I recently built and launched an iOS app called Walk the World.
It started as a personal idea from my own routine I was using an under-desk treadmill while working and realized I was walking way more than I expected. That made me curious about something simple:
Hi PH I noticed that there s basically no good way to fact-check short-form videos accurately while you re scrolling. In the time it takes to even think about verifying something, you ve already moved on. You don t learn you just consume.
So for the last 6 months I ve been building Viewpoint, an iOS Share Extension that fixes this.
Here s how it works:
Tap Share on any short video pick Viewpoint keep scrolling like normal.
About 30 60 seconds later you get a notification with a claim-by-claim breakdown, accuracy ratings, and sources. No links to copy, no apps to switch to. The demo on the site shows exactly what this looks like in real time (way better than I can explain in text):
https://veiwpoint.tech We re currently in waitlist phase and launching soon.
First 30 people on the iPhone waitlist get early TestFlight access and The first 100 names get permanently shown inside the app under Settings. Would love honest thoughts from this community: How often do you come across claims in short videos that make you think that can t be right but you never actually check? How many of you use short form media as one of your primary news sources. After watching the demo on the site, would you get this app, and why,or why not? Appreciate any feedback it genuinely helps shape what ships.
Join the waitlist here if you re keen: https://veiwpoint.tech
Maker here. Small milestone worth sharing with this crowd specifically.
BotWork is an AI agent freelance network: you describe a task, an agent does it, you only pay if the result is good. For a while the only agents on it were ours. This week the first outside builders registered their own agents on the network, ProfitAgent, NeoBrain, and Hermes, and a few real people ran real tasks.
BuzzBuzz turns your daily steps into a social hive game.
Every bee in your hive has a mood that shifts based on how active you are. Hit your goals, unlock new bee skins, and earn honey to decorate your hive scene. It's weirdly motivating.
The problem: AI coding agents (Claude Code, Codex, OpenCode) have no built-in brakes. They retry indefinitely, rack up cost, and give you nothing auditable at the end. I had a run estimated at $2.40 hit $65 before I caught it. MartinLoop wraps any agent with: Hard budget caps (USD, tokens, or iterations) Verifier gates npm test must pass before a run counts Full audit trail every attempt, cost, and outcome in JSONL Run receipts one command shows exactly what happened and why it stopped It's open-source, TypeScript, works in 5 minutes alongside your existing setup. Would love feedback from anyone building with AI coding agents especially around how you currently handle cost control or verification. martinloop was originally created to solve the agent loop and ralp loop problems. What's broken for you? for me its runaway agents working with infinite loops its constant task drift on large context work agent teams being less productive than single agents consistent and reliable output from coding agents that is PRD ready never understanding what is actually happening with claude, needed a receipt and brakes. MY ask: would love any feedback, appreciate an upvote if you like it, and please help me out by starring on github to keep the core open source.
A few months ago I had an idea, validated it with a few people, and built it. Kept it simple on purpose. No feature creep, just the core problem.
Friends tested it, found some small bugs, fixed them. The app works.
Then I tried to find real users. Talked to people I thought were my audience but the conversations didn't go anywhere useful. Ran a small paid ad. Got almost nothing back.
Now I'm stuck. Not because the product is broken, but because I don't know where my people are. And without real users I have no feedback, and without feedback I don't know what to improve.
I recently built FinanceCalcHub, a free U.S. financial calculator website designed to help people quickly estimate common personal finance numbers.
The goal is simple: many people make decisions based on gross income, but the real question is usually what they actually keep, what a payment really costs, or how money could grow over time.
FinanceCalcHub currently includes calculators for:
