9,065 results for king

benzi.fly.dev
Show HN: Try Benzi – A coding harness/agent beating Claude Code itself on Sonnethttps://benzi.fly.dev/aboutHi y'all. Been working on something that should've been made a long time ago imo. It compiles codebases into O(1) hashmaps that the agent queries to discover the structure of your code/answer questions/write code.It also does complete static analysis checks on any writes the agent makes.Don't take my word for it though. Here are the benchmarks: https://benzi.fly.dev/benchmark. on 2/20 tests, Claude Code (mostly Sonnet on one task) regressed or timed out. Benzi didn't because of course, it has a map it can query and not get lost in the sauce. On the other 18 it is cheaper, faster, or often both.Would love to get some early adoption and criticism!(Only available on Windows for now. soz. and also keep an eye on the benchmarking page; I think I can push it far more -- no promises, still work in progress. Haven't thoroughly tested greenfielding experience either.)(another note: VS Code extension/website is running DeepSeek V4 flash. not Sonnet. Everything mostly built with CC Sonnet tho )
Aug 8, 2026 10:47 PM
github.com
Show HN: 49IDE – 2D Grid IDE for managing many agents, Git trees, issueshttps://github.com/alpbahadur/49AgentsBeads tables (Steve Yegge's) for issue tracking. Can view git trees, terminals, issue tables, notes, and files all on one screen. Can connect multiple machines via private network (like tailscale)I had this issue where i really did not like the when i had many terminals open at the same time - when you try to code with 6+ agents at the same time, across, say, 3 projects, you get huge context fragmentation. I am a visual person, and its way easier for me to remember where things are if I placed them there - I build this 2D canvas for myself initially and then decided to open-source - the main goal there is to let me (or the user) to place the terminals, github trees (to track agent's progress across branches on different repos), beads issues tables across many machines all on the same screen. Most important note, once again, is since its a 2D canvas, it feels more like a citybuilder where i I decide where to put stuff and thus remember exactly where what is running. It boosts my efficie
Aug 8, 2026 4:37 PM
spacenews.com
Lessons for the future of NASA Mars exploration from a 1970s missionhttps://spacenews.com/lessons-for-the-future-of-nasa-mars-exploration-from-a-1970s-mission/July 20 marked the 50th anniversary of one of the biggest robotic spaceflight achievements in NASA’s history: the landing of the Viking 1 spacecraft on Mars. It was the first […] The post Lessons for the future of NASA Mars exploration from a 1970s mission appeared first on SpaceNews.
Aug 6, 2026 3:00 PM
bing.com
Meta Launches Muse Code, A New AI Coding Agent Powered By Spark 1.2http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a895b353b2d43ce83e18bc41bebeb83&url=https%3A%2F%2Fwww.forbes.com%2Fsites%2Fjonmarkman%2F2026%2F08%2F06%2Fmeta-launches-muse-code-a-new-ai-coding-agent-powered-by-spark-12%2F&c=16992900326159865695&mkt=en-usMeta has launched Muse Code, an AI coding agent in beta, designed to handle entire engineering tasks from planning to checking code.
Aug 6, 2026 6:31 AM
news.ycombinator.com
Show HN: I was wrong about scrollytelling landing pageshttps://news.ycombinator.com/item?id=49185678My position for years: minimal static landing page, one clear offer, optimised for conversion. Everything else is designers entertaining themselves. Then the “built this 3D scrolling page with Fable in 5 minutes” posts started going around and my customers began asking for that. I pushed back, lost the argument, and built a few.Two things surprised me.First, the viral demos don’t survive contact with a client. I tested so many circulating prompt/skill setups. One-shot output looks great; changing anything afterwards is brutal... The demos are impressive because nobody in the thread ever has to revise them.Second, and worse for me: dwell time and conversion on the pages I built came out ahead of the minimal pages I’d have argued for. Small sample, and I’d like someone to tell me why it’s noise.So I built the thing that fixes the first problem: prebuilt interactive widgets that stay editable instead of a generated blob you re-prompt. https://scrollytelling.ai my own landing page is now b
Aug 5, 2026 5:05 PM
slickfast.com
Show HN: SlickFast Deterministic Chart/Dash Renderer, No Browser(JSON → SVG/PNG)https://slickfast.com/SlickFast started 6 months ago, and evolved in a super backwards way. I was using lowfruits to look for good SEO keywords, I wanted to make a simple free tool to rank with SEO. I found some great keywords related to graphs/charts. I did research for optimizing for SEO. Turns out edge processing / using static HTML is super fast and lightweight, great for SEO. I made freepiechartmaker.com. I was really blown away by how fast the site was loading, and how lightweight all the processing was. The site renders changes on the fly, and is much much faster than other sites in the space. I started looking into the tech, pure math rendering, and I saw a lot of openings for what this tech can do. That's how SlickFast was made.SlickFast is a JSON input > pure javascript SVG Native render core > with PNG+SVG output. No headless chrome. No library calls. deterministic output. on my local machine(m1 max) it renders 140,000 svg charts a second. PNG @ ~50/sec at retina (scale-2) and ~145/sec at scale-1
Aug 5, 2026 3:01 PM
news.ycombinator.com
Read HN twice a day for the last decade. Here's my list of S-Tier HN linkshttps://news.ycombinator.com/item?id=49183198- Everyday I read 2 pages of HN in the morning and 2 in the evening for years now- Of late, I noticed that most of the stuff on the 1st 2 pages is AI this, AI that, LLM this, LLM that, model here, model there- Today I am going to attempt to break that trend by sharing the greatest resources on HN from my collection of 50000+ bookmarks over the last decade- I have a process on my end for bookmarking- The most visual explainers get S-Tier ranking- Good info from reputed sources gets an A, non reputed gets B- Opinion blogs are at the bottom of the barrel and maybe ranked C, D, E and even F depending on quality- Here's my S-Tier list- Animated explanation of how transformers work https://poloclub.github.io/transformer-explainer/- Visual intro to K-means clustering algorithm https://k-means-explorable.vercel.app/- Animated 3D intro to vision LLMs https://blog.mdturp.ch/posts/2024-04-05-visual_guide_to_vision_transformer.html- Animated intro to machine learning https://r2d3.us/visual-intro-t
Aug 5, 2026 2:12 PM
news.ycombinator.com
Do You Think OpenAI Is Apple Circa the 1980s?https://news.ycombinator.com/item?id=49178393OpenAI is a deeply mismanaged company. Most recently, a blog post that feels like it has got to have dozens of PR violations, responding to the Apple lawsuit.More broadly, OpenAI’s main problem is that it does not have a real competitive advantage. No real models do; the real differentiation is price; they will become commodities. The need to move upwards in the market in enterprise software is difficult since the current stack should remain the same, since sticking with Salesforce plus its new AI features is much simpler than the cost of switching to an AI-first startup version, which won’t be around 3 to 5 years from now. So consumer hardware and trying to become the next Apple could work, except you would likely have to focus on people not in the Apple ecosystem because of the double-sided lock-in Apple has.The opposite dynamic works in consumer and mobile, really. Apple with AI is a much worse experience than something AI-first built from the ground up. Especially considering the c
Aug 5, 2026 3:50 AM
nasa.gov
NASA Will Attempt to Observe Rocket Part’s Lunar Impacthttps://www.nasa.gov/humans-in-space/commercial-space/nasa-will-attempt-to-observe-rocket-parts-lunar-impact/Using ground-based telescopes and space-based assets, NASA and SpaceX are tracking a used Falcon 9 upper stage from a commercial mission expected to impact the Moon on Wednesday, Aug. 5, near the Einstein and Bell craters. The impact poses no danger to Earth and NASA scientists are planning to collect lunar data from the event […]
Aug 4, 2026 8:00 PM
nasa.gov
NASA Provides Updates on Moon Base Cargo Landers, Tech Demonstrationshttps://www.nasa.gov/missions/moon-base/nasa-provides-updates-on-moon-base-cargo-landers-tech-demonstrations/NASA is making progress in building the Moon Base, which will become a resilient outpost near the Moon’s South Pole for science, technology, and eventual human operations. To advance lunar surface infrastructure development, commercial partners such as Blue Origin, Firefly Aerospace, Intuitive Machines, and Voyager Lunar Systems are working toward delivering landers by 2028. These […]
Aug 4, 2026 4:14 PM
github.com
Show HN: Guide AI coding agents on how to use libraries securelyhttps://github.com/Reware-Labs/securitycardsHi HN,TL;DR: AI Code Security Cards give coding agents library- and version-specific guidance to generate safer code.AI coding agents can generate working code, but they often lack library- and version-specific security knowledge. We've developed AI Code Security Cards, an open-source security knowledge layer, to provide that missing context.The project is related to my PhD, in which I focused on the security of LLM-generated code. During my research, I studied how code generation models behave, how they introduce security issues, and how we can guide them toward generating safer code.My research [1] and several other studies [2–4] show that at least 40% of code generated by state-of-the-art models contains one or more security issues. Similar problems also affect AI coding agents.One reason is that these models often lack sufficient library-specific security knowledge in their context. They may not know which configurations are unsafe, which validation steps are required, or what secu
Aug 4, 2026 2:12 PM
github.com
Show HN: Neal – Codex writes the code, Claude reviews ithttps://github.com/navels/nealneal is a CLI I wrote while trying to use an LLM coding agent (in this case, Codex GPT-5.4) to work autonomously on a migration of our large frontend codebase. A few things came up during that project that guided the development of neal:1. Telling an agent to "keep working unless blocked" doesn't actually work over long stretches of time.2. Large projects should be broken up into smaller chunks of work.3. The coding agent should start each chunk of work with a fresh context to prevent context rot.4. The coding agent benefits from having a different agent doing adversarial reviews along the way.What I ended up with is an orchestrator that- lets you configure planner, coder, and reviewer roles. I started with Codex and Claude using their SDKs but later added OpenRouter as well as a compatibility mode for verifying that a model can handle the orchestration. Currently there are 44 compatible OpenRouter models.- runs a plan that you provide through a planner / reviewer loop which splits the
Aug 4, 2026 1:14 PM
bing.com
Nvidia’s open-source alliance seeks industry input on AI safety controlshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a88fe13f64448d79b61c2c947fec710&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Fnews%2Fpolitics%2Fnvidia-s-open-source-alliance-seeks-industry-input-on-ai-safety-controls%2Far-AA29nE9B&c=10904541637519194988&mkt=en-usA working group within Nvidia’s new initiative on open-source technologies is seeking public input as it develops guidelines on how to share and learn from AI cybersecurity incidents to prevent future ...
Aug 4, 2026 8:59 AM
bing.com
Nvidia’s open-source alliance seeks industry input on AI safety controlshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a88f527bb3642028ff75d64ee93f6ed&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Fnews%2Fpolitics%2Fnvidia-s-open-source-alliance-seeks-industry-input-on-ai-safety-controls%2Far-AA29nE9B&c=10904541637519194988&mkt=en-usA working group within Nvidia’s new initiative on open-source technologies is seeking public input as it develops guidelines on how to share and learn from AI cybersecurity incidents to prevent future ...
Aug 4, 2026 8:59 AM
jackcushman.org
Show HN: Christopher Nolan's Hymn to Athenahttps://jackcushman.org/writing/hymn-to-athena/Hi, HN! Did you know that Chris Nolan's casting of Tom Holland and Zendaya eerily echoes a 3000-year-old dance battle between Athena and Telemachus? I've been working on an art project that says so.If you like, it can be fun to go in blind with a strong research agent to sort out what this really is. Or there is a multi-layered CAPTCHA at the bottom that spells it out increasingly clearly.As a small spoiler: my day job is building reliable public data tools for a library. This piece draws on that background to try to make AI-native art -- fiction by and for humans who use AI agents as a source of truth. At best I hope it works as the kind of joke one Iain M. Banks Culture AI would tell another about humans.
Aug 3, 2026 2:45 PM
nasa.gov
NASA Delivers Navigation System for Commercial Lunar Relayhttps://www.nasa.gov/technology/space-comms/nasa-delivers-navigation-system-for-commercial-lunar-relay/NASA delivered the NavCube3-mini payload on July 13 to Intuitive Machines for integration into Altus-1, the company’s first lunar relay satellite, marking an important milestone in the development of future lunar communications and navigation services. The lunar relays are designed to enable communications and navigation for astronauts and rovers operating at the agency’s future Moon Base. About half the size of a shoebox and weighing just 3.5 pounds, NavCube3-mini is a compact but powerful navigation […]
Aug 3, 2026 2:20 PM
dmerullo.github.io
Show HN: Project ESPAÑOL: Find level-appropriate Spanish-language poemshttps://dmerullo.github.io/project-espanol/I made this application while taking Spanish lessons to find texts that used verb forms I was learning (present, past, future, subjunctive, etc.). First, I scraped ~10,000 Spanish-language poems from the web that are in the public domain. Then, I built a conjugation dictionary for the 550+ most common verbs, using rules to generate regular verbs, and scraping irregular verbs from the web. From this alone, you can identify which poems contain the most type of verbs you're trying to target. To take it further, I used a k-means clustering algorithm in Python to classify the poems into four difficulty levels based on verb form frequencies (poems with lots of verbs in subjunctive future perfect are more difficult than only present tense, for example).I first completed the project in December 2024, almost entirely by hand, using LLMs primarily to make an interactive Plotly Dash application. (I have a lot of experience with data visualization, especially ggplot2; that was my first time using
Aug 3, 2026 1:12 AM
marnetto.net
Show HN: A mod for Grand Prix Circuit (DSI/Accolade, 1988)https://marnetto.net/projects/grand-prix-circuitHello HN,I have built a mod for Grand Prix Circuit, an old 2.5D racing game: the latest episode of a long series of community efforts to reverse-engineer and improve the games made by Distinctive Software (today's EA Vancouver) in the DOS era.I've been dabbling in hacking old DOS games for almost two years, but this time I think my project is big enough to be worthy of a “Show HN“.From the gaming point of view, the mod offers a variety of new cars and tracks, from Spa to the Space, and more sophisticated EGA backgrounds than the original game.From the technical point of view, it was an interesting effort combining reverse engineering, development, design and pixel art, all of which both in classic and LLM-assisted variants.From the literary point of view, I have documented the making of the game in a series of (fully human-written) posts [1]. There is something for everyone: war stories, hacking techniques, the word “boustrophedonic” and, as bonus, an outdoor game to keep your kids awa
Aug 2, 2026 2:40 PM
d2ykijtrvb890q.cloudfront.net
Show HN: Vein, a minimalist open-source resource management gamehttps://d2ykijtrvb890q.cloudfront.net/Recently I've been working on Vein, a small open-source resource management game built with Godot.I've always loved resource management board games, and I wanted to see how minimal I could make one. The core idea is simple: keep the heart beating by supplying it with the resources it demands. I tried to strip the mechanics down as much as possible while still leaving room for interesting decisions, and I added a short tutorial to help players get started.The problem is that I still don't feel like I've found the right gameplay loop. It works, but it isn't yet the game I imagined. I'd really appreciate any feedback—whether it's about the mechanics, pacing, tutorial, UI, or anything else that stands out. I'm especially interested in ideas for making the core loop deeper without making the game more complicated.Most of the development was done with Claude Sonnet as a coding partner, while I focused on the design, gameplay, and iteration. The game engine is Godot.You can play it here: http
Aug 2, 2026 9:44 AM