The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Personalized book recommendations with Librarian AI
Show HN: Personalized book recommendations with Librarian AI
Show HN: GPT-4-powered web searches for developers
Hi HN,<p>Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search.<p>GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a step-by-step guide complete with citations (<a href="https://phind.com/search?cache=0fecf96b-0ac9-4b65-893d-8ea5708db222">https://phind.com/search?cache=0fecf96b-0ac9-4b65-893d-8ea57...</a>) while Phind in default mode meanders a bit and answers the question very generally (<a href="https://phind.com/search?cache=dd1fe16f-b101-4cc8-8089-ac56defb228d">https://phind.com/search?cache=dd1fe16f-b101-4cc8-8089-ac56d...</a>).<p>GPT-4 is significantly more concise and “systematic” in its answers than our default model. It generates step-by-step instructions over 90% of the time, while our default model does not.<p>We’re particularly focused on ML developers, as Phind can answer questions about many recent ML libraries, papers, and technologies that ChatGPT simply cannot. Even with ChatGPT’s alpha browsing mode, Phind answers technical questions faster and in more detail.<p>For example, Phind running on “Expert” GPT-4 mode can concisely and correctly tell you how to run an Alpaca model using llama.cpp: (<a href="https://phind.com/search?cache=0132c27e-c876-4f87-a0e1-cc48f07ccc20">https://phind.com/search?cache=0132c27e-c876-4f87-a0e1-cc48f...</a>). In contrast, ChatGPT-4 hallucinates and writes a make function for a fictional llama.cpp.<p>We still have a long way to go and would love to hear your feedback.
Show HN: GPT-4-powered web searches for developers
Hi HN,<p>Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search.<p>GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a step-by-step guide complete with citations (<a href="https://phind.com/search?cache=0fecf96b-0ac9-4b65-893d-8ea5708db222">https://phind.com/search?cache=0fecf96b-0ac9-4b65-893d-8ea57...</a>) while Phind in default mode meanders a bit and answers the question very generally (<a href="https://phind.com/search?cache=dd1fe16f-b101-4cc8-8089-ac56defb228d">https://phind.com/search?cache=dd1fe16f-b101-4cc8-8089-ac56d...</a>).<p>GPT-4 is significantly more concise and “systematic” in its answers than our default model. It generates step-by-step instructions over 90% of the time, while our default model does not.<p>We’re particularly focused on ML developers, as Phind can answer questions about many recent ML libraries, papers, and technologies that ChatGPT simply cannot. Even with ChatGPT’s alpha browsing mode, Phind answers technical questions faster and in more detail.<p>For example, Phind running on “Expert” GPT-4 mode can concisely and correctly tell you how to run an Alpaca model using llama.cpp: (<a href="https://phind.com/search?cache=0132c27e-c876-4f87-a0e1-cc48f07ccc20">https://phind.com/search?cache=0132c27e-c876-4f87-a0e1-cc48f...</a>). In contrast, ChatGPT-4 hallucinates and writes a make function for a fictional llama.cpp.<p>We still have a long way to go and would love to hear your feedback.
Show HN: GPT-4-powered web searches for developers
Hi HN,<p>Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search.<p>GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a step-by-step guide complete with citations (<a href="https://phind.com/search?cache=0fecf96b-0ac9-4b65-893d-8ea5708db222">https://phind.com/search?cache=0fecf96b-0ac9-4b65-893d-8ea57...</a>) while Phind in default mode meanders a bit and answers the question very generally (<a href="https://phind.com/search?cache=dd1fe16f-b101-4cc8-8089-ac56defb228d">https://phind.com/search?cache=dd1fe16f-b101-4cc8-8089-ac56d...</a>).<p>GPT-4 is significantly more concise and “systematic” in its answers than our default model. It generates step-by-step instructions over 90% of the time, while our default model does not.<p>We’re particularly focused on ML developers, as Phind can answer questions about many recent ML libraries, papers, and technologies that ChatGPT simply cannot. Even with ChatGPT’s alpha browsing mode, Phind answers technical questions faster and in more detail.<p>For example, Phind running on “Expert” GPT-4 mode can concisely and correctly tell you how to run an Alpaca model using llama.cpp: (<a href="https://phind.com/search?cache=0132c27e-c876-4f87-a0e1-cc48f07ccc20">https://phind.com/search?cache=0132c27e-c876-4f87-a0e1-cc48f...</a>). In contrast, ChatGPT-4 hallucinates and writes a make function for a fictional llama.cpp.<p>We still have a long way to go and would love to hear your feedback.
Show HN: GrammarDaily – daily bite-sized grammar lessons
Hey everyone, I'm Utku! So, I just whipped up this fun little MVP for GrammarDaily, and I'd absolutely love for you lovely people to give it a try! It's a bit modest in features at the moment, but hey, that's where your awesome thoughts and ideas come in handy!<p>I'll be adding fresh grammar lessons every day and spicing things up with new features every week. Feel free to drop any suggestions, comments, or questions you might have. You can also reach me directly through my email at utku@usegrammardaily.com.
Show HN: Semantic Search on AWS Docs
Show HN: Semantic Search on AWS Docs
Show HN: Wolverine: Give your Python scripts regenerative healing abilities
Run your scripts with Wolverine and when they crash, GPT-4 edits them and explains what went wrong. Even if you have many bugs it will repeatedly rerun until it's fixed.<p>Demo video on twitter: <a href="https://twitter.com/bio_bootloader/status/1636880208304431104" rel="nofollow">https://twitter.com/bio_bootloader/status/163688020830443110...</a>
Show HN: Wolverine: Give your Python scripts regenerative healing abilities
Run your scripts with Wolverine and when they crash, GPT-4 edits them and explains what went wrong. Even if you have many bugs it will repeatedly rerun until it's fixed.<p>Demo video on twitter: <a href="https://twitter.com/bio_bootloader/status/1636880208304431104" rel="nofollow">https://twitter.com/bio_bootloader/status/163688020830443110...</a>
Show HN: Oasis AI – Craft Emails, Essays and Notes, Just by Talking
I’m Yousif, founder/CTO of OASIS AI, a new iOS app to elevate your communication skills.<p>https://apps.apple.com/us/app/oasis-ai/id1668222944<p>OASIS AI transforms natural speech into polished writing—college essays, business emails, social media posts, journals, and more. Everything is instant, automatic and efficient. and efficiency. It’s very simple.<p>Let’s face it: humans communicate constantly, but we suck at it.<p>We want to use LLMs to go beyond Grammarly's error correction and Google Translate's word-for-word translation. Instead, OASIS refines your thoughts and intentions, choosing the perfect words to express your ideas in any format or language. The app gives you a first draft, a starting place, and then you’re in control from there.<p>OASIS started off as English–to-English, and we are now in the process of rolling out language translation and speech transcription for over 30 languages, including Chinese, Japanese, Spanish, and Arabic. As a preview, the app enables English speakers to craft WeChat posts that mimic the casual writing of a native Mandarin Chinese speaker.<p>What do you think? What features should we add? How can we be better?<p>https://theoasis.com/
Show HN: Oasis AI – Craft Emails, Essays and Notes, Just by Talking
I’m Yousif, founder/CTO of OASIS AI, a new iOS app to elevate your communication skills.<p>https://apps.apple.com/us/app/oasis-ai/id1668222944<p>OASIS AI transforms natural speech into polished writing—college essays, business emails, social media posts, journals, and more. Everything is instant, automatic and efficient. and efficiency. It’s very simple.<p>Let’s face it: humans communicate constantly, but we suck at it.<p>We want to use LLMs to go beyond Grammarly's error correction and Google Translate's word-for-word translation. Instead, OASIS refines your thoughts and intentions, choosing the perfect words to express your ideas in any format or language. The app gives you a first draft, a starting place, and then you’re in control from there.<p>OASIS started off as English–to-English, and we are now in the process of rolling out language translation and speech transcription for over 30 languages, including Chinese, Japanese, Spanish, and Arabic. As a preview, the app enables English speakers to craft WeChat posts that mimic the casual writing of a native Mandarin Chinese speaker.<p>What do you think? What features should we add? How can we be better?<p>https://theoasis.com/
Show HN: Skip the SSO Tax, access your user data with OSS
As the former CTO of an Insurtech and Fintech startup I always had the “pleasure” to keep regulators and auditors happy. Think of documenting who has access to what, quarterly access reviews, yearly audits and so on…<p>Like many others we couldn’t justify the Enterprise-plan for every SaaS tool to simply get access to SSO and SCIM/SAML APIs. For Notion alone the cost would have nearly doubled to $14 per user per month. That’s insane! Mostly unknown to people, SSO Tax also limits access to APIs that are used for managing user access (SCIM/SAML).<p>This has proven to be an incredibly annoying roadblock that prevented me from doing anything useful with our user data:
- You want to download the current list of users and their permissions? Forget about it!
- You want to centrally assign user roles and permissions? Good luck with that!
- You want to delete user accounts immediately? Yeah right, like that's ever gonna happen!<p>It literally cost me hours to update our access matrix at the end of every quarter for our access reviews and manually assigning user accounts and permissions.<p>I figured, there must be a better way than praying to the SaaS gods to miraculously make the SSO Tax disappear (and open up SCIM/SAML along the way). That’s why I sat down a few weeks ago and started building OpenOwl (<a href="https://github.com/AccessOwl/open_owl">https://github.com/AccessOwl/open_owl</a>). It allows me to just plug in my user credentials and automatically download user lists, including permissions from SaaS tools.<p>Granted, OpenOwl is still a work in progress, and it's not perfect. At the moment it's limited to non-SSO login flows and covers only 7 SaaS vendors. My favorite part is that you can configure integrations as “recipes”. The goal was for anybody to be able to add new integrations (IT managers and developers alike). Therefore you ideally don’t even have to write any new code, just tell OpenOwl how the new SaaS vendor works.<p>What do you think? Have you dealt with manually maintaining a list of users and their permissions? Could this approach get us closer to overcoming parts of the SSO Tax?
Show HN: Skip the SSO Tax, access your user data with OSS
As the former CTO of an Insurtech and Fintech startup I always had the “pleasure” to keep regulators and auditors happy. Think of documenting who has access to what, quarterly access reviews, yearly audits and so on…<p>Like many others we couldn’t justify the Enterprise-plan for every SaaS tool to simply get access to SSO and SCIM/SAML APIs. For Notion alone the cost would have nearly doubled to $14 per user per month. That’s insane! Mostly unknown to people, SSO Tax also limits access to APIs that are used for managing user access (SCIM/SAML).<p>This has proven to be an incredibly annoying roadblock that prevented me from doing anything useful with our user data:
- You want to download the current list of users and their permissions? Forget about it!
- You want to centrally assign user roles and permissions? Good luck with that!
- You want to delete user accounts immediately? Yeah right, like that's ever gonna happen!<p>It literally cost me hours to update our access matrix at the end of every quarter for our access reviews and manually assigning user accounts and permissions.<p>I figured, there must be a better way than praying to the SaaS gods to miraculously make the SSO Tax disappear (and open up SCIM/SAML along the way). That’s why I sat down a few weeks ago and started building OpenOwl (<a href="https://github.com/AccessOwl/open_owl">https://github.com/AccessOwl/open_owl</a>). It allows me to just plug in my user credentials and automatically download user lists, including permissions from SaaS tools.<p>Granted, OpenOwl is still a work in progress, and it's not perfect. At the moment it's limited to non-SSO login flows and covers only 7 SaaS vendors. My favorite part is that you can configure integrations as “recipes”. The goal was for anybody to be able to add new integrations (IT managers and developers alike). Therefore you ideally don’t even have to write any new code, just tell OpenOwl how the new SaaS vendor works.<p>What do you think? Have you dealt with manually maintaining a list of users and their permissions? Could this approach get us closer to overcoming parts of the SSO Tax?
Show HN: TurboPilot: Copilot clone runs code completion LLM on your CPU
Hi HN,<p>I spent my easter weekend stuck in the house with COVID and I decided to play with llama.cpp [1] and fauxpilot [2] to see if I could get LLM code assist working on pure CPU.<p>As a proof of concept I'd say I've proven that it's possible. However there's still a lot to do. The auto complete is quite slow at the moment. PRs welcome.<p>[1] <a href="https://github.com/ggerganov/llama.cpp">https://github.com/ggerganov/llama.cpp</a><p>[2] <a href="https://github.com/fauxpilot/fauxpilot">https://github.com/fauxpilot/fauxpilot</a>
Show HN: TurboPilot: Copilot clone runs code completion LLM on your CPU
Hi HN,<p>I spent my easter weekend stuck in the house with COVID and I decided to play with llama.cpp [1] and fauxpilot [2] to see if I could get LLM code assist working on pure CPU.<p>As a proof of concept I'd say I've proven that it's possible. However there's still a lot to do. The auto complete is quite slow at the moment. PRs welcome.<p>[1] <a href="https://github.com/ggerganov/llama.cpp">https://github.com/ggerganov/llama.cpp</a><p>[2] <a href="https://github.com/fauxpilot/fauxpilot">https://github.com/fauxpilot/fauxpilot</a>
Show HN: ThoughtCoach: Helping to improve mental health with AI
Show HN: ThoughtCoach: Helping to improve mental health with AI
Show HN: The HN Recap – A daily podcast that recaps the top HN posts of the day
The podcast is produced entirely using AI tools. We welcome your feedback on all aspects including the following:<p>Clarity of post summaries: Are the summaries easy to understand? Would you like them to be more or less detailed?
Top 10 focus: Should we continue featuring the top 10 posts or consider covering more or fewer posts?
Background music: Do you enjoy the music in the background, or would you prefer a music-free podcast?
Synthetic voice recognition: Were you able to identify that the voice is AI-generated?
Additional suggestions: If you have any other ideas for improvement, please feel free to share.
Create your own podcast by visiting <a href="https://podcast.wondercraft.ai/" rel="nofollow">https://podcast.wondercraft.ai/</a>
Show HN: The HN Recap – A daily podcast that recaps the top HN posts of the day
The podcast is produced entirely using AI tools. We welcome your feedback on all aspects including the following:<p>Clarity of post summaries: Are the summaries easy to understand? Would you like them to be more or less detailed?
Top 10 focus: Should we continue featuring the top 10 posts or consider covering more or fewer posts?
Background music: Do you enjoy the music in the background, or would you prefer a music-free podcast?
Synthetic voice recognition: Were you able to identify that the voice is AI-generated?
Additional suggestions: If you have any other ideas for improvement, please feel free to share.
Create your own podcast by visiting <a href="https://podcast.wondercraft.ai/" rel="nofollow">https://podcast.wondercraft.ai/</a>