What are your top picks of some great launch videos recently which aren't just cool cinematically but also bring across what they are trying to solve more clearly?

I'm the author of a new preprint that tries to resolve why major U.S. sexual behavior surveys appeared to report contradictory trends over the past decade. The key move is separating never-occurrence from temporary inactivity among the experienced, rather than averaging them together. That decomposition is applied symmetrically across surveys and validated against an independent dataset. The paper then treats the remaining discrepancy as a debugging problem: • check distributions for digit heaping and compression • look for stock–flow reversals consistent with under-reporting • compare adjacent survey waves for internal consistency • cross-validate against an external series not subject to the same reporting incentives Once those diagnostics are applied, the conflicting results reconcile cleanly. This is a methods/measurement paper, not a causal one. The contribution is showing how small reporting artifacts and aggregation choices can produce large apparent disagreements—even in high-quality surveys—when they aren't handled carefully. (One note for the methodologically inclined: conditioning on "sexually experienced" looks like it could induce collider bias. Section 4 and Appendix D5 address this directly—the gender gap in sexual debut didn't change differentially, so selection into the analysis sample is symmetric.) Preprint: https://osf.io/preprints/socarxiv/jcdbm_v2 Replication code: https://github.com/Joshfkon/ResearchPaper_PartnershipGap Happy to discuss the diagnostics, decomposition logic, or limitations.

I built Invoice Studios because I was tired of messy invoice templates and subscription tools. It’s a local‑first desktop app: create invoices/quotes, live preview, export clean PDFs. Looking for feedback on the UX and the exported PDF layout.

X-AI recently open sourced their new recommendation algorithm.

I wanted to see exactly how the X "For You" algorithm decides whether to recommend your tweet or not, so I built this 'playable' CRT-styled simulator that runs a simpler version of X's recommendation pipeline right in your browser.

It's a "playable documentary" that allows you to type raw text and watch it physically travel through tokenization, embedding, safety filtering, and final ranking, all based on the X-AI reference docs.

Under the hood it's running real local ML inference (a tiny embedding model using Transformers.js) to generate embeddings and score content on the fly - all locally on your machine.

Would love some feedback!

I use Claude Code heavily and wanted to search through past sessions, see what Claude was doing in long-running tasks, and monitor multiple sessions at once. I also was looking for an exscus to build something end-to-end with just Claude on the implementation.

I had Claude create a task system, hook it up to a `/task` command, then can use `bun ralph` to churn through any open tasks.

Try it out and feel free to contribute!

I built OMIU.ME as a small indie project. Not trying to reinvent profile or link-in-bio sites, rather just approach the same idea with a more predictable editor. I'll continue to iterate on it over time and add features.

The problem with LLMs isn't intelligence; it's amnesia and dishonesty.

Hey HN,

I’ve spent the last few months building Remember-Me, an open-source "Sovereign Brain" stack designed to run entirely offline on consumer hardware.

The core thesis is simple: Don't rent your cognition.

Most RAG (Retrieval Augmented Generation) implementations are just "grep for embeddings." They are messy, imprecise, and prone to hallucination. I wanted to solve the "Context integrity" problem at the architectural layer.

The Tech Stack (How it works):

QDMA (Quantum Dream Memory Architecture): instead of a flat vector DB, it uses a hierarchical projection engine. It separates "Hot" (Recall) from "Cold" (Storage) memory, allowing for effectively infinite context window management via compression.

CSNP (Context Switching Neural Protocol) - The Hallucination Killer: This is the most important part. Every memory fragment is hashed into a Merkle Chain. When the LLM retrieves context, the system cryptographically verifies the retrieval against the immutable ledger.

If the hash doesn't match the chain: The retrieval is rejected.

Result: The AI visually cannot "make things up" about your past because it is mathematically constrained to the ledger. Local Inference: Built on top of llama.cpp server. It runs Llama-3 (or any GGUF) locally. No API keys. No data leaving your machine.

Features:

Zero-Dependency: Runs on Windows/Linux with just Python and a GPU (or CPU).

Visual Interface: Includes a Streamlit-based "Cognitive Interface" to visualize memory states. Open Source: MIT License. This is an attempt to give "Agency" back to the user. I believe that if we want AGI, it needs to be owned by us, not rented via an API.

Repository: https://github.com/merchantmoh-debug/Remember-Me-AI

I’d love to hear your feedback on the Merkle-verification approach. Does constraining the context window effectively solve the "trust" issue for you?

It's fully working - Fully tested. If you tried to Git Clone before without luck - As this is not my first Show HN on this - Feel free to try again.

To everyone who HATES AI slop; Greedy corporations and having their private data stuck on cloud servers.

You're welcome.

Cheers, Mohamad