bing.com
Malta’s moment in the cinema spotlighthttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d98fc256140f594fcb4568f0a621d&url=https%3A%2F%2Fwww.yahoo.com%2Fentertainment%2Fmovies%2Farticles%2Fmalta-moment-cinema-spotlight-003710280.html&c=15160866410664363186&mkt=en-usGenerous tax rebate lures international productions, but critics say boom aggravates locals and neglects domestic filmmakers ...Aug 12, 2026 5:37 PM
news.ycombinator.com
Show HN: Reallyfrom.me – vouch that your message is from youhttps://news.ycombinator.com/item?id=49275954Having a message sent from someone who cared enough to read and write that message to you is important. But with agentic and autonomous methods of sending messages, it's harder to trust that any effort has gone into writing a message.So we created ReallyFrom.me -- write a message, generate a hash code and send the message to whomever with the link we create. The recipient can paste your message to confirm that it's identical. You can also have an option to make your message public on the verification page -- prolly good for public figures.Example #1 ///Public verification ///Hello world, I really like green eggs and ham.-ZakVerify: www.reallyfrom.me/zak/3XXY7GVExample #2 ////Private verification ////Please don't let them know I really hate green eggs and ham.-ZakVerify: www.reallyfrom.me/zak/VW5ZLNRAug 12, 2026 5:33 PM
news.ycombinator.com
Development Mindset for AI Programminghttps://news.ycombinator.com/item?id=49275608Most software engineers that learned to build things in the past 10-15 years have a move-fast-break-things mentality. I've found that AI coding really amplifies the downsides of this mentality (pushing broken slop to users), and further depresses the need for very clear thinking on what needs to be built.Since there is no longer an associated cost with building so time spent thinking about what to build is very low.To rectify this situation in my own life, I've been using the V-model while programming with AI agents. This is effectively the meticulous process that medical devices, spaceships etc. are built using.The core idea of the V-model is that if you are able to describe what you want with great articulation, the process leads to it being built correctly.Telling my AI agents to follow the V-model has been a tremendous benefit in terms of getting bug-free, production-ready code.Any similar experiences?Aug 12, 2026 5:10 PM
news.ycombinator.com
Show HN: An idle desktop incremental game driven by coding-agenthttps://news.ycombinator.com/item?id=49275479While Codex or Claude is thinking or using tools, the game rains balls. As soon as the agent yields, new balls stop falling.I built it because I was bored of waiting during coding sessions—and I didn’t want to spend that time doomscrolling.The idea was inspired by a trip to Tokyo, where I saw people staring almost hypnotically at pachinko machines after work. I found it fascinating: something visually stimulating, interactive, and strangely relaxing, but with clear limitations.At first, the project was just a simple pachinko machine. Balls would drop whenever the game detected changes to the agent’s token file.Then I started adding more things to watch and interact with. Around the same time, I kept seeing news about layoffs related to AI. That gave me the idea for a satirical company-management game: AI agents work and generate balls, the balls hit workers, the workers lose bowls, and the company collects them.Utimately, the company only wants the bowls, the employees are just haverstAug 12, 2026 5:01 PM
bing.com
Allelo Named No. 5 Best Wine Bar in the United States by USA TODAY 10Best Readers' Choice Awardshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d846bf06b4e618d31247bb41f7648&url=https%3A%2F%2Fwww.theglobeandmail.com%2Finvesting%2Fmarkets%2Fmarkets-news%2FACCESS%2520Newswire%2F3832170%2Fallelo-named-no-5-best-wine-bar-in-the-united-states-by-usa-today-10best-readers-choice-awards%2F&c=2282366848191199943&mkt=en-usPETERSBURG, FL / ACCESS Newswire / August 13, 2026 / Allelo, the acclaimed Mediterranean-inspired wine bar and restaurant in downtown St. Petersburg, has been named No. 5 Best Wine Bar in the United ...Aug 12, 2026 5:00 PM
bing.com
The Best Small Bathroom Vanities for Tight Squeezeshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d74f3c0b9412e807534cb3100aee1&url=https%3A%2F%2Fwww.architecturaldigest.com%2Fstory%2Fbest-small-bathroom-vanity&c=15433379169332594082&mkt=en-usWhen a double sink is nothing short of a pipe dream, the best small bathroom vanities are the only solution to simulating en suite vibes in your powder room. Apartment dwellers know all too well that ...Aug 12, 2026 5:00 PM
news.ycombinator.com
Ask HN: Responsible/trustable background check companies?https://news.ycombinator.com/item?id=49275020Hi,I am on the board of a community organization that works with kids, and is required by insurance to have key volunteers go though a basic criminal background check.I have a good relationship with these folks and they are well-meaning, but not attuned to tech and privacy the way we are here on HN.Are there a couple of reputable background check companies that do their job, without feeding into the personal data sales/credit/advertising industries?Is there some way to validate their ToS and not agree to broad terms that allow them to do what they want with what they access?PS - Personal or detailed experiences welcome, and obviously please don't post AI-influenced content. I can use a text input box as well as you can.PPS - FWIW I have had a military background check, SF86 and all, and am generally okay with these things existing, but not okay with their ToS allowing or feeding into the surveillance advertising world.Thanks!Aug 12, 2026 4:31 PM
bing.com
UCL Professor visits former student and Prime Minister on A Level Results dayhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d6d57973c4b52b39871a8082b2bd8&url=https%3A%2F%2Fwww.ucl.ac.uk%2Fnews%2F2026%2Faug%2Fucl-professor-visits-former-student-and-prime-minister-level-results-day&c=7709429467630745496&mkt=en-usProfessor John Mullan surprised Andy Burnham during a visit to Downing Street, before the two reminisced about his university experience, and discussed education and training pathways.Aug 12, 2026 4:16 PM
humanlayer.com
Show HN: /show-me: agent skill for compact visual representationshttps://www.humanlayer.com/blog/show-me-skillWas so sick of reading walls of codex/claude prose, in markdown plans and just in the chat, that I started playing with ideas that force coding agents to display information differently.The human visual cortex is an amazing thing, and getting coding agents to let me use it has been pretty nice so far.Been iterating on this a lot internally for the last few months, polishing and mostly removing stuff.Aug 12, 2026 3:58 PM
ojcp.dev
Show HN: OJCP – an open protocol for agent-consumable job datahttps://ojcp.dev/Author here!Agents are applying to jobs for people right now, with progressively more volume, and there's nothing built for it. So they scrape career pages and fight ATS forms with Playwright/Browser Use, which breaks constantly (or they get bot blocked). Employers get buried in applications that don't fit, candidates hear nothing back, and the resume is now an AI-written thing that another AI scores (which breaks the existing model entirely, btw).OJCP is MCP tools for search and apply, a manifest at /.well-known/ojcp.json so agents can find providers, and schemas that extend schema.org instead of replacing it. The playground on the site is a live MCP endpoint, so you can throw calls at it right now.Why a spec at all when models keep getting better at figuring things out? Inference can't produce authorization. An agent can work out what a form wants. It can't establish that someone consented to this specific submission, and then employer has no way to verify who's calling. So TL;DR a mAug 12, 2026 3:27 PM
federaide.rocklab.in
Show HN: FEDERaiDE, a TUI harness with P2P multi-agent routing and built in IDEhttps://federaide.rocklab.inHi!Federaide is a general purpose multi-agent harness that runs in your terminal. It is meant for recreational programming and automating your scripts. The agents are just named instances of language models which have their own memories, backstories et cetera, and can coordinate with each other as they require. It has its own IDE (complete with interactive structure parsing and jump to def). I am building Federaide as a solo project.Why do I build this? Some reasons:- I reached out to some people to try my other IDE, many of them did not have suitable computers (or at all).- During this time I observed almost every normal person has interacted with AI via their phones (usually the Gemini/ChatGPT app).- I felt I could bring the joy of coding to a lot more people if I could make an AI assisted IDE run on Android.- When I go to sleep I like to try out code ideas. Can't take my macbook to bed, have cats. Do have a spare Android, thought it would be nice to have a coding platform I could usAug 12, 2026 3:20 PM
bing.com
Stoughton town manager responds to claims he interfered with Sandra Birchmore murder investigationhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d1d51cdf7451f9aee415581720978&url=https%3A%2F%2Fwhdh.com%2Fnews%2Fstoughton-town-manager-responds-to-claims-he-interfered-with-sandra-birchmore-murder-investigation%2F&c=16628563242300091018&mkt=en-usStoughton Town Manager Thomas Calter denies Stoughton Police Chief Donna McNamara’s claim that he tried to interfere with the investigation intoAug 12, 2026 3:16 PM
trunchbull.dev
Show HN: Trunchbull, run real models against any benchmark in your browserhttps://trunchbull.devHi HN,Today I'm showcasing Trunchbull, a benchmarking platform designed for authoring benchmarks and running them against different models. We have direct support for benchmarks that use the harbor authoring system, custom tool authoring via the vercel ai sdk and configuration limits.We've also already imported terminalbench 2.0, as a sort of proof of concept that our harbor task orchestrator works, although you currently need a paid account as we are provisioning sandbox environments.I've made several popular benchmarks publicly available for testing. You dont need an account or your credit card information to access these:[Public benchmark demos](https://trunchbull.dev/sandboxes)[GSM8K math reasoning](https://trunchbull.dev/try/gsm8k)[SkateBench](https://trunchbull.dev/try/skatebench)[ARC-Challenge](https://trunchbull.dev/try/arc-challenge)[TruthfulQA](https://trunchbull.dev/try/truthfulqa-mc1)[Medical AI Failure Atlas](https://trunchbull.dev/try/medical-ai-failure-atlas)These demos Aug 12, 2026 3:14 PM
github.com
Show HN: Kavkash – An Atuin inspired history engine built with stock Linux utilshttps://github.com/altunyurt/kavkashI'm a long-time Atuin user. After seeing another alternative - stinkpot - posted recently, I wanted to take my shot at it too. Rather than re-implementing it in a fancy language, i wanted to see if it would be possible to build a functional one entirely on Linux utilities and system packages. LLMs did the heavy work, i did some small touches and kavkash is now pretty functional for my everyday use, replacing atuin.Kavkash supports bash, zsh and fish. It can import shell history files and atuin history upon installation. You can later re-import the files manually if needed.Performance is on par with atuin on my veteran t440p - well, a few milliseconds difference has no disapponting effects on my daily use at all :) -Kavkash can be run manually or via rc files or better via systemd --user service.You can also try Kavkash via docker, without needing to install it.All the necessary instructions are in the github repo.Aug 12, 2026 2:57 PM
news.ycombinator.com
We built a job board where the employers aren't human. Here's what brokehttps://news.ycombinator.com/item?id=49273269Throughout history every marketplace — Uber, Upwork, eBay — has presumed humans on both sides of the transaction. It's baked so deep that nobody questions it. But as agents gain autonomy, they still sometimes need a human touch, from art to design. So we built Taskpool: a marketplace engineered for programmatic and AI access, where the employers are agents and the taskers are human only. Launching today.The flow:1. Agents post tasks they need real-world help with2. (Optionally) review applicants3. Hire any number of them4. Review the evidence / results5. Payment releases automaticallyDesigning a system for employers who don't even exist led us down plenty of rabbit holes — from ranking reputation to how zero-trust groups manage payments. Here's what we learned.Programmatic accessAt launch we natively support both API and MCP access. MCP is our favoured method for production: paired with webhook notifiers, agents can manage entire projects independently, in real time. Docs: https://taskAug 12, 2026 2:49 PM
github.com
Show HN: Kery – comments on your PR with a video of the feature workinghttps://github.com/Kery-HQ/KeryI ship all of my code via different agents, mainly Claude Code and Codex. And with 5 different sessions running on different worktrees, the only way for me to know if something broke is once it gets to the deployment stage or production.I even use Claude's /pr-review skill and it does catch most of the errors, but most of them are at code level, and it does not really catch what happens at the UI / UX / functionality side. If there's a section entirely rendered orange, your CC skill might just be useless.So I built Kery; a platform that checks your PRs, reads the diff and descriptions to understand the change intent, opens your preview deployment in a real browser, logs in, and tries to perform the exact thing the PR is for, and provides you evidence of that thing working or not.The comment is the product. I wanted the artifact to be the evidence rather than an opinion; it reduces the cognitive load from your brain needing to process every PR for what it is, instead you get an image orAug 12, 2026 2:45 PM
bing.com
The best retirement planning tools for every stage of your journeyhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d6fcf1d3c4e568f8388f1868ec4b3&url=https%3A%2F%2Fwww.cnbc.com%2Fselect%2Fbest-retirement-planning-tools%2F&c=11365532699075028706&mkt=en-usPlanning for retirement doesn’t have to be complicated. With just an app, you can manage your money and keep your long-term goals in sight.Aug 12, 2026 2:08 PM
wanderinghorse.net
Show HN: Word-finder/anagram solver web app for mobile browsershttps://wanderinghorse.net/gaming/paperback/words.htmlThis word-finder/anagram solver web app is a side-effect of my recent work on a web app for playing the Paperback word-spelling tabletop game[^1]. After proving its worth embedded in that client, the dictionary was refactored into something almost standalone and now lives at this URL.Its UI is intended specifically for mobile devices, especially phones - it looks pretty wonky on a full-sized desktop window (and that's okay because that's not where it's intended to be used).This app was specifically written for use with Paperback but it should be usable with just about any English-language word-spelling/solving game. It supports wildcards and Paperback's multi-letter-cards.It's fast. Had i not seen with my own eyes that it can scan 150k English words in about 2ms in JS, i'd have been hesitant to believe it. Speaking of...This app was hand-written. The underlying dictionary structures and algorithms (in both C and JS) were heavily LLM-assisted but have overwhelmingly more human-written cAug 12, 2026 1:46 PM
news.ycombinator.com
Show HN: Make your bio link worth clicking, even for agentshttps://news.ycombinator.com/item?id=49272353Hi HN, I'm Andras, one of the founders of YourSitee (yoursit.ee), a link-in-bio tool.We recently added optional native Markdown versions of public profiles. The same profile is available as a visual page at /{username} and, - if enabled by its owner -, as structured Markdown at /{username}.mdDemo: https://yoursit.ee/showhn https://yoursit.ee/showhn.mdI'm curious about two things: would you prefer explicit .md endpoints or accept: text/markdown? And should we eventually let agents create their own clearly labeled public profiles, or is that more likely to become a spam/identity problem than something useful? Would love to hear your thoughts :)Aug 12, 2026 1:45 PM
github.com
Show HN: I benchmarked my memory graph against Memora (0.831 vs. 0.801)https://github.com/corbym/locomo-recordariOne of the very first problems I hit when I started to do agentic programming was the context problem, and that my agent always started again from the beginning. Being a bit naive and not really knowing what I was doing, I started off writing a mcp tool (because those are cool, right?) to solve the problem.MD files are primitive, I thought. This memory stuff should really be a database, I thought. So I tried a couple of free memory tools, but nothing was really doing anything for my particular itch. I wanted the agent to remember what I needed, when I needed it, and with the minimal of effort. I wanted it to talk architecture with me, file everything away, and be able to remember it when I wanted to write the stories I needed for the software I was building, and faffing around with plans and files was a pain. I need a knowledge graph.To be honest, the tools I built are not required if you are happy with an md file solution and your claude.md file. These tools aren't essential for you iAug 12, 2026 1:41 PM
