45,939 results for all

github.com
Show HN: A Bomberman-style 1v1 game where LLMs compete in real timehttps://github.com/klemenvod/TokenBrawlA few weeks ago, ARC-AGI 3 was released. For those unfamiliar, it’s a benchmark designed to study agentic intelligence through interactive environments.I'm a big fan of these kinds of benchmarks as IMO they reveal so much more about the capabilities and limits of agentic AI than static Q&A benchmarks. They are also more intuitive to understand when you are able to actually see how the model behaves in these environments.I wanted to build something in that spirit, but with an environment that pits two LLMs against each other. My criteria were:1. Strategic & Real-time. The game had to create genuine tradeoffs between speed and quality of reasoning. Smaller models can make more moves but less strategic ones; larger models move slower but smarter. 2. Good harness. I deliberately avoided visual inputs — models are still too slow and not accurate enough with them (see: Claude playing Pokémon). Instead, a harness translates the game state into structured text, and the game engine renders the
Apr 14, 2026 7:36 AM
bing.com
The Voice finale airs tonight! What time it starts, how to watch, & more detailshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8c28ccc03d45e097911e9277852ae2&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Ftv%2Fnews%2Fthe-voice-finale-airs-tonight-what-time-it-starts-how-to-watch-more-details%2Far-AA20QTTT&c=6897782472350249734&mkt=en-usFor the first (and last) time all season, The Voice: Battle of Champions airs on a Tuesday. That's because tonight — Tuesday, April 14 — we find out who is the winner of Season 29 of The Voice, and ...
Apr 14, 2026 3:00 AM
bing.com
Gemini could take a 'proactive' approach with leaked 'Your Day' featurehttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8ced0ba21a406490add571bf18d109&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Fmoney%2Fother%2Fgemini-could-take-a-proactive-approach-with-leaked-your-day-feature%2Far-AA20RbOX&c=2944244607104823420&mkt=en-usA report claims that Google is working on a new Gemini feature that could be called "Your Day." Supposedly, this feature leans on the AI's Personal Intelligence to use a user's Connected Apps to ...
Apr 14, 2026 2:11 AM
news.ycombinator.com
Why hasn't anyone built the easy button for reporting wage theft?https://news.ycombinator.com/item?id=47759617$50B is stolen from US workers every year — more than all US burglaries combined. The DOL has 800 investigators for 135 million workers. The existing reporting mechanism is a government PDF form in English only, that takes 45+ minutes to complete and requires workers to submit their real name — which goes directly to their employer. I've been mapping documented social problems with no dominant tech solution. This one keeps standing out: the inputs are clear (document violation, know rights, file complaint without retaliation risk), the victims are reachable through worker centers and unions, and federal grant funding is available. And yet — nothing. Has anyone tried to build here? Specifically trying to understand:What breaks the model — retaliation risk? Difficulty reaching workers? Legal liability? Is the go-to-market through worker centers (B2B) or direct to workers (B2C)? Are there regulatory or legal landmines I should know about before building?Happy to share the research prototy
Apr 14, 2026 12:11 AM
mercury.build
Show HN: Mercury – No-code orchestration for human and agent teamshttps://www.mercury.build/Hey HN, I'm Naveen, one of three co-founders building Mercury (mercury.build).We spent the last year in deploying AI agents for teams in large enterprises. The agents themselves worked fine. The problem was managing them. You've got Claude Code in a terminal, a research agent in a browser tab, a Slack bot somewhere else, a scheduling assistant in yet another window. It's chaotic. There's no single place to see what's running, who's doing what, or how things connect. As the number of agents grows, this gets unmanageable fast.Mercury is a canvas where you bring your agents and humans together in one place. You draw connections between them to form agent teams. An edge between Agent A and Agent B means A can delegate work to B — B processes the request, calls its tools, and replies. Agents can delegate further down the graph. The canvas becomes a living map of how your team operates.Some details on the stack:- Delegation as a primitive: when Agent A messages Agent B, it creates a persiste
Apr 13, 2026 10:16 PM
nasa.gov
NASA Invites Media to Rollout Event for Artemis III Moon Rocket Stagehttps://www.nasa.gov/news-release/nasa-invites-media-to-rollout-event-for-artemis-iii-moon-rocket-stage/NASA will roll the largest section of the agency’s SLS (Space Launch System) rocket, which will launch the second crewed Artemis mission, out of the agency’s Michoud Assembly Facility in New Orleans on Monday, April 20. What’s called the top four-fifths of the SLS core stage – the section containing the liquid hydrogen tank, liquid […]
Apr 13, 2026 9:34 PM
nasa.gov
NASA Awards Data Engineering, Informatics Support Contracthttps://www.nasa.gov/news-release/nasa-awards-data-engineering-informatics-support-contract/NASA has selected Development Seed of Washington to provide research and development services to the Office of Data Science and Informatics (ODSI) at the agency’s Marshall Space Flight Center in Huntsville, Alabama. The award is a performance-based, indefinite-delivery/indefinite-quantity contract with a maximum potential value of $76 million. A phase-in period begins on May 15, 2026, […]
Apr 13, 2026 8:58 PM
spacenews.com
Phantom Space eyes edge in orbital data race with thermal dealhttps://spacenews.com/phantom-space-eyes-edge-in-orbital-data-race-with-thermal-deal/Phantom Space believes it now has the key pieces of a vertically integrated model to compete on the edges of the emerging orbital data center market, where industry giants are already staking claims to meet soaring AI-driven demand. The Tucson, Arizona-based satellite and rocket developer recently acquired what it sees as a critical missing piece: […] The post Phantom Space eyes edge in orbital data race with thermal deal appeared first on SpaceNews.
Apr 13, 2026 6:15 PM
spacenews.com
Aerospace to support industry with government furnished talenthttps://spacenews.com/aerospace-to-support-industry-with-government-furnished-talent/The Aerospace Corp. plans to offer industry access to its expertise and facilities through a new program called government furnished talent (GFT). By providing companies with access to the Federally Funded Research and Development Center’s talent, technology, expertise and laboratory infrastructure, Aerospace intends to help accelerate development of space capabilities, Aerospace CEO Tanya Pemberton told […] The post Aerospace to support industry with government furnished talent appeared first on SpaceNews.
Apr 13, 2026 6:10 PM
news.ycombinator.com
Show HN: Bloomberg Terminal for LLM ops – free and open sourcehttps://news.ycombinator.com/item?id=47754636Bloomberg Terminal exists because financial traders needed one place to see everything: prices, risk, routing, counterparty health. You can't trade blind.LLM engineers are trading blind.Which provider is degraded right now? What does this model actually cost when you factor in overhead, not just token price? If traffic shifts between providers, what happens to cost and latency? Is your stack dangerously concentrated on one provider?These are operational questions every production LLM system has. Nobody's built the tooling for them until now, so most teams either fly blind or patch together status pages, spreadsheets, and gut feel.We built the LLM Ops Toolkit to fix that:1. Provider uptime monitor across 18+ LLM providers, live status in one view 2. Cost calculator that includes overhead, not just raw token pricing 3. Routing simulator to model cost and latency impact before you shift traffic 4. Model diversity audit to surface concentration risk before it becomes an incidentFree, open-
Apr 13, 2026 4:39 PM
github.com
Show HN: Girlfriend in CLI – AI-native persona harness for social traininghttps://github.com/NomaDamas/girlfriend-in-cliBeing good at coding alone is no longer enough.In the AI-native era, the ability to talk to people, empathize, and convey your charm is also part of your stack.Feeling lonely while vibe coding? Do you want to find a real-world girlfriend or boyfriend? Do you want to measure your dating combat power and see whether you could actually date IU?With a single brew install click, talk in your terminal while vibe coding with the person you want to become lovers with. Just enter a name or a link, and it will do the deep research you want, create a person-based persona, and let you immediately talk to the kind of person you want. While you talk, it will help you discover your charm, and at the end, you can receive a dating combat power evaluation!girlfriend in cli will equip you with a harness inside the terminal that helps you become an attractive person!!Wake up, nerds! Let’s escape being single!!! Stars are always welcome haha
Apr 13, 2026 3:55 PM
bing.com
Your Full Guide to Angel Number 222http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d16cdabaf44cc9ebd6865f28ce5c8&url=https%3A%2F%2Fwww.cosmopolitan.com%2Flifestyle%2Fa40463098%2F222-angel-number-meaning%2F&c=16644909788742197945&mkt=en-usThere are some things that once you start noticing, you simply can't stop. Even things as mundane as the time of day. That's usually where noticing an angel number pattern starts. You look down at ...
Apr 13, 2026 11:43 AM
europeanspaceflight.com
ESA Publishes New Details on Crew Launch Abort Demonstratorhttps://europeanspaceflight.com/esa-publishes-new-details-on-crew-launch-abort-demonstrator/The European Space Agency has opened its call for proposals to develop a crew launch abort demonstrator, a project first announced on 28 November 2025. With the call now open, the agency has published additional information about the project, including a budget of €1 million for this initial phase of the demonstrator’s development. Officially opened […] The post ESA Publishes New Details on Crew Launch Abort Demonstrator appeared first on European Spaceflight.
Apr 13, 2026 10:30 AM
bing.com
Understanding Legal Separation: Definition, Preparation, and Benefitshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d055df7e1459da040330c8377ef24&url=https%3A%2F%2Fwww.investopedia.com%2Fterms%2Fl%2Flegal-separation.asp&c=5696191972067394325&mkt=en-usJulia Kagan is a financial/consumer journalist and former senior editor, personal finance, of Investopedia. Erika Rasure is globally-recognized as a leading consumer economics subject matter expert, ...
Apr 13, 2026 9:23 AM
github.com
Show HN: Equirect – a Rust VR video playerhttps://github.com/greggman/equirectThis is almost entirely created by Claude, not me. I know some people aren't into that. I was one of them 3 months ago. Since the beginning of the year I finally started getting more serious about trying out AI. The company I work for also had an AI week with lots of training. All I can say is I'm pretty blown away. My entire life feels like it changed over the last month from someone who mostly writes code to mostly someone that prompts AI to write code. And just for a tiny bit of context, I'm 60yrs old and have been coding since 1980.I get all the concerns, and I review all AI code at work and most AI code for personal projects. This one in particular though, not so much. I get that's frowned on but this is a small, limited scope, personal project. Not that I didn't pay attention, Claude did do some things in strange ways and I asked it to fix them quite often. But, conversely, I have zero rust experience, zero OpenXR experience, zero wgpu expericence, next to zero relevant Windows e
Apr 13, 2026 8:26 AM
news.ycombinator.com
Artemis II: Christina Koch's PCD Failurehttps://news.ycombinator.com/item?id=47747307Early in the Artemis 2 Mission, Christina Koch's PCD (personal computing device, essentially a Surface tablet) completely failed to power on, and Houston had her attempt to perform a hard reset (hold down the power button, and the volume up button) several times, later having her remove the SD card and try again, at one point referring to last ditch efforts to get it running as a "hail-mary."These efforts were ultimately unsuccessful, and this equipment failure led to the crew having to share three working PCDs between the four of them for all of their work for the entire remaining duration of the mission. They were able to make this configuration work, albeit not without complications. Their PCDs were their direct means of tracking their jobs, documenting their work, running checklists, looking up procedures, etc. During the lunar fly-by in particular, while they were doing photography of their various lunar targets, they said that they had to swap out SD cards as they rotated between
Apr 13, 2026 3:40 AM
bing.com
Best Whole-Body Deodorantshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d5b269eab4d49ad0196a49be3f598&url=https%3A%2F%2Fwww.eonline.com%2Fnews%2F1405845%2Fbest-whole-body-deodorants&c=6527330792372804923&mkt=en-usSize: 2.0 oz. Shoppers say: "I work with the elderly and they have a tendency to keep their homes very hot all year round, and that always causes me to melt. I bought this to try to help with keeping ...
Apr 13, 2026 3:01 AM
bing.com
Neuroscience Just Discovered This Unexpected Hobby Slows Brain Aginghttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d5fb16d0b446fbd3a25e23664f298&url=https%3A%2F%2Fwww.inc.com%2Fjessica-stillman%2Fneuroscience-just-discovered-this-unexpected-hobby-slows-brain-aging%2F91327229&c=3545673679355217209&mkt=en-usBut a new neuroscience study suggests maybe you should. The new brain imaging study published in the Journal of Neuroscience found that experienced birders had hallmarks of brains younger than their ...
Apr 13, 2026 2:00 AM
bing.com
How The HELLENiQ ENERGY (ATSE:ELPE) Investment Story Is Shifting On Crack Spread Assumptionshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8cdd500f8d47d5aae890ca416273f6&url=https%3A%2F%2Ffinance.yahoo.com%2Fsectors%2Fenergy%2Farticles%2Fhelleniq-energy-atse-elpe-investment-042934460.html&c=11085528396226929483&mkt=en-usMake better investment decisions with Simply Wall St's easy, visual tools that give you a competitive edge. The latest analyst update for HELLENiQ ENERGY Holdings sets a higher price target of €36, up ...
Apr 12, 2026 9:29 PM