Show HN: Groovyfmt, a fast formatter for Groovy, Gradle and Jenkinsfiles
Article URL: https://github.com/costajohnt/groovyfmt Comments URL: https://news.ycombinator.com/item?id=50528260 Points: 1 # Comments: 0
Search headlines, summaries and articles to connect the dots.
Article URL: https://github.com/costajohnt/groovyfmt Comments URL: https://news.ycombinator.com/item?id=50528260 Points: 1 # Comments: 0
Article URL: https://github.com/skorotkiewicz/jiff-js Comments URL: https://news.ycombinator.com/item?id=50529532 Points: 1 # Comments: 0
Article URL: https://github.com/debarshibasak/listodo Comments URL: https://news.ycombinator.com/item?id=50525250 Points: 1 # Comments: 0
You don’t need to sign in to multiple tools and services to deploy software. Loisium brings the process together in one place. Our beta is now live. Try it out and let us know what you think. We’re just getting started, and your feedback will help us improve. Comments URL: https://news.ycombinator.com/item?id=50529523 Points: 1 # Comments: 0
Open Academy is an open-source app inspired by Math Academy (https://mathacademy.com/). You use it to create courses on any subject, taught in a similar way.If you're unfamiliar with Math Academy, it's a maths learning site with short lessons, lots of practice questions, and reviews that bring old topics back before you forget them. I really enjoyed using it to study maths, but I couldn't find anything similar for other subjects. At the same time, I was using AI a lot to learn new topics but my lessons had no structure. So I built Open Academy to bridge that gap.You create courses with your AI of choice through the CLI, ideally grounded in your own notes or content from the web. The app handles the rest, which includes prerequisite locks, quizzes and spaced review (FSRS).I don't intend to make a managed version of this. The repo and the demo include example courses: Maths for ML, ML Foundations, Deep Learning, Transformers and LLMs, LLM Inference and Reinforcement Learning so you can get a feel fo rit.MIT licensed. Runs with Docker, on Vercel with Neon, or fork it do with it as you please as far as hosting is concerned.Demo: https://open-academy-demo.vercel.app Comments URL: https://news.ycombinator.com/item?id=50519860 Points: 1 # Comments: 0
Article URL: https://github.com/yocontra/pulsar Comments URL: https://news.ycombinator.com/item?id=50526967 Points: 1 # Comments: 0
Article URL: https://softytools.com/ Comments URL: https://news.ycombinator.com/item?id=50521407 Points: 1 # Comments: 0
Article URL: https://standardsupport.dev/ Comments URL: https://news.ycombinator.com/item?id=50524768 Points: 1 # Comments: 2
Article URL: https://github.com/openstatusHQ/stromboli Comments URL: https://news.ycombinator.com/item?id=50523348 Points: 1 # Comments: 0
Article URL: https://github.com/0nelight/sutra-os Comments URL: https://news.ycombinator.com/item?id=50525052 Points: 9 # Comments: 0
Article URL: https://github.com/automatics-dev/mac-tom Comments URL: https://news.ycombinator.com/item?id=50531364 Points: 2 # Comments: 0
Article URL: https://github.com/rdcm/triton-ng Comments URL: https://news.ycombinator.com/item?id=50532862 Points: 1 # Comments: 0
This is the developer of XDMIn a time of bunch of vibe coded download managers XDM one of the oldest open source downloader that is been serving as IDM alternative from 2013. Apart from a modern beutiful UI XDM now comes with torrent support powered by Libtorrent (the engine behind famous qBittorrent) and a new yt-dlp wrapper on top of XDM's built in browser extension based video grabber.New features: - Torrent and magnet link support - Additional option for video download based on yt-dlp - Lightweight but modern UI. XDM still runs under 50mb of RAM - Brand new social media reels and profile downloaderCore features: - Dynamic segmentation based battle tested multi threaded download engine - Takes over downloads from browser and detects video playing in the browser - Runs on Windows, Linux ( with native wayland support ) and macOS. - Usual features: Pause/resume/refresh expired links, queue, scheduler, speed limit, custom actions after completion, proxy, authentication and many more. - Android version soonPlease visit GitHub repo for more info: https://github.com/subhra74/xdm Comments URL: https://news.ycombinator.com/item?id=50521479 Points: 2 # Comments: 0
New tools, practical guidance, and partnerships will help prevent, detect and respond to online child sexual exploitation and abuse.
arXiv:2611.18956v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models add parameters without proportionally increasing per-token compute. However, training cost also depends on bytes moved, memory held, and kernels launched, and many of those costs follow total parameter size rather than active compute. On infrastructure built for dense models, this mismatch is costly: in early baselines, throughput fell as stored expert parameter size grew, even though the useful work per token stayed nearly fixed. To close this gap, we present a redesigned training stack in Olmo-core, built for efficient, scalable MoE training. We replace the Fully Sharded Data Parallel (FSDP) of earlier Olmo-core versions with an architecture built on Distributed Data Parallel (DDP), and add Expert Parallelism (EP), Pipeline Parallelism (PP), a distributed optimizer, and activation recompute. We propose NVSHMEM-based rowwise EP, which writes each token directly into its expert's buffer, avoiding dispatch and combine permutation overhead. We make EP fully synchronization-free by keeping routing metadata on the GPU and using device-scheduled grouped GEMMs. Closely integrated MXFP8 cuts compute, activation-memory, and transport costs, and topology-agnostic checkpoints let the parallel layout change between runs. On NVL8 B300 nodes, the stack supports training configurations from 12.9 billion to 1.2 trillion total parameters on up to 512 GPUs, reaching 858 useful-model TFLOP/s/GPU at 1.2 trillion with MXFP8 and per-layer recompute; an experimental capacity test with the optional DeepEP v2 backend reaches 2.38 trillion. We also explain each design choice and share findings for other training systems; for example, we identify a failure pattern we call Token Gerrymandering, in which the MoE router can learn to hack the load-balancing loss, and find that overlapping communication with computation can slow the overlapped kernels by more than it hides.
SuperDial Inc., the creator of voice-first artificial intelligence agents for automating healthcare workflows, is overhauling its platform with a new Agent-to-Agent RCM architecture. The goal is to eliminate the compute inefficiencies that have arisen as autonomous workers become more prevalent in the industry. The startup, which raised $26.5 million in a Series B funding round […] The post SuperDial revamps its healthcare voice agent platform to stop AI bots wasting time calling each other appeared first on SiliconANGLE.
Multi-agent coordination is a distributed systems problem, not a model problem. This post gives a field-tested taxonomy of multi-agent design patterns and anti-patterns, a framework for deciding when multiple agents are warranted, and how to build cost-efficient, reliable systems on AWS.
Live Rewind and Siri Recap can transcribe missed moments and summarize your day—if you don’t mind a little social clumsiness.
Oussama Ammar, cofounder of French startup accelerator The Family, was sentenced to 16 months in prison by a London court for breaching asset freezing orders and making false statements about his finances.
The first 90 days after a funding round can be overwhelming for founders, but executive coach Kelly Meerbott explains how they can protect their decision-making by pausing before major commitments, acknowledging stress, scheduling candid co-founder conversations, and seeking support from boards and trusted outside advisers.