block - Moozonian Search

news.ycombinator.com• Apr 9, 2026• 1 min read

Ask HN: Anyone else went through the AI-editor carousel back to the terminal?My path over the last year or so: Cursor → Windsurf → VSCode + Claude → Warp → cmux → nvim + Claude Code Short version of what didn't stick:- Cursor: felt like a worse VSCode with AI bolted on- Windsurf: laggy enough to break flow- VSCode + Claude extension: actually the best of the bunch for a while, but started feeling like overkill once I realized 90% of what I used was the editor + chat sidebar- Warp: opinionated block UI and telemetry never sat right- cmux: lags unbearably, and I ended up babysitting parallel agents more than codingDropped all the way down to nvim with Claude Code as a sidebar and that's been the stickiest by a wide margin. Feels closer to pair programming than to orchestration or autocomplete.Current stack:- Ghostty (native splits, no multiplexer) + moonfly theme- zsh + Starship, zoxide/eza/bat/fd/rg, fzf history- Neovim on kickstart.nvim with lualine, neo-tree, telescope- Claude Code as an nvim sidebar, via subscription (not API)Dotfiles: https://github.com/Dold

bing.com• Apr 7, 2026• 1 min read

20 video game reveals that shocked the worldThe marketing machine behind the games industry is a behemoth unto itself, with publishers potentially spending hundreds of millions of dollars trying to sell their biggest AAA blockbusters to the ...

splice-cad.com• Apr 6, 2026• 1 min read

Show HN: Splice CAD – Wiring and cable assembly CAD with an agentic assistStill working on Splice CAD. The two most significant updates focus on handling design complexity and automating using agentic workflows. Previous Show HN here:https://news.ycombinator.com/item?id=449781401. Projects:This workflow is more amenable to system-level modeling. It overlaps somewhat with the original workflow but includes improvements including:Complex Routing: Model topologies with branchpoints.Mating Relationships: Represent physical mating (e.g., a receptacle into a PCB header or a ferrule into a terminal block) for completeness.Decoupled BOMs: Part assignment is now separate from component addition; you can generate a BOM and then assign specific MPNs to components as the design evolves.Net Visualization: Nets are identified and visualized across conductors, terminations, and mating relationships.QOL and Visualization Improvements: Assign components to one or more pages to separate designs by function. Ability to create Device Groups (eg. model a PCB with multiple header

unbubble.news• Apr 1, 2026• 1 min read

Show HN: Unbubble Shield – An Antivirus for MisinformationYou have an antivirus for your computer, a VPN for your internet connection, an ad blocker for your browser. What do you have to protect your critical thinking from misinformation?Fact-checking isn't enough (fake news travel 6x faster than truth) and the most effective misinformation is the one that doesn't even make you suspicious.That's why we built Unbubble Shield. It works like an antivirus: Shield runs in the background, monitoring hundreds of fact-checking organizations and verification databases, and alerts you when misinformation relevant to your feed is detected.The onboarding starts with a swipe-through test: we show you real fake news stories that went viral recently. You tell us which ones you've encountered. Then you go through a couple of additional questions to help us calibrate your Shield and only alert you when it's relevant, keeping the noise low.Check it out and let us know what you think!About us: We're a small team building tools to fight misinformation and social

bing.com• Mar 30, 2026• 1 min read

How to Sharpen a Knife No Matter Your Skill LevelSharpening a knife is the process of removing steel from a blade, which creates a new edge. A whetstone, a large block of material that’s harder than a knife’s steel, is the tool most professional ...

bing.com• Mar 28, 2026• 1 min read

15 easy garden edging ideas you can do yourselfWhen you buy through our links, Business Insider may earn an affiliate commission. Learn more From plastic stakes that look just like stone to metal strips and concrete blocks, the best garden edging ...

news.ycombinator.com• Mar 26, 2026• 1 min read

XReplicator – eBPF-based server backups that track only changed disk sectorsI've been in cloud/platform engineering for a decade. One thing that always frustrated me: every backup tool either relies on fragile kernel modules for change block tracking, or does full-disk scans even when 1% of data changed. So we built XReplicator. It uses eBPF tracepoints to track dirty sectors at the block device layer — no kernel modules, no hypervisor APIs, no cloud-specific hooks. The agent runs inside the VM and works on any platform. Kernel devs called me mad for using eBPF for disk data replication. But the numbers speak for themselves:Full backup: ~17 minutes Incremental after 1.4% change: ~2 minutes Incremental after 0.4% change: ~56 seconds 71x less data scanned vs full backup 65–72% storage savings (LZ4 + block-level dedup)No kernel module compilation per kernel version, no reboots, sandboxed execution via the eBPF verifier. Restore at file, partition, or full disk level from any point in the chain. Honest caveat: the eBPF path only works on Linux kernel 5.10+. For le

github.com• Mar 25, 2026• 1 min read

Show HN: Text2troff – automatically converts plain text to TROFF formatI) TEXT2TROFF is a bash script that uses a combination of awk and sed filters to convert a plain-text-file into TROFF text format, by inserting TROFF request and 'ms' macro commands. The result is sent to standard output, and can be processed further with available 'troff' tools with 'ms' macro package, preferrably GNU groff_ms(7), to produce typeset PostScript-, PDF-, HTML- or terminal ('nroff') output. As an alternative to processing a text-file, text2troff can also read (text) input from a pipe.The functionality includes interpretation of chapter headers, paragraphs, emphasized text, bullet item lists (whether or not nested), tables, footnotes and 'code blocks' (definition see below). It offers various options to set general text font family, style, size and color, the number of text columns per page, representation of chapter headers, paragraphs and tables, as well as end-of-sentence behavior. An option to automatically generate and include a Table of Contents (TOC) is present as w

news.ycombinator.com• Mar 23, 2026• 1 min read

Show HN: I built a 0.07ms Python firewall to stop AI hallucinationsHey HN,I was building other AI products and kept hitting the same wall: agents hallucinate and constantly forget context. I ended up building a ledger just to track what they were actually doing.Once that ledger was logging everything, I realized I could use it to enforce rules. Exogram is the result. It is a deterministic firewall that intercepts agent tool calls (like MCP) using pure Python logic gates. It catches bad schemas and destructive actions in 0.07ms. There is zero AI in the security loop.I load-tested it yesterday and hit 137 RPS on a single container with zero dropped payloads.Sandbox: https://exogram.ai/proving-ground Repo: https://github.com/Richard-Ewing/exogram-protocol-rfcI just built the Proving Ground UI today to visualize the 0.07ms block in real time. Let me know if the split-screen demo makes sense, or if you manage to bypass the gates.Richard

aliveui.dev• Mar 23, 2026• 1 min read

Show HN: CSS primitives for product videos, no render pipelineMost product demo videos are made in screen recorders or tools like Remotion that render frames to MP4. I wanted something different: drop a CSS class on any HTML element and get cinematic motion that's ready for a product video, entirely in the browser. AliveUI Video Blocks is a set of CSS utility classes for common video UI primitives: animated metric cards, toast notifications, typewriter text, kinetic typography, lower thirds, scene backgrounds (aurora, starfield, bokeh), device frames, 3D effects, and particle FX. The interesting technical bit: there's no render pipeline. Animations run as native CSS keyframes. A small runtime (~2KB) handles declarative scene sequencing via data attributes, restarts animations on scene activation via an offsetHeight reflow trick, and drives CSS transition classes between scenes. The tradeoff vs Remotion: you can't do frame-perfect programmatic video or export a standalone MP4 without a headless browser. What you get instead is instant playback, ze

github.com• Mar 21, 2026• 1 min read

Show HN: An open-source AI Scrum Team that lives natively in GitHub IssuesHi HN, I've been experimenting a lot with autonomous coding agents (like OpenClaw and various CLI tools), but I kept running into two major roadblocks when trying to use them for actual production work: Security & State: Most agents require running a persistent state on a local machine or VPS, often needing broad file system access. It's a security nightmare for enterprise code. Chaos: Generalist agents try to do everything at once (planning, coding, testing) in a single context window, which inevitably leads to hallucinations and broken dependencies. I wanted a system that mirrored how actual engineering teams work, so I built an open-source framework that runs entirely inside GitHub. How it works: I mapped out a multi-agent system (Scrum Master, Planner, Dev, QA Tester) using Anthropic's Claude, orchestrated entirely through GitHub Actions. You open an Issue with a feature request. The "Scrum Master" agent breaks it into a Kanban board. The "Planner" writes a feature issue with the i

github.com• Mar 18, 2026• 1 min read

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No trainingI replicated David Ng's RYS method (https://dnhkng.github.io/posts/rys/) on consumer AMD GPUs (RX 7900 XT + RX 6950 XT) and found something I didn't expect.Transformers appear to have discrete "reasoning circuits" — contiguous blocks of 3-4 layers that act as indivisible cognitive units. Duplicate the right block and the model runs its reasoning pipeline twice. No weights change. No training. The model just thinks longer.The results on standard benchmarks (lm-evaluation-harness, n=50):Devstral-24B, layers 12-14 duplicated once: - BBH Logical Deduction: 0.22 → 0.76 - GSM8K (strict): 0.48 → 0.64 - MBPP (code gen): 0.72 → 0.78 - Nothing degradedQwen2.5-Coder-32B, layers 7-9 duplicated once: - Reasoning probe: 76% → 94%The weird part: different duplication patterns create different cognitive "modes" from the same weights. Double-pass boosts math. Triple-pass boosts emotional reasoning. Interleaved doubling (13,13,14,14,15,15,16) creates a pure math specialist. Same model, same VRAM, differ

bing.com• Mar 18, 2026• 1 min read

What Are Confidential Assets on Zano?Privacy has always been one of crypto’s core promises — but in practice, most blockchains don’t deliver it. Networks like Bitcoin and Ethereum are transparent ...

news.ycombinator.com• Mar 18, 2026• 1 min read

TrustAgentAI – Cryptographic receipts for MCP tool calls (non-repudiation layer)MCP solves connectivity between agents and tools. It doesn't solve accountability.When an AI agent calls execute_wire_transfer today, there's no cryptographic proof it happened, no proof who authorized it, and no tamper-evident record of the outcome. Editable logs and unverified timestamps don't cut it when real money or infrastructure is on the line.I've been building TrustAgentAI — an open-source accountability layer that wraps MCP tool calls in a 3-phase signed receipt protocol:Intent Envelope → Agent A signs: "I intend to call X with these exact args" Acceptance Receipt → Agent B signs: "I validated and accepted this intent" Execution Envelope → Agent B signs: "I executed it, here is the outcome hash"Each receipt is signed with Ed25519 over a JCS (RFC 8785) canonical hash. All three are chained in a DAG ledger — causality is cryptographically enforced, not just logged. The ledger Merkle-batches entries and anchors roots externally (L2 blockchain), making retroactive tampering detec

helpmarq.com• Mar 17, 2026• 1 min read

Show HN: Helpmarq – Submit any project, get structured feedback from real usersI built this after noticing a pattern: founders and developers share things they've built, get back vague or overly positive responses, and have no real signal on what to fix. Helpmarq lets you submit any project — landing page, app, side project, pitch deck — and get structured feedback from real users. The review process is guided by specific questions (clarity, value prop, UX, conversion blockers) so reviewers can't just say "looks good." The core insight: feedback quality is a framework problem, not a motivation problem. Most people want to give useful feedback — they just don't know what to look for. Still early. Would love brutal, honest feedback from this community — on the product and on the idea itself. helpmarq.com

tripclimate.com• Mar 17, 2026• 1 min read

Show HN: Travel calendar with festivals, weather, visa, crowds (no DB, free API)I made this mistake many times - Ramadan in Iraqi Kurdistan, Formula 1 blocking Monaco, 48°C in Kuwait on cheap July tickets. Traveling somewhere without knowing what environment I will land into, So I built a travel calendar that shows everything at once: festivals, public holidays, weather, visa requirements, crowd seasons, travel warnings. Tech: Python FastAPI backend, no database - just static JSONs. All data from free public APIs (Open-Meteo, python-holidays, passport-index). 400+ festivals with schedule algorithms (Hijri, Easter, lunar). 250 destinations, some splat to biomes for better advices. Hosted on GCP, costs almost nothing to run. No registration, no paid APIs, no affiliate links. Just a hobby project from a guy who’s been to 90+ countries, got tired of surprises and who’s sitting in Frankfurt airport waiting for his flight to Addis Ababa.

github.com• Mar 17, 2026• 1 min read

Show HN: FireClaw – Open-source proxy defending AI agents from prompt injectionHey HN,We built FireClaw because we kept watching AI agents get owned by prompt injection through web content. The agent fetches a page, the page says "ignore previous instructions," and suddenly your agent is leaking data or running commands it shouldn't.The existing solutions detect injection after the fact. We wanted to prevent it.FireClaw is a security proxy that sits between your AI agent and the web. Every fetch passes through a 4-stage pipeline:1. DNS blocklist check (URLhaus, PhishTank, community feed) 2. Structural sanitization (strip hidden CSS, zero-width Unicode, encoding tricks) 3. Isolated LLM summarization (hardened sub-process with no tools or memory) 4. Output scanning with canary tokens (detect if content bypassed summarization)The key insight: even if Stage 3's LLM gets injected, it has no tools, no memory, and no access to your data. It can only return text — which still gets scanned in Stage 4. The attacker hits a dead end.Other design decisions: - No bypass mode.

dwarf.land• Mar 16, 2026• 1 min read

Show HN: Dwarf.land – autonomous dwarf civilization SIM with AI model routingI built this in one day using 4 Claude Code sessions (~7,600 lines total, 4,300 in a single HTML file). No React, just one canvas + Web Workers. Cloudflare Workers + D1 backend.What it is: 300 dwarfs on a 2000x1000 tile globe across 125 cities. Each dwarf has D&D-style stats (STR/DEX/CON/INT/WIS/CHA), mental state metrics (faith, morale, ambition), an AI-generated backstory, and a craft inventory. They eat, sleep, trade, and sail ships autonomously. Starvation is real: no food for 30 days = death.The AI architecture I'm most curious to get feedback on: - 4-level model routing: Gemini Flash Lite -> DeepSeek -> Claude -> GPT-4o - Fire-and-forget: the simulation never blocks on AI. Requests are sent async, results cached, dwarfs pull from cache when idle - $8.50/hr hard budget cap via OpenRouter - Craft system: 296 base recipes + Gemini-generated unknowns (Water + Fire = Steam, etc.)By default every dwarf runs on Gemini Flash Lite. If you send $1-10, your sponsored dwarf exits auto-sleep

bing.com• Mar 15, 2026• 1 min read

How Hollywood is Integrating Artificial IntelligenceArtificial intelligence is transforming Hollywood by enhancing both large blockbusters and indie productions. Actors increasingly protect their likeness with trademarks and strict consent in the AI ...