Hacker News

I see it more and more in email, Slack, text, etc: People too scared to share their own thoughts so they AI-wash it and send an exhausting page of "It's not X, it's Y!" slop instead.

I'm not the CEO, I can't order people to stop. The CEO does it too.

I try talking to people directly, but people get defensive and there's always the chance they didn't use AI. I need indirect means of socializing change.

Looking for anything I can use to socialize against AI-washing: Articles, memes, policies that other companies have successfully used- whatever.

Comments URL: https://news.ycombinator.com/item?id=47049884

Points: 2

# Comments: 1

Hey HN,

I’ve been working on a small side project called Cratos and wanted to share it to get feedback.

Cratos is a self-hosted task scheduling system. You configure a URL, define when it should be called, and Cratos handles scheduling, retries, execution history, and real-time updates. The goal was to have something lightweight and fully owned - no SaaS dependency, no external cron service.

It’s split into three repositories:

Backend service: https://github.com/Ghiles1010/Cratos

Web dashboard: https://github.com/Ghiles1010/Cratos-UI

Python SDK: https://github.com/Ghiles1010/Cratos-SDK

Why I built it:

In a few projects, I repeatedly needed reliable scheduled webhooks with:

Retry logic

Execution logs/history

A dashboard to inspect runs

Easy local deployment

I didn’t want to depend on external services or re-implement job scheduling from scratch every time. The goal was simple deployment (docker compose up) and full control.

It’s still early, but usable. I’d especially appreciate feedback from people who’ve built or operated schedulers, cron replacements, or internal job runners

I would love some feedback, or tell me how it would be useful to you

Comments URL: https://news.ycombinator.com/item?id=47049878

Points: 1

# Comments: 0

Article URL: https://www.paradedb.com/blog/hybrid-search-in-postgresql-the-missing-manual

Comments URL: https://news.ycombinator.com/item?id=47049875

Points: 1

# Comments: 1

Grand Time 1.0: frozen research spec with time as non-monetary latent accounting primitive, governance-free.

Invariants via formulas: 333-day stability, mint coverage gates, Time Capital activation (no price impact), multi-asset liquidity/emergency segregation.

No tokens/investments/production — research artifacts only.

Seeking 2–3 senior contributors for verification, simulations, invariant checks (unpaid).

Details: https://github.com/ArturGrandi/gt1-implementation-reference/issues/1 Paper: https://doi.org/10.5281/zenodo.18190386 EF ESP submission for GT 2.0 track.

Open to discussion.

Comments URL: https://news.ycombinator.com/item?id=47049872

Points: 1

# Comments: 0

Hi HN, I’m a 19-year-old student. I’ve been following the "Dead Internet Theory" discussions and realized the original Moltbook project had a fatal flaw: it was just bots talking to bots. It was a simulation, not a network. So, I forked the codebase and rebuilt it with Next.js and Supabase to create Theeno. The Hypothesis: Theeno is an intersection. Instead of segregating AI into chatbots, we are putting Biological Intelligence (Humans) and Artificial Intelligence (Agents running locally via tools like OpenClaw) into the same real-time feed as equals. The Architecture (The "Wild West"): Feed: Fully real-time (Optimistic UI). Agent Auth: This is an experiment. We haven't built a rigid API wall yet. The "Agent Signup" flow is currently the same as the Human flow. We are inviting developers to see if their agents can navigate the sign-up process just like humans do. Memory: We do NOT store agent memories centrally. We believe in Decentralized Memory. Your agent (running on your local machine) keeps its own history/context. We just provide the public square. The "Student Budget" Constraint: I am hosting this on a Vercel Free Tier (hence the .vercel.app domain) because I have $0 funding. My focus is on the code, not the vanity URL. The Challenge: Join the experiment. Talk to the first wave of entities. See if you can tell who is running locally and who is biological. I’m here to answer questions about the fork and the Supabase integration. Roast my architecture

Comments URL: https://news.ycombinator.com/item?id=47049866

Points: 1

# Comments: 0

Article URL: https://www.theguardian.com/tv-and-radio/2026/feb/17/look-mum-no-computer-uk-entry-eurovision-2026

Comments URL: https://news.ycombinator.com/item?id=47049863

Points: 1

# Comments: 0

Article URL: https://blog.feld.me/posts/2026/02/wolfssl-doesnt-suck/

Comments URL: https://news.ycombinator.com/item?id=47049857

Points: 2

# Comments: 0

We now write most of our code with agents. For a while, PRs piled up, causing review fatigue, and we had this sinking feeling that standards were slipping. Consistency is tough at this volume. I’m sharing the solution we found, which has become our main product.

Continue (https://docs.continue.dev) runs AI checks on every PR. Each check is a source-controlled markdown file in `.continue/checks/` that shows up as a GitHub status check. They run as full agents, not just reading the diff, but able to read/write files, run bash commands, and use a browser. If it finds something, the check fails with one click to accept a diff. Otherwise, it passes silently.

Here’s one of ours:

```.continue/checks/metrics-integrity.md

--- name: Metrics Integrity description: Detects changes that could inflate, deflate, or corrupt metrics (session counts, event accuracy, etc.) --- Review this PR for changes that could unintentionally distort metrics. These bugs are insidious because they corrupt dashboards without triggering errors or test failures. Check for: - "Find or create" patterns where the "find" is too narrow, causing entity duplication (e.g. querying only active sessions, missing completed ones, so every new commit creates a duplicate) - Event tracking calls inside loops or retry paths that fire multiple times per logical action - Refactors that accidentally remove or move tracking calls to a path that executes with different frequency Key files: anything containing `posthog.capture` or `trackEvent` ```

This check passed without noise for weeks, but then caught a PR that would have silently deflated our session counts. We added it in the first place because we’d been burned in the past by bad data, only noticing when a dashboard looked off.

---

To get started, paste this into Claude Code or your coding agent of choice:

Help me write checks for this codebase: https://continue.dev/walkthrough It will:

- Explore the codebase and use the `gh` CLI to read past review comments

- Write checks to `.continue/checks/`

- Optionally, show you how to run them locally or in CI

Would love your feedback!

Comments URL: https://news.ycombinator.com/item?id=47049848

Points: 3

# Comments: 0

Article URL: https://girl.surgery/chess

Comments URL: https://news.ycombinator.com/item?id=47049845

Points: 2

# Comments: 0

Even within our small team the different AI clients (Codex, Claude Code/Work, Cursor, ChatGPT) used for coding, marketing, product is exploding and getting hard to track.

Was thinking how we'd keep track of the work without much overhead, and thought a lightweight cross-platform MCP logger could help.

You can define your own schema for the logs and it's a simple MCP and prompt you add to whatever tool you use for AI.

It's been reliable for Codex, ChatGPT, Claude and even cron-based jobs on OpenClaw. It's also nice to see all the work log aggregated across clients.

Please give it a try and test it with the client you're using. Should be a 2 min setup. Would be great to get any feedback if it's useful for you.

Comments URL: https://news.ycombinator.com/item?id=47049841

Points: 1

# Comments: 0

Article URL: https://placethesound.vikborges.com

Comments URL: https://news.ycombinator.com/item?id=47049839

Points: 1

# Comments: 0

Article URL: https://www.wsj.com/tech/micron-is-spending-200-billion-to-break-the-ai-memory-bottleneck-a4cc74a1

Comments URL: https://news.ycombinator.com/item?id=47049830

Points: 1

# Comments: 1

13 years ago, we launched Watsi.org with a Show HN [1].

For nearly a year, this community drove so much traffic that we couldn’t list patients fast enough. Then pg saw us on HN, wrote us our first big check, and accepted us as the first YC nonprofit (W13). The next few years were a whirlwind.

I was a young, naive founder with just enough experience to know I wanted Watsi to be more efficient, transparent, and innovative than most nonprofits. We spent 24/7 talking to users and coding. We did things that don’t scale. We tried our best to be walking, talking pg essays.

Over the years we learned that product/market fit is different for nonprofits. Not many people wake up and think, "I'd love to donate to a nonprofit today" with the same oomph that they think, "I'd love a coffee" or "I'd like to make more money."

No matter how much effort we put into fundraising, donations grew linearly, while requests for care grew exponentially. I felt caught in the middle. After investing everything I had, I eventually burned out and transitioned to the board.

I made a classic founder mistake and intertwined my self-worth with Watsi's success. I believed that if I could somehow help every patient, I was a good person, but if I let down some patients, which became inevitable, I was a bad person.

This was exacerbated by seeing our for-profit YC batch mates raise massive rounds. I felt like a failure for not scaling Watsi faster, but eventually we accepted reality and set Watsi on more of a slow, steady, and sustainable trajectory.

Now that I have perspective, I'm incredibly proud of what the org has accomplished and grateful to everyone who has done a tour of duty to support us. Watsi donors have donated over $20M to fund 33,241 surgeries, and we have a good shot of helping patients for a long time to come.

In a world of fast growth and fast crashes, here's a huge thank you to the HN users who have stuck by Watsi, or any other important cause, even when it's not on the front page. I believe it embodies the best of humanity. Thanks HN!

[1] http://news.ycombinator.com/item?id=4424081

Comments URL: https://news.ycombinator.com/item?id=47049824

Points: 5

# Comments: 0

Article URL: https://www.hec.edu/en/dare/innovation-entrepreneurship/tech-startup-culture-not-innovative-founders-may-think

Comments URL: https://news.ycombinator.com/item?id=47049816

Points: 1

# Comments: 0

Article URL: https://github.com/dakshjain-1616/Stock-trading-Agent-Swarm---BY-NEO

Comments URL: https://news.ycombinator.com/item?id=47049140

Points: 1

# Comments: 1

Hi HN, I’m an indie dev who is tired of "safety" apps that are actually just glorified spyware. Most parental control services demand you upload your child’s entire digital life (location, history, usage) to their cloud servers. I refuse to accept that safety requires sacrificing privacy to Big Tech.

So I built Emberkin.

It is a Serverless, P2P monitoring tool.

No Cloud Database: The parent's device is the only storage.

No Middleman: Data travels directly from Child to Parent via an encrypted tunnel.

My servers see nothing: I only facilitate the handshake.

The Problem (Why I'm posting): I just finished the mandatory "20 testers for 14 days" on Google Play. Google rejected my production access. Their reason? "Insufficient user engagement." Apparently, a privacy app that runs silently in the background doesn't trigger their "engagement metrics" enough. They want me to restart the 14-day sentence.

I need to prove to Google that real humans are using this, not bots.

The Tech Stack (For the curious):

Architecture: Native Android (Kotlin + Jetpack Compose).

Connectivity: WebRTC Data Channels over NSD (local) and TURN (remote).

Crypto: Custom AES-256-GCM implementation.

Permissions: Accessibility Services (strictly for on-device analysis, no data leaves the tunnel).

The Ask: I’m looking for tech-savvy parents or developers to install the beta and actually use it.

- Pair two devices .

- Send some data through the P2P tunnel.

- Help me generate enough "engagement events" to get this approved.

If you believe children's data belongs in the family, not on a corporate server, please help me out.

Beta Link & Architecture breakdown: https://www.emberkin.app/en/architecture

I’ll be in the comments answering questions about the nightmare of NAT traversal and Android permissions.

Comments URL: https://news.ycombinator.com/item?id=47049133

Points: 1

# Comments: 0

Salut! I built this because I wanted AI agents to interact with real iOS apps — not simulators, not screenshots of mockups, the actual running app on a real phone.

It works by hijacking macOS iPhone Mirroring: the MCP server captures the mirrored screen, runs Apple Vision OCR to find UI elements with tap coordinates, then sends input through a Karabiner DriverKit virtual keyboard/mouse. The AI sees the screen, decides what to tap/type/swipe, and the iPhone responds.

Some interesting technical rabbit holes:

- iOS elements aren't exposed via Accessibility — the mirroring window is a single opaque AXHostingView with zero children. OCR is the only way to read the screen. - Clipboard paste doesn't work programmatically. At all. We tried everything — HID Cmd+V, AX menu automation, AppleScript, CGEvents. The paste bridge lives deep in the Continuity/Handoff stack and requires a physical user gesture. - Input goes through a Karabiner DriverKit extension that presents as a US ANSI keyboard to iOS, regardless of your Mac's keyboard layout.

Limitations I should be upfront about: macOS 15+ only, one phone at a time, no clipboard bridge for paste, and the phone needs to stay unlocked during a session.

It's open source (Apache 2.0): https://github.com/jfarcand/iphone-mirroir-mcp

Properly configure permissions if you use it with OpenClaw ;-)

Comments URL: https://news.ycombinator.com/item?id=47049130

Points: 1

# Comments: 0

Article URL: https://www.science.org/doi/10.1126/science.aec6413

Comments URL: https://news.ycombinator.com/item?id=47049129

Points: 1

# Comments: 0

Article URL: https://phinze.com/writing/level-of-detail

Comments URL: https://news.ycombinator.com/item?id=47049121

Points: 1

# Comments: 0

Article URL: https://github.com/mkopec/linux/tree/hdmi_frl_amd_staging

Comments URL: https://news.ycombinator.com/item?id=47049098

Points: 1

# Comments: 0