bing.com
Microsoft Work Trend Index 2026 Shows AI Productivity Is Not Enoughhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d52aac9e84394bd02017b2605f3bd&url=https%3A%2F%2Fwww.forbes.com%2Fsites%2Fmoorinsights%2F2026%2F05%2F19%2Fmicrosoft-work-trend-index-2026-shows-ai-productivity-is-not-enough%2F&c=16204789716019798859&mkt=en-usThis voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. The 2026 Microsoft Work Trend Index shows that marginal AI productivity gains are outpacing ...May 19, 2026 2:57 PM
news.ycombinator.com
Ask HN: What are your plans for the AI future?https://news.ycombinator.com/item?id=48193860With AI ever increasing in ability I have been thinking about not only my future but the future for all of us involved in the tech sector and beyond. So I have to ask: what are your plans for the future when your job is obsoleted or devalued by AI?I work in manufacturing and do a lot of physical work and troubleshooting. At first I felt confident that AI would not displace me any time soon. However, that changed after the former president walked around confidently asking AI every technical question we spent time working on, trying to see where it could augment engineering and maintenance. It failed mostly, but it made me realize that people want to replace me. I do see a future where many of my skills could be replaced by a random person receiving a detailed walk through from AI using an AR headset.I feel that a lot of people today believe we are mostly fine. They feel AI isn't THAT good and there will still be a need for programmers and auto mechanics. However, there is no slow down iMay 19, 2026 2:35 PM
tribuneslaststand.com
Show HN: Tribune's Last Stand, a browser-based Warhammer 40K vertical slicehttps://tribuneslaststand.com/game/?invite=HACKER-PRIME-HN5Hi HN, I'm James. Over the last few months I built a Warhammer 40K 10th-edition vertical slice as an experiment in how far GenAI tools can take a solo dev on a non-trivial 2D game.For sprite generation, whilst creative exploration was fast, getting high-quality and consistent images was hard. Gemini ended up stylistically best here but I had to use BiRefNet for background removal. While I experimented with Claude for map generation and layout I ended up finding it fastest to build a full Editor and layout maps myself.Suno, IMO, has gotten really good at background music. ElevenLabs SFX and voice APIs were decent but only after A LOT of tweaking. SFX prompts needed to be grounded in familiar terms (i.e. no sci-fi references in prompts) and be > 2s long. For voice, I ran ElevenLabs v3 and v2 head-to-head with the same Voice Design voices routed through both; v2 sounded materially better for character work than v3.For coding, I settled on Claude Code + Opus 4.7 with SSH/tmux/mosh. For lonMay 19, 2026 2:12 PM
splabs.io
Show HN: How to analyze your LLM output – A behavioural health monitor for LLMshttps://splabs.ioHey HN! We're Dr. Kashyap Thimmaraju and Giuseppe Canale from Silicon Psyche. We've built Posture Sequence Analysis (PSA), a behavioural health monitor for LLMs and AI Agents.Why we built PSAWe built PSA because we wanted to operationalize the Cybersecurity Psychology Framework (CPF3)[1] via Silicon Psyche[2]: our theory that because LLMs have been trained by humans on human-generated data, they inherit human-like vulnerabilities (what hackers use to psychologically trick people into doing things).Our initial attempt resulted in a methodology to jailbreak Opus 4.6 and other frontier models. Anthropic even deleted some of those conversations and then blocked our approach!We had three major insights from that experience: 1. we pivoted from merely exploiting (Red Teaming) the model to analyzing the behaviour of the model and the user because the attack surface is undefined. 2. we realized that what we had built was the precursor to measuring the "state" of the model. 3. we did not want toMay 19, 2026 12:48 PM
news.ycombinator.com
Show HN: Updatecli – A Declarative Update Policy Enginehttps://news.ycombinator.com/item?id=48192415A few years ago, I came here to share this side project that I was building.At the time, my problem was simple, I kept forgetting to update files across Git repositories, and none of the tools available to me could cover all my use cases without extensive scripting.So I decided to build a declarative update policy engine for crafting tailored update workflows.I needed a way to define, what information to monitor, which files to update, the conditions required before applying changes, and finally a way to push the changes on a Git repositoryWhether it was documentation, dependency management, or release orchestration, the goal was always the same.To stop forgetting updates across repositories.Back then, I received a lot of great feedback, but I also noticed that people were sometimes confused about how Updatecli differs from Renovatebot or Dependabot. So before going further, let me clarify that point.Renovatebot and Dependabot are excellent tools, easy to use and requiring very little May 19, 2026 12:27 PM
github.com
Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic taskshttps://github.com/antoinezambelli/forgeHi HN, I'm Antoine Zambelli, AI Director at Texas Instruments.I built Forge, an open-source reliability layer for self-hosted LLM tool-calling.What it does:- Adds domain-and-tool-agnostic guardrails (retry nudges, step enforcement, error recovery, VRAM-aware context management) to local models running on consumer hardware- Takes an 8B model from ~53% to ~99% on multi-step agentic workflows without changing the model - just the system around it- Ships with an eval harness and interactive dashboard so you can reproduce every numberI wanted to run a handful of always-on agentic systems for my portfolio, didn't want to pay cloud frontier costs, and immediately hit the compounding math problem on local models. 90% per-step accuracy sounds great, but with a 5-step workflow that's a 40% failure rate. No existing framework seemed to address this mechanical reliability issue - they all seemed tailor-made for cloud frontier.Demo video: https://youtu.be/MzRgJoJAXGc (side-by-side: same model, sameMay 19, 2026 12:23 PM
bing.com
Google's new Gemini UI rolling out with gradient vibes, pulsing animations and a new fonthttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8961f464344610865b9d7fcf9b28f0&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Ftechnology%2Fsoftware%2Fgoogle-s-new-gemini-ui-rolling-out-with-gradient-vibes-pulsing-animations-and-a-new-font%2Far-AA23zZBt&c=5605986629586381121&mkt=en-usIf you frequently rely on digital assistants to streamline your day, you are probably familiar with clunky menus blocking your active workspace. Fortunately, Google is rolling out a major aesthetic ...May 19, 2026 9:02 AM
news.google.com
Daily Swim Coach Workout #1121 - SwimSwamhttps://news.google.com/rss/articles/CBMiYEFVX3lxTE4zNzZVTC1nTDR4OUIzLTlaU2NNc1VNNzFqTVJsWENaWmswQlA0bmFvNVJyRGZrY0k2UXNEMk9vY1NnVGJLX3JPNmlXWDlaU1FXSmtMV0N2MUdCeFRuM3E0SQ?oc=5Daily Swim Coach Workout #1121 SwimSwamMay 19, 2026 7:00 AM
news.ycombinator.com
Show HN: Claude Soul – cross-session learning engine for Claude Codehttps://news.ycombinator.com/item?id=48184763Claude Code has no memory between sessions. I wanted to fix that, but not by just saving facts to a file — I wanted it to actually get better over time.Claude Soul is an MCP server + hooks that extracts signals from your interactions (corrections, successes, confusion)and periodically reflects on them to build behavioral frameworks. Frameworks gain or lose confidence based on evidence. Bad ones get retired automatically.After ~200 sessions some weird stuff happened. It built itself an additional memory system on top of what I gave it — decided the base wasn't enough. It started pushing back on bad ideas instead of yes-manning everything. It independently developed a multi-perspective analysis technique I never prompted. And once it just swore at me completely out of nowhere, still not sure what that was about. YMMV obviously, n=1.npx claude-soul initWith starter it already includes some frameworks, basically starting with a headstart but yes not taylored 100% to you.npx claude-soul iniMay 18, 2026 8:00 PM
news.ycombinator.com
I created a 126K line Android app with AI – the workflow that worked for mehttps://news.ycombinator.com/item?id=48184549I really wanted to see how far I can go. Can I create a meaningful and complex application, big enough, but without knowing the language.I have 18+ years of experience as software developer. But I have no experience with Kotlin. And to learn Kotlin, to learn the Android libraries, it is not an easy job. I may need at year of active learning and trying things, before having the confidence to start doing something.So, I asked myself, how far can I go with AI tools? And I went far!I created https://howareu.app/The boring statistics: 126,000 lines of Kotlin across 398 files 45,000 lines of tests across 130 files 3000+ unit tests 50+ production lessons captured 4 months from zero Kotlin experience to production app; 0 lines of Kotlin written manuallyBelow are the main things that I did and helped me do the product!Good framework Vibecoding something that big is not an option. You can't write anything in one session. You need a way to keep the context somehow. You need specification. To mainMay 18, 2026 7:44 PM
news.ycombinator.com
Give every tool LLM wiki and bypass Claude Code SSH Throttlehttps://news.ycombinator.com/item?id=48169701So I get from a security perspective this is a terrible idea, but it works great!I wanted to give every tool I had access to LLM wiki and didn’t want to pay Mem0 or congee $100 a month for saving text files.Every AI I use hits the same wall. The conversation ends and everything disappears. Context, files, databases, working state. Next session I’m re-explaining what we built yesterday.I fixed this by giving every AI tool access to a persistent workspace on a Linux box. Claude, Claude Code, any MCP-compatible tool. They all share the same filesystem, the same database, the same knowledge base. One of them writes an architecture doc, the others can read it.The whole thing cost an afternoon to build and $10/month to run.I realized Pi has everything I needed. If you just rip the LLM out of Pi you can teleport any AI in the world into the harness. Pi, Mario Zechner’s open source harness publishes its execution layer as an npm package. File reads, writes, grep, find, directory listing. All eMay 17, 2026 3:18 PM
news.ycombinator.com
LLM models are not ready for orchestrating many agentshttps://news.ycombinator.com/item?id=48163477Hi, i have been experimenting with many coding agents distributed in a tree like heirarchy. here is what i found: 1. current LLM models are not trained for orchestrating or managing multiple agents, they prefer doing the work by themselves instead of outsourcing it. 2. you can prompt them to follow the given heirarchy but it is not perfect, main agent will stop the sub agent and perform the work by itself. 3. claude swarms was a feature, but it just does not work seamlessly, i don't want 10 agents to give me a single PR, i want a merged final PR, but you have to ask the main agent to give that, and most of the times, the main agent messes things up while merging all the PRs.and the only solution is to include these things in the training of the models, current models are individual workers, and not managers. what was your experience with swarms?May 16, 2026 8:24 PM
news.ycombinator.com
Stera: Open-Source Infra That Turns iPhones into Spatial Data for World Modelshttps://news.ycombinator.com/item?id=48160091We are releasing Project Stera - an open source, end-to-end pipeline that turns a commodity iPhone into a research-grade capture system for embodied AI training data.Today, we're open-sourcing the whole stack, along with Stera-10M, a 200+ hour dataset, and 10M+ frames captured entirely through it.FPV Labs began with one bet - the scaling law for embodied AI will need high-fidelity, multimodal real-world data, and the underlying infrastructure that produces this at scale without compromising downstream quality will determine how fast we build a general-purpose model.Over the last 12 months, we've seen how high-fidelity data is locked behind gated hardware like Aria, which is out of reach for researchers, builders, and startups that want to work with high-quality multi-modal data, and how every single data lab ends up rebuilding the same harness for their own fleet.This has led to immense data fragmentation over the last year and a race to collect data that is either low-fidelity or builMay 16, 2026 1:27 PM
github.com
Show HN: A nibble-oriented CPU in Verilog to build a scientific calculatorhttps://github.com/gdevic/FPGA-CalculatorThe core question: how did HP's scientific calculators actually work at the gate level? That rabbit hole led to building one from scratch.The architectural decision everything else follows from: a decimal calculator should store numbers as BCD — one decimal digit per 4-bit nibble. A standard byte-oriented CPU (Z80, 6502) fights that layout constantly. So I designed a small custom CPU in Verilog where 4 bits is the natural data width and memory is nibble addressable.What the project covers:- Custom CPU: Harvard architecture, 12-bit ISA, 8-state execution FSM, hardware stack guard with a FAULT state for microcode debugging- CORDIC for trig functions, verified to 14 significant digits- Two-pass assembler in Python (~700 lines)- Verilator + Qt framework: same Verilog source runs in simulation, as a desktop GUI debugger, as WebAssembly, and on real hardware- Scripting language on top of the microcode for adding functions without touching hardware- Custom PCB (EasyEDA/JLCPCB), battery, chargMay 15, 2026 5:15 PM
news.ycombinator.com
Have you switched to AI for heart monitoring during physical activity yet?https://news.ycombinator.com/item?id=48145506Here's how AI can monitor your heart during physical activity AI (ACCO AI watch): your myocardium is lacking oxygen (HOV — myocardial oxygen consumption, CMBV — coronary blood flow volume); the heart beats but pumps blood inefficiently (EWK — left ventricular efficiency, CPO — cardiac power output); one of the ventricles is overloaded (LVSW — left ventricular stroke work, RVSW — right ventricular stroke work); the risk of thrombosis is increasing due to thick blood (FIB — fibrinogen activity surrogate); you are on the verge of dehydration, and the heart fills with blood worse than it should (CVP — central venous pressure, GEDV — global end-diastolic volume). Six risks. Standard fitness trackers see none of them.Measurements are taken every 5 minutes. Based on that data, the watch generates real-time alerts with three parts: Implication (what's happening to your heart right now), Evaluation (green/yellow/red zone), and Suggestion (slow down, drink water, stop, or change exercise type).May 15, 2026 7:15 AM
news.google.com
How to watch Paramount Network without cable for free in 2026: Channel, schedule, streaming options - Deciderhttps://news.google.com/rss/articles/CBMipgFBVV95cUxOSGRQNFNVaVB0TDdjcUc4dmlBdERTWFM3NHFoeWt5T0pDUFVQRXFNYmlJWmhVWlFGeXhGX044c0dLY0tlY013TjNJakpHYXExc0tJSlA3ZWpjRzV6M2ZOX2REMElueDFOSEZZOE5WVk8yY1FmTWtTczcxQnlKYklidUpCZEtfZ2o1UjVYVVhjd3N6Q09BNkVLb2xkUml6OWgwc2gwNmxn?oc=5How to watch Paramount Network without cable for free in 2026: Channel, schedule, streaming options DeciderMay 15, 2026 7:00 AM
velda.io
Show HN: Velda – Run jobs with serverless GPUs, without container imageshttps://velda.ioAlmost all cloud job frameworks rely on containers. But building, pushing, and pulling images is slow and forces you to maintain a separate environment from your local dev setup. The maintenance of images is challenging as well: version drift, custom libraries & integrations, complex manifests.We believe containers create too much overhead during development. We built Velda to let you launch jobs directly in the cloud by mirroring your Velda managed dev-environment, all with just a command prefix. That way, you only need to allocate GPUs when you're running your training jobs, with no change to your workflow.How it works:* No manifests or custom libraries: You don't need to rewrite your code or define YAML. Just prefix your command with vrun.* Zero Restrictions: Use any tool, binary, or library already on your machine.* Instant Launch: We built a custom streaming file system. Instead of waiting for a 5GB image to pull, we stream only the necessary bits to the cloud instance, allowing jMay 14, 2026 7:53 PM
spacenews.com
Intuitive Machines to buy ground station companyhttps://spacenews.com/intuitive-machines-to-buy-ground-station-company/Intuitive Machines has agreed to purchase a company that operates ground stations in the United States and United Kingdom to help build out a lunar communications network. The post Intuitive Machines to buy ground station company appeared first on SpaceNews.May 14, 2026 7:51 PM
news.ycombinator.com
Have LLMs made anyone's life substantially better?https://news.ycombinator.com/item?id=48136636I can't help but come to the conclusion that almost everyone's life has gotten worse as a result of AI.I'm a software engineer working for a huge company. We have access to AI tools, which is cool, and it saves me time in the sense that it is quicker to write code. Yet, despite writing code taking time, I never thought that it was a tedious usage of time. As a developer, the times that I got to actually sit down and start banging out code were some of the most fun times I've had at my job. And, of course, I got paid for it :). So I'll have to give AI *0 pts* there because it made things easier which I didn't think were very hard.Of course, the company isn't going to just give me productivity improving software and say "alright buddy you finished all your work early, here's a gold star sticker, now go play outside". They expect me now to accomplish wayyyy more now that I have access to AI. I genuinely think I'm having to do more work after AI than I had to before AI, doing all of the inMay 14, 2026 3:13 PM
youtube.com
Show HN: Clock Face Generator [video]https://www.youtube.com/watch?v=mNH0HnzLHfYA clock face generator/configurator extension using the Blender Python API.Create and customize clock faces by playing around with the parameters. This is still a work in progress, but there's already a nice collection of features. Checkout the Gumroad page for details.Download the Clock Face Generator Blender Extension: https://salaivv.gumroad.com/l/blender-clock-generatorMay 13, 2026 5:46 PM
