4 News Express

Friday, December 9, 2022

Show HN: Live AI Avatars for videochats and streaming https://news.ycombinator.com/item?id=33926322

Show HN: Live AI Avatars for videochats and streaming https://ift.tt/v3laOJM December 10, 2022 at 02:20AM

तलाक पर केरल हाईकोर्ट का बड़ा फैसला:ईसाई कपल को डाइवोर्स के लिए सालभर तक अलग रहना जरूरी नहीं

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

Show HN: Panoptisch – A recursive dependency scanner for Python projects https://ift.tt/4MnVZIp

Show HN: Panoptisch – A recursive dependency scanner for Python projects Hello all, Very excited to share this project with you all! Panoptisch scans your Python file or module to find it's imports (aka dependencies) and recursively does so for all dependencies and sub-dependencies. It then generates a dependency tree in JSON for you to parse and enforce import policies. Supply chain attacks are no joke, and this is one way to transparently analyze your dependencies to see if any malicious imports are taking place. For example, your yaml parser, nor it's sub-dependencies should import socket, or sys. Panoptisch is in early stages, with known limitations (for now). I welcome feedback, testing and contributions. Also, happy to answer any questions! https://ift.tt/8kMsimA December 10, 2022 at 03:15AM

BeSanta: Real time Santa Claus AI avatars on your iPhone Oh-oh-oh https://ift.tt/5KbxV7B

BeSanta: Real time Santa Claus AI avatars on your iPhone Oh-oh-oh https://ift.tt/Snwg9NA December 10, 2022 at 02:40AM

भास्कर अपडेट्स:राजस्थान में बॉर्डर पर पाकिस्तान ने BSF जवानों पर की फायरिंग, कोई हताहत नहीं

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

Show HN: I fine-tuned Flan-T5. Can it cook? https://ift.tt/bhGDlvu

Show HN: I fine-tuned Flan-T5. Can it cook? Checkout the app at https://www.lechef.fyi https://ift.tt/6t8rizG December 10, 2022 at 12:30AM

Thursday, December 8, 2022

ट्रांसजेंडर भर्ती मामले में महाराष्ट्र सरकार से कोर्ट नाराज:दो पद न रखने पर जताई नाराजगी, भर्ती प्रक्रिया रोकने की दी चेतावनी

via देश | दैनिक भास्कर https://ift.tt/cZM1RQn

मोरबी न महंगाई, सिर्फ मोदी; रेवड़ी पर भारी पड़ा राष्ट्रवाद:सौराष्ट्र की 48 में इस बार रिकॉर्ड 46 सीटें, पिछली बार से 27 ज्यादा

via देश | दैनिक भास्कर https://ift.tt/7q3JCKo

Show HN: This VC Does Not Exist https://ift.tt/FejrQBy

Show HN: This VC Does Not Exist Everything on this page was created with DallE and ChatGPT (other than the title) It's using a single session token for ChatGPT - so you're probably going to hug it to death. Hosted on cloudflare workers. Source code: https://ift.tt/3v2P6pG https://ift.tt/yPV1qrY December 9, 2022 at 01:28AM

भास्कर अपडेट्स:TMC सांसद का दावा- प्रवक्ता साकेत गोखले को जमानत के बाद गुजरात पुलिस ने फिर किया गिरफ्तार

via देश | दैनिक भास्कर https://ift.tt/oJjr6xe

Show HN: Web search using a ChatGPT-like model that can cite its sources https://ift.tt/q9BKUcg

Show HN: Web search using a ChatGPT-like model that can cite its sources We’ve trained a generative AI model to browse the web and answer questions/retrieve code snippets directly. Unlike ChatGPT, it has access to primary sources and is able to cite them when you hover over an answer (click on the text to go to the source being cited). We also show regular Bing results side-by-side with our AI answer. The model is an 11-billion parameter T5-derivative that has been fine-tuned on feedback given on hundreds of thousands of searches done (anonymously) on our platform. Giving the model web access lessens its burden to need to store a snapshot of human knowledge within its parameters. Rather, it knows how to piece together primary sources in a natural and informative way. Using our own model is also an order of magnitude cheaper than relying on GPT. A drawback to aligning models to web results is that they are less inclined to generate complete solutions/answers to questions where good primary sources don’t exist. Answers generated without underlying citable sources can be more creative but are prone to errors. In the future, we will show both types of answers. Examples: https://ift.tt/Bt5wWVP https://ift.tt/D6mAiqd... https://ift.tt/zSFR5D2... https://ift.tt/awgUloj... Would love to hear your thoughts. https://ift.tt/XV714Ch December 8, 2022 at 11:23PM

Wednesday, December 7, 2022

राहुल गांधी ब्रेकफास्ट करने घर आए, मालकिन बाहर:सिक्योरिटी चेक न होने से 40 मिनट इंतजार करती रही महिला

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

Show HN: Let AI to generate beautiful art prints https://ift.tt/5o96gAz

Show HN: Let AI to generate beautiful art prints hi, I was working last few months on service where you can easily generate beautiful art images using machine learning algorithm called stable diffusion. Additionally, service is offering possibility to print your favourite images on high quality acrylic sheet and deliver it to you so that you can put them on your wall. What do you think? Best, Wiktor https://www.simulai.co/ December 8, 2022 at 01:46AM

भास्कर अपडेट्स:अर्जेंटीना की उपराष्ट्रपति को करप्शन मामले में 6 साल की सजा

via देश | दैनिक भास्कर https://ift.tt/zj5PQpk

Show HN: We used ChatGPT to write a blogpost about using ChatGPT to write emails https://ift.tt/ZfKzgOD

Show HN: We used ChatGPT to write a blogpost about using ChatGPT to write emails https://ift.tt/dbvlcJH December 8, 2022 at 12:34AM

Show HN: Music quiz web app powered by Spotify API https://ift.tt/9ulvWVd

Show HN: Music quiz web app powered by Spotify API I had some time over and decided to put together this idea I had for a few years. A music quiz based on a playlist on Spotify. https://introquiz.se/ December 7, 2022 at 06:21PM

Tuesday, December 6, 2022

Show HN: I designed a ChatGPT prompt evaluator to ruin your fun;) https://ift.tt/XZzN6eQ

Show HN: I designed a ChatGPT prompt evaluator to ruin your fun;) Today I designed a method to prevent users from jailbreaking ChatGPT (for instance, users have generated instructions to produce weapons or illegal drugs, commit a burglary, kill oneself, take over the world as an evil superintelligence, or create a virtual machine which they then can use). The OpenAI team appears to be countering these primarily using prompt engineering or fine-tuning on the ChatGPT model. The idea is to use a second and fully separate, fine-tuned LLM to evaluate prompts before sending them to ChatGPT. You can test this by inserting your successful ChatGPT jailbreaks. Break it for me if you dare! I look forward to seeing your results! https://ift.tt/G8vaE4U December 6, 2022 at 11:16PM