4 News Express

Saturday, December 17, 2022

Show HN: 4-7-8 Breathing – BreathWithMe.io https://ift.tt/vlJ9inh

Show HN: 4-7-8 Breathing – BreathWithMe.io Hello, Let's take a few deep breaths together. https://ift.tt/yIRnkjs December 18, 2022 at 03:44AM

पिता की संपत्ति में बेटियों का हक इस्लाम के खिलाफ:केरल सरकार की नई योजना पर भड़के मौलवी, बोले- महिलाएं सिर्फ एक-चौथाई प्रॉपर्टी की हकदार

via देश | दैनिक भास्कर https://ift.tt/BcTYO3L

Show HN: Speleomorph, an Exploration Puzzle https://ift.tt/VOCMEXm

Show HN: Speleomorph, an Exploration Puzzle https://ift.tt/ajlwGY2 December 18, 2022 at 02:19AM

Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts https://ift.tt/09Z7SUJ

Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts This is a quick prototype I built for semantic search and factual question answering using embeddings and GPT-3. It tries to solve the LLM hallucination issue by guiding it only to answer questions from the given context instead of making things up. If you ask something not covered in an episode, it should say that it doesn't know rather than providing a plausible, but potentially incorrect response. It uses Whisper to transcribe, text-embedding-ada-002 to embed, Pinecone.io to search, and text-davinci-003 to generate the answer. More examples and explanations here: https://twitter.com/rileytomasek/status/1603854647575384067 https://ift.tt/zfIq1aG December 17, 2022 at 11:35PM

Friday, December 16, 2022

पठान विवाद में स्वरा की एंट्री:कहा- नेताओं की नजर एक्ट्रेसेस के कपड़ों पर; नीतीश बोले- दारू पीकर मरने वालों को मुआवजा नहीं

via देश | दैनिक भास्कर https://ift.tt/zOL5pTd

पठान विवाद में स्वरा की एंट्री:कहा- नेताओं की नजर एक्ट्रेसेस के कपड़ों पर; राहुल गांधी बोले- जय सियाराम, नॉट जय श्रीराम

via देश | दैनिक भास्कर https://ift.tt/1CcSFVJ

CJI ने बिजली चोरी के दोषी को रिहा किया:बोले- कोई केस छोटा नहीं; रिजिजू ने कहा था- सुप्रीम कोर्ट छोटे नहीं, संवैधानिक मामले सुने

via देश | दैनिक भास्कर https://ift.tt/3VnuL2Z

Show HN: I made a Slack bot that qualifies your sign-ups using GPT-3 https://ift.tt/dwDf0bJ

Show HN: I made a Slack bot that qualifies your sign-ups using GPT-3 OP here, this was super fun to build. It all started from playing around with Nat Friedman's GPT browser https://twitter.com/0xferruccio/status/1599014988693180417 Then after having this running for our product for a couple of days or so we decided to give 10 customers access and they loved it! So expanding access now feels great :) https://ift.tt/b5x2UCi December 15, 2022 at 09:00PM

आंध्र में TDP-YSR कांग्रेस कार्यकर्ताओं के बीच हिंसक झड़प:पालनाडु में वर्कर्स ने एक-दूसरे पर पत्थर फेंके, आगजनी की; धारा 144 लागू

via देश | दैनिक भास्कर https://ift.tt/dl1wv6U

भास्कर अपडेट्स:CBI ने मेहुल चोकसी के खिलाफ 6700 करोड़ रुपए के फ्रॉड केस में 3 नई FIR दर्ज कीं

via देश | दैनिक भास्कर https://ift.tt/loybWGu

Thursday, December 15, 2022

Show HN: I'm challenging your clicking speed with this game I rebuilt https://ift.tt/LXuAWTZ

Show HN: I'm challenging your clicking speed with this game I rebuilt https://ift.tt/FSHLNql December 16, 2022 at 02:15AM

महंत बोले- पठान फिल्म लगे तो थिएटर फूंक दो:विवाद पर शाहरुख का बयान आया; एसिड अटैक केस में फ्लिपकार्ट मुश्किल में

via देश | दैनिक भास्कर https://ift.tt/IoVAWUN

Show HN: Natural language Twitter search using Codex https://ift.tt/z5oYQ74

Show HN: Natural language Twitter search using Codex We built a structured search engine for Twitter called Bird SQL, available at https://ift.tt/HQZOch0 . Our search interface uses OpenAI Codex to translate natural language to SQL. Our backend then verifies the SQL, executes it, and displays the results on the web app. This makes large structured datasets like a scrape of Twitter easy for anyone to explore. As background, while working on text-to-SQL as a general problem, we came to believe one of its most powerful applications is as a search tool because: - SQL is hard to write by hand and prone to errors - It allows you to iterate quickly if you’re exploring a new dataset - A lot of contextual information that you’d normally have to internalize (e.g. your data’s schema) can be automatically generated and offloaded to the language model Using large language models (LLMs) like Codex to write the SQL for you means you don’t have to worry about the nitty gritty language details, but still benefit from the power of a language like SQL. Also, after seeing the results of the query, you can inspect (and if necessary, change) the SQL. The lack of this sort of explainability of the query result is one of the more notorious challenges of returning the output of an LLM directly to the user. Additionally, using LLMs in this way makes these kinds of queries over structured data accessible to people who know little or no SQL. While Bird SQL shares significant infrastructure with our more general LLM-powered search engine over unstructured data (Ask Perplexity - https://perplexity.ai[1] ), the two approaches and their respective challenges are quite different. For example, the type of models are different (GPT3.5 vs Codex), obviously the model prompts have different structure, and how to verify model output when its text vs when it's code is different. We are currently exploring ways to combine the two approaches, such as using the results of retrieving information from a structured source (as in Bird SQL) as one of the inputs for the LLM to interpret or summarize (as in Ask Perplexity). We would love to hear your questions, suggestions, and feedback! [1] https://ift.tt/Xx0kSFp https://ift.tt/TKuZmNr December 16, 2022 at 03:42AM

भास्कर अपडेट्स:महाराष्ट्र के नवी मुंबई में दो कारों में टक्कर, पांच लोग घायल

via देश | दैनिक भास्कर https://ift.tt/u03Sjyc

संयुक्त राष्ट्र में महात्मा गांधी की प्रतिमा पर मोदी बोले:ये देखकर हर भारतीय को गर्व हो रहा

via देश | दैनिक भास्कर https://ift.tt/n4mgJLP

Show HN: Readwise Reader, an all-in-one reading app https://ift.tt/mMsJUPd

Show HN: Readwise Reader, an all-in-one reading app Hey HN, cofounder of Readwise here. We've been working on this cross-platform reader app for about 2 years, excited to finally share it in public beta. Probably the most notable thing that makes Reader unique is that it supports almost any content type you could want to save/read/highlight: * web pages * emails/newsletters * PDFs * ePubs * twitter threads * youtube videos (with transcripts) * RSS feeds With all of your knowledge content in one place, we built powerful reading and highlighting, as well as a bunch of novel triage/organization features, so you can actually consume & stay on top of that content! There are also a lot of advanced features too, such as text-to-speech, GPT3 questions/summaries, super powerful highlighting (that includes markup and images), complex filtering/search (with our own query language), sleek mobile triage UI, keyboard shortcuts for reading/everything, integrations with note-taking apps, a browser extension for both saving pages and highlighting them, and much more. If anyone's interested in more product details, as well as our business model, etc, we wrote a detailed launch post: https://ift.tt/7l4ctL2... Predicting a common question: Reader is part of the Readwise subscription pricing right now in beta -- there's a 30 day free trial and then it's paid at ~$8usd/month. We also promise to not raise this price for existing subscribers. Reader is also fairly technically interesting -- our iOS, Android and webapp all work fully offline and sync your reading data/progress with eachother. Our search on web is built with wasm sqlite. We have a fairly intense pipeline for cleaning web articles (removing ads/styling). We share lot of modules around syncing/highlighting across all platforms, etc... Happy to answer any questions :) https://ift.tt/r9fnXhm December 16, 2022 at 03:14AM

Wednesday, December 14, 2022

हरियाणा के मंत्रियों की 2 घंटे पार्टी ऑफिस में ड्यूटी:CM को खटकी जनता-वर्करों से दूरी; खुद तैयार करेंगे शेड्यूल, दिन अलॉट होंगे

via देश | दैनिक भास्कर https://ift.tt/PylnYkh