Show HN: Modreveal – Utility to find hidden Linux kernel modules https://ift.tt/kMPGfOw

Show HN: Modreveal – Utility to find hidden Linux kernel modules https://ift.tt/40S7ouc January 1, 2023 at 09:02PM

Show HN: Lama2 - Plain-Text Powered REST API Client for Teams https://ift.tt/tFlBq71

Show HN: Lama2 - Plain-Text Powered REST API Client for Teams https://ift.tt/C5n8UM2 January 1, 2023 at 07:36PM

Show HN: I created my AI clone based on 600.000 written words https://ift.tt/h587p1x

Show HN: I created my AI clone based on 600.000 written words https://twitter.com/louis030195/status/1609487185602023426 January 1, 2023 at 03:21PM

Show HN: My programming language, building in public for 1 year https://ift.tt/0mzXgBH

Show HN: My programming language, building in public for 1 year My weekly(ish) video logs tracking my progress of building a completely sound statically typed language and structural editor. The motivation is to make lots of invalid programs unrepresentable. https://ift.tt/ZjgeiRT January 1, 2023 at 05:12AM

Show HN: I made a simple, open source, chromatic tuner mobile app https://ift.tt/zX4l7vC

Show HN: I made a simple, open source, chromatic tuner mobile app I'm a musician by night, software developer by day, and one of the minor frustrations I've always had was trying to find a simple tuner app for my phone. Looking at both the iOS and Android app stores, you'll find a lot of the top tuner apps are rather bloated with ads or subscription callouts. I thought I'd create a dead-simple minimalistic mobile chromatic tuner the way I would like it - open the app and tune my guitar. My work is in web with NodeJS and React, so I chose React Native since it was the easiest to understand coming from React. Flutter was also an option since the company I work for has a team working in that, but I thought it would be a bit too much effort to learn Dart. I learned a bit more about React rendering with this project as well. The main issue I had was trying to have a React state variable be constantly updated with any frequencies detected from the mic input, but that ended up causing substantial slowdown due to so many rerenders, so I opted to use a React ref to maintain any detections, and then only update the React state when there was an actual note. I feel like sometimes the UI has trouble updating occasionally when my iPhone is in battery saving mode, which I guess might be related to throttling the audio sample rate somehow, though I'm not entirely sure. Friends and family haven't noticed this, so it may be due to my old 2016 iPhone SE :P. The apps you can find on the both the iOs App Store and Google Play (free!). https://ift.tt/fCTXYBx https://ift.tt/EKAQwbG... Would love any feedback! https://ift.tt/1ac24B6 January 1, 2023 at 02:21AM

Show HN: I Built Sailboat UI – Modern UI Framework for Tailwind CSS https://ift.tt/QJfDvCG

Show HN: I Built Sailboat UI – Modern UI Framework for Tailwind CSS Get start with 150+ Tailwind CSS components , built your website quickly with Sailboat UI. https://sailboatui.com/ December 31, 2022 at 02:18PM

Show HN: lambdaprompt – build, compose and call templated LLM prompts https://ift.tt/Awq8vIE

Show HN: lambdaprompt – build, compose and call templated LLM prompts For the past few months I've been building a lot of things with LLMs (GPT-3, Codex, etc.) as I've been trying to push them to their limits (especially towards applying them to the tabular data domain) When working on this, I've found there are some common patterns for solving problems (templating, chaining, functional-programming style operations, etc.) As I've iterated, I've come to believe that a functional style interface is likely going to power a new wave of systems I'm calling "prompt-machines"(systems where the core new unit of work is a "named" LLM prompt, extending the "function" concept). Additionally, in order to make the code capable of meta-prompting (where the LLM can write its own templated prompts), I aimed to make the interface and library as simple and lightweight as possible. I think I've achieved my goal, so I'm releasing the library to share with others! I mainly use lambdaprompt in two main ways: (1) to quickly try out "map" applying a LLM prompt against multiple inputs, to see how it behaves on a fixed set of inputs (2) to quickly iterate on a prompt-chain (taking the output of a prompt, and passing it to other prompts) to create complex behavior. An example of (2) that worked quite well is a Text-2-SQL prototype: It generates multiple SQL options, then executes each against the database (if it errors, asks `Codex-EDIT` to fix the errors and retry), then takes the most "consistent" answer as the valid answer. Simply by adding this prompt-chain on top of codex, we saw an improvement from ~75% to ~85% on a spider Text-2-SQL benchmark (On just a small sample of N=200). To increase usability it also ships (extras) with a fastapi app that registers any defined prompts as endpoints directly, and hosts the functions to be directly callable via HTTP-GET requests. This makes it easy to build client-applications off of these prompts, while allowing the prompt itself to be arbitrarily complex (composition of prompts) I hope you enjoy using it! Also, I'm super curious to hear if anyone else has been thinking about LLMs (composing them, building interfaces to them, etc.) in similar ways and what learnings have been (even if not though this library) https://ift.tt/WLYnmVS December 31, 2022 at 02:43PM