Show HN: Q&A with AI Trained on Bankruptcy Law https://bit.ly/3DP14QC

Show HN: Q&A with AI Trained on Bankruptcy Law I crawled a #$%^ ton of bankruptcy case law and pointed a LLM at it to answer bankruptcy legal questions. I just tried it on the Supreme Court's request today in its order stopping the Purdue Pharma settlement[1], and it gives a decent answer. > The parties are directed to brief and argue the > following question: Whether the Bankruptcy Code authorizes a > court to approve, as part of a plan of reorganization under > Chapter 11 of the Bankruptcy Code, a release that extinguishes > claims held by nondebtors against nondebtor third parties, > without the claimants’ consent. ChatLaw's answer: The Bankruptcy Code does not explicitly authorize a court to approve, as part of a plan of reorganization under Chapter 11, a release that extinguishes claims held by non-debtors against non-debtor third parties, without the claimants’ consent. However, courts have interpreted certain provisions of the Bankruptcy Code to permit such non-consensual third-party releases under certain circumstances. The relevant provisions of the Bankruptcy Code include Section 105(a), which empowers the court to issue any order, process, or judgment that is necessary or appropriate to carry out the provisions of this title, and Section 1123(b)(6), which allows a plan to include any other appropriate provision not inconsistent with the applicable provisions of this title. In the case of In re: Mallinckrodt PLC, (District of Delaware, 02/08/2022), the court noted that while Section 524(e) of the Bankruptcy Code should be read to preclude non-debtor releases, releases are not the equivalent of a discharge. The court also noted that the Third Circuit has recognized that bankruptcy courts do have statutory and constitutional authority to approve a plan of reorganization that contains non-consensual third-party releases, albeit, only in extraordinary cases. In the case of In Re: 18-13374-mew Aegean Marine Petroleum Network Inc. (Southern District ofNew York, 2019-04-08), the court noted that some Circuit Courts of Appeal have held that bankruptcy courts lack the power to grant nonconsensual third-party releases of the kind that the Debtors seek here. However, other Courts of Appeal, including the Second Circuit Court of Appeals, have held that bankruptcy courts have the power to impose involuntary releases, but that such involuntary releases should be imposed only in rare cases. In the case of 22-110 In re: Purdue Pharma L.P. (Second Circuit Court of Appeals, 5/30/2023), the court concluded that two sections of the Bankruptcy Code, 11 U.S.C. 105(a), 1123(b)(6), jointly provide the statutory basis for the bankruptcy courts authority to approve a plan that includes nonconsensual releases of third-party claims against non-debtors. The court further held that the bankruptcy courts inclusion of the releases is equitable and appropriate under the specific factual circumstances of this case. In the same case, in a concurring opinion, Judge Richard C. Wesley agreed that a bankruptcy court has the authority to approve a Chapter 11 reorganization plan that includes nonconsensual nondebtor releases, based on the court's precedent in In re Drexel Burnham Lambert Grp., Inc., 960 F.2d 285, 293 (2d Cir. 1992). However, he expressed concerns about the lack of explicit statutory basis for such releases in the Bankruptcy Code. In conclusion, while the Bankruptcy Code does not explicitly authorize non-consensual third-party releases, courts have interpreted certain provisions of the Code to permit such releases under certain circumstances. The permissibility of such releases often depends on the specific facts and circumstances of the case, and courts have cautioned that such releases should be approved only in rare cases. [1] https://cnn.it/3DP15nE... https://bit.ly/3DP16Ie August 11, 2023 at 12:58AM

Show HN: ChatKey – Supercharge your productivity with ChatGPT and AutoHotkey https://bit.ly/47ppWMp

Show HN: ChatKey – Supercharge your productivity with ChatGPT and AutoHotkey https://bit.ly/3rDoNQQ August 10, 2023 at 05:11PM

Show HN: Open-Source Web App with User Interface for AutoML on Tabular Data https://bit.ly/47ppPjX

Show HN: Open-Source Web App with User Interface for AutoML on Tabular Data https://bit.ly/47oEGv4 August 10, 2023 at 05:09PM

Show HN: Netdata released v1.42 and it includes 800 integrations https://bit.ly/3OmSOfq

Show HN: Netdata released v1.42 and it includes 800 integrations https://bit.ly/3On8Mq4 August 10, 2023 at 10:00AM

Show HN: A Strategic Guessing Game https://bit.ly/47EJahp

Show HN: A Strategic Guessing Game https://bit.ly/3KBSOr7 August 10, 2023 at 08:10AM

Show HN: Applite – Clean Homebrew front end app for macOS built with SwiftUI https://bit.ly/3qrsGrX

Show HN: Applite – Clean Homebrew front end app for macOS built with SwiftUI https://bit.ly/3ORXA64 August 10, 2023 at 02:13PM

Show HN: Computer Socialism https://bit.ly/3Ox9AIU

Show HN: Computer Socialism https://bit.ly/3YsW7q8 August 10, 2023 at 11:13AM

Show HN: Easiest way to convert PDF tables to Excel https://bit.ly/45hhXzL

Show HN: Easiest way to convert PDF tables to Excel We built a Windows app to convert PDF tables to Excel. You just have to take a screenshot of the table. Why try another app when there's so many PDF to Excel converters? It is: - Faster - More convenient - More accurate than other converters (including Excel's Power Query). Feel free to test it with complex tables (like the ones found in financial documents). https://bit.ly/46WVlFH August 10, 2023 at 01:35AM

Show HN: Traxoft – Easy Image Voting Shopify App https://bit.ly/3DPktko

Show HN: Traxoft – Easy Image Voting Shopify App https://bit.ly/3ONXaxA August 9, 2023 at 11:38AM

Show HN: I'm 17 and wrote this guide on how CPUs run programs https://bit.ly/45kfUdx

Show HN: I'm 17 and wrote this guide on how CPUs run programs https://bit.ly/3OPjyGX August 9, 2023 at 02:33PM

Show HN: Infracost (YC W21): Be proactive with your cloud costs https://bit.ly/45iAqeE

Show HN: Infracost (YC W21): Be proactive with your cloud costs Hi, we are Ali, Hassan, and Alistair, co-founders of Infracost (https://bit.ly/3q0dSel). Infracost helps engineers see the cost of each Terraform change before launching resources. When changes are made, it posts a comment with the cloud cost impact. For example, “you’ve added 2 instances and volumes, and change an instance type from medium to large, your bill will increase by 25% next month, from $1000 to $1250 per month”. We launched in February 2021 (https://bit.ly/3q0AHPl), and Infracost is now being actively used by over 3,000 companies. However, there is a shift happening in the cloud cost management space. New teams, called FinOps teams (a combination of "Finance" and "DevOps"), are being formed within companies to manage cloud costs. One of the first tasks assigned to these teams is to determine "who is using what" - that is, which teams, business units, products, etc. are spending the most on cloud. To accomplish this, they use tags. Tags are labels that all cloud resources should have and are key-value pairs. For example, a server could be tagged with: product=HackerNews; environment=production; team=blueTeam. So if resources are not tagged properly, then you can’t tell who is using what. However, FinOps teams face challenges because their tools are reactive. These tools begin by analyzing cloud bills and providing visibility of tags from there. This means that they are looking at resources that are already running in production and costing money. A customer recently shared, “I want all resources to be properly tagged. But if they are not, I would rather a resource not be tagged at all than be tagged incorrectly.” My "aha" moment! FinOps teams can define a tagging policy that can be validated in CI/CD before resources are launched. This is important because if code is shipped with the wrong tags, FinOps teams will have to fight for sprint time to fix them. Even if you shut down an untagged resource directly in the cloud, the next time Terraform runs, the resource will launch again with no tag. You need to fix the issue at its root. I’d love your feedback on our solution to the tagging problem. You define your tag key-value policy in our SaaS product, and Infracost checks all Terraform resources per change. If anything fails the policy, it posts a comment with the details of which resources need tags, and what the allowed values are. Once fixed, it will let the code be shipped to production. Try it out by going to https://bit.ly/3qnXOZw, setting up with the GitHub app or GitLab app, and defining your tagging policy. It will then scan your repository and inform you of any missing tags and their file and line number. You can use the free trial, but if you need more time, please message me and I’ll extend it for you. I would also love to hear how others ensure that the correct tag keys and values are applied to all resources, and whether this is done proactively or reactively. Additionally, I would be interested in hearing about any lessons learned in the process. Cheers August 9, 2023 at 02:01PM

Show HN: Social Bellow – AI-Powered Interactive Companion https://bit.ly/45jyjal

Show HN: Social Bellow – AI-Powered Interactive Companion Greetings HN, My name is Edgar and I've created Social Bellow, an AI chat companion. Before this I spent close to a decade working on games with Grumpyface Studios, working closely with Cartoon Network as well as managing my own business. I've built Social Bellow out of the need to manage prompts and eliminate the repetitive task of copying and pasting the same prompts. Storing prompts has the added advantage of providing Large Language Models (LLMs) with more context, thereby facilitating structured content responses. Moreover, I saw the necessity for a tool that could maintain the context window during conversations with the LLMs. Social Bellow was built using AWS Amplify, NextJS, and the help of Vercel to do the streaming. Figma has also helped tremendously in the creation of the project. Having a workflow of Figma, Amplify Studio, and Git continuous deployment has cut down on the time to publish a change. Social Bellow is free to use with OpenAI GPT-3.5 Turbo with a token allowance of 50,000 tokens a month. I've just launched this so you'd be one of the first to try it out. Thank you for the feedback and helping improve the application! https://bit.ly/3QES1cu August 9, 2023 at 09:10AM

Show HN: Minimal note-taking app https://bit.ly/3OPyQvx

Show HN: Minimal note-taking app No accounts, barely any UI chrome. Web-based note taking app with real-time collaboration. Visiting homepage generates a new note with a unique URL. https://bit.ly/45mlD2M August 9, 2023 at 08:39AM

Show HN: MagicQuit – closes apps when you don't use them anymore (free) https://bit.ly/3DMEc46

Show HN: MagicQuit – closes apps when you don't use them anymore (free) I often end up having 15+ applications open in my Dock. And, unfortunately, I tend to never close them. While Arc Browser does a great job for browser tabs, I didn’t find any fully satisfying solution for MacOS. One used way too much power and the other one would have taken quite some time to set it up. So instead I decided to develop an app which took x times more of my free time. MagicQuit is entirely free, open source, 100% offline and closes apps that you haven’t been using in the last 12 hours (customizable). Feature-wise I wanted to keep it as clean and simple as possible. It also uses nearly ~0% of cpu usage. Give it a try if you’re a Mac user and also having the same issue with many open applications: https://bit.ly/3KybkAp https://bit.ly/3KybkAp August 9, 2023 at 12:48PM

Show HN: Kvak.io – Online note-taking app https://bit.ly/3E7NTKZ

Show HN: Kvak.io – Online note-taking app Web-based note taking app with real-time colab. No accounts, barely any UI. Visiting the homepage generates a new note with a unique URL. https://bit.ly/45mRJLw August 9, 2023 at 08:55AM

Show HN: The Population Project https://bit.ly/44Yd91L

Show HN: The Population Project Two years ago, I turned 50. After a successful career as an entrepreneur, a business angel and a novelist, I set out to start a philanthropic venture under the following constraints: - it had to be global. - it had to be beautiful (in my eyes, at least). - it had to be technology and stats driven. I decided I would try to list the full name and date of birth of all humans alive. While some may find the concept pointless, I immediately knew I had struck gold: - it was global and incredibly hard. - it had an almost artistic quality to it, like an ever-changing installation. - as a libertarian, I resent that states conduct censuses and then sit on the data. - One billion people in the world aren't officially registered. At least someone would acknowledge their existence. I created a non-profit called The Population Project. I would never make a dime off it, but at least my costs would be tax-deductible. I then started researching lists of names online. I quickly adopted two principles. First I would collect a minimal set of information : full name, birth date, and birth place. Second, I would only scrape public information, i.e. nothing behind a password. After a few months, I realized I needed help from more experienced developers. I chose to work on 4D, a platform I had used in the past to develop my company's information system. It was a tough choice: 4D is not a leading player in the back-end world, but I figured the growth of API tooling would make language choice less critical. The first iteration of our database was frustrating - way too slow to publish a website. I learned the power of incremental change, with each marginal improvement saving you a few percent of speed or space. I also got to implement concepts I had heard about but never implemented, such as mirroring, partitioning, or hash-indexing. Then I hired a team of six data processors in Madagascar who clean up and process the lists found online. Lots of Python and Excel macros in their day-to-day. I have instilled in them an obsession with quality. A bad record will sit in our base forever. After trying dozens of softwares, we've settled on Adobe Acrobat and Octoparse. The final piece was the website. I lucked out in finding a strong team in Romania. They build with Next.js and deploy on Vercel. I gave them Wikipedia as the model to aim for. We/they haven't been able to match Wikipedia's simplicity. Our pages are too heavy. But I find the site user-friendly, pleasing to the eye and reasonably fast. We can and we will do better. A word about privacy. Some people complain that because it publishes names and DOBs, the Population Project infringes on their privacy. We obviously don't see it that way. - All our info is public. That DOB you find on the site is probably in the voter list of your state, a list that anyone can request or plainfully download. - The info we publish is minimal. Basically, we say that you exist. No one will find anything about your race, religion, sexual preferences, job or income. - We have adopted Wikipedia's privacy policy. We do not record your IP, unless you create or edit a record. - We're using Matomo for our Analytics. Great stuff. It's not free but they do not use your data like GA. Why am I telling you all this? From the beginning, I've envisioned a three-step process: 1) Build the database and populate it with millions of Western profiles. 2) Launch the site, where anybody can create or edit records and share them with their family. 3) When we've reached critical mass (1B records?), start making deals with NGOs and governments, and venture into other alphabets. We have just completed step 1. Step 2 is daunting as hell. I have grown a business but I have never grown a website. While I am ready to spend a bit of money on PR or SEO, I am not delusional: to reach the level of success we have in mind, we need this thing to go (somewhat) viral. How do you do that? https://bit.ly/453p8LC August 7, 2023 at 04:46PM

Show HN: Open-Source Dashboard for Splitwise https://bit.ly/3KyT22a

Show HN: Open-Source Dashboard for Splitwise Demo: mani.sebastianpapanicolau.com https://bit.ly/47l5uMH August 8, 2023 at 02:19PM

Show HN: LiteLLM -Open-Source Library for Anthropic,Azure,OpenAI, etc. API Calls https://bit.ly/3KuKc5i

Show HN: LiteLLM -Open-Source Library for Anthropic,Azure,OpenAI, etc. API Calls Needed a simple way to call multiple LLM providers. LiteLLM provides 2 functions - `completion` and `embedding`; and guarantees consistent input/output formats across all providers. That's it! https://bit.ly/47oNnW1 August 8, 2023 at 01:41PM

Show HN: A social media site for reviewing albums, movies, books, and podcasts https://bit.ly/47pxi2E

Show HN: A social media site for reviewing albums, movies, books, and podcasts I’ve been working on a social media web app for reviewing works of entertainment with the hopes to compete against Goodreads and Letterboxd. I started working on this two and a half years ago and it has taught me a lot about full stack development, from Vue, and REST APIs, to hosting with AWS. It’s still very much so a work in progress, but it’s functional and I’d love any feedback I can get. I know other options exist, but I couldn’t find one that I like that had all of the different mediums, and I’d rather have them all in one place. Likewise didn’t give me enough freedom with rating, and seemed more focused on algorithm generated suggestions. Usage : A lot of functionality requires a login, so I created this guest account for you guys to use: username: showhnguest password: hackernews23 If you wind up liking it enough to create an account, feel free to invite your friends. https://bit.ly/44UdLWe August 8, 2023 at 01:38PM

Show HN: Build your own code interpreter for ChatGPT https://bit.ly/47nmwK4

Show HN: Build your own code interpreter for ChatGPT https://bit.ly/3OMyjKH August 8, 2023 at 01:33PM