pomdevv | 0 comments on Hacker News.
Hi HN, Made this little service where people can subscribe and receive a comforting message as a text through whatsapp, each day. I hope it helps alleviate some of the stress in their life :)
2 by pomdevv | 0 comments on Hacker News.
Hi HN, Made this little service where people can subscribe and receive a comforting message as a text through whatsapp, each day. I hope it helps alleviate some of the stress in their life :)
New Show Hacker News story: latest news
Show HN: Durdraw – a modern ANSI art editor for modern Unix terminals
5 by indyjoenz | 3 comments on Hacker News.
I've been working on an ANSI art editor off and on for a while. It works like a traditional ANSI text editor, except it supports 256 colors, Unicode and CP437 encoding, frame-based animation, custom UI themes, terminal mouse input, HTML and IRC color output, and runs in Utf-8 terminals. It's written in Python and curses, and is fairly portable across Unix systems. If you have ever used TheDraw or Aciddraw, the user interface is similar. It can also load/convert, view, edit and save most CP437 (MS-DOS style) ANSI art in a Utf-8 terminal, so you can view ANSI artscene packs in the comfort of your favorite terminal, and even convert them into 256 color Unicode ANSI. I've been using it for my own ANSI and ASCII art for a number of years, and hope this will help artists work with less restrictions. I think there is a lot of opportunity for ANSI art beyond its dominant 16-color Code Page 437 format. We all have computers with amazing ANSI terminals with modern features. Shouldn't they be the natural home for making text art? It's still a work in progress, and I'm always adding features. Thanks for checking it out!
5 by indyjoenz | 3 comments on Hacker News.
I've been working on an ANSI art editor off and on for a while. It works like a traditional ANSI text editor, except it supports 256 colors, Unicode and CP437 encoding, frame-based animation, custom UI themes, terminal mouse input, HTML and IRC color output, and runs in Utf-8 terminals. It's written in Python and curses, and is fairly portable across Unix systems. If you have ever used TheDraw or Aciddraw, the user interface is similar. It can also load/convert, view, edit and save most CP437 (MS-DOS style) ANSI art in a Utf-8 terminal, so you can view ANSI artscene packs in the comfort of your favorite terminal, and even convert them into 256 color Unicode ANSI. I've been using it for my own ANSI and ASCII art for a number of years, and hope this will help artists work with less restrictions. I think there is a lot of opportunity for ANSI art beyond its dominant 16-color Code Page 437 format. We all have computers with amazing ANSI terminals with modern features. Shouldn't they be the natural home for making text art? It's still a work in progress, and I'm always adding features. Thanks for checking it out!
Subscribe to:
Posts (Atom)