XXXX

We still can't stop plagiarism in undergraduate computer science (2018) 7 by wonger_ | 11 comments on Hacker News.

Sguaba: Hard-to-misuse rigid body transforms for engineers 4 by lukastyrychtr | 0 comments on Hacker News.

Vibe coding is not the same as using an AI assistant 44 by adityaoberai1 | 15 comments on Hacker News.

Colour and Shape: Using Computer Vision to Explore the Science Museum (2020) 5 by airstrike | 1 comments on Hacker News.

Open-sourcing circuit tracing tools 14 by jlaneve | 3 comments on Hacker News.

Airlines are charging solo passengers higher fares than groups 70 by _tqr3 | 58 comments on Hacker News.

What does "Undecidable" mean, anyway 16 by BerislavLopac | 4 comments on Hacker News.

Why is it so hard to get families to live in community houses? 27 by caser | 29 comments on Hacker News.

Show HN: Maestro – A Framework to Orchestrate and Ground Competing AI Models 9 by defqon1 | 1 comments ive spent the past few months designing a framework for orchestrating multiple large language models in parallel — not to choose the “best,” but to let them argue, mix their outputs, and preserve dissent structurally. It’s called Maestro heres the whitepaper https://github.com/d3fq0n1/maestro-orchestrator (Narrative version here: https://defqon1.substack.com/p/maestro-a-framework-for-coher... ) Core ideas: Prompts are dispatched to multiple LLMs (e.g., GPT-4, Claude, open-source models) The system compares their outputs and synthesizes them It never resolves into a single voice — it ends with a 66% rule: 2 votes for a primary output, 1 dissent preserved Human critics and analog verifiers can be triggered for physical-world confirmation (when claims demand grounding) The feedback loop learns not only from right/wrong outputs, but from what kind of disagreements lead to deeper truth Ma...

Show HN: Free mammogram analysis tool combining deep learning and vision LLM 8 by coolwulf | 7 comments I've built Neuralrad Mammo AI, a free research tool that combines deep learning object detection with vision language models to analyze mammograms. The goal is to provide researchers and medical professionals with a secondary analysis tool for investigation purposes. Important Disclaimers: - NOT FDA 510(k) cleared - this is purely for research investigation - Not for clinical diagnosis - results should only be used as a secondary opinion - Completely free - no registration, no payment, no data retention What it does: 1. Upload a mammogram image (JPEG/PNG) 2. AI identifies potential masses and calcifications 3. Vision LLM provides radiologist-style analysis 4. Interactive viewer with zoom/pan capabilities You can try it with any mass / calcification mammo images, e.g. by searching Google: mammogram images mass Key Features: - Detects and classifies masses (benign/malignant) - Ide...

Mutmut – Python Mutation Tester 3 by e-topy | 0 comments on Hacker News.

Advice to Tenstorrent 7 by lexoj | 3 comments on Hacker News.

Ask HN: What are you working on? (May 2025) 16 by david927 | 38 comments What are you working on? Any new ideas that you're thinking about? on Hacker News. What are you working on? Any new ideas that you're thinking about?

Beware the Complexity Merchants 2 by kiyanwang | 0 comments on Hacker News.

Use ramoops for logging under Linux (2021) 5 by zdw | 0 comments on Hacker News.

Exposed Industrial Control Systems and Honeypots in the Wild [pdf] 5 by gnabgib | 0 comments on Hacker News.

Show HN: I made an infinite gallery of AI-generated 3D skeuomorphic icons 7 by clarkcharlie03 | 1 comments on Hacker News.

We’ll be ending web hosting for your apps on Glitch 13 by js4ever | 4 comments on Hacker News.

Show HN: Representing Agents as MCP Servers 12 by saqadri | 4 comments Hey HN! A few months ago we shared mcp-agent ( https://github.com/lastmile-ai/mcp-agent ) [1][2], a lightweight framework that implements every agent pattern from Anthropic’s Building Effective Agents blog [3] and handles MCP server/client management seamlessly. Our core bet is that connecting LLMs to tools, resources, and external systems will soon be MCP-native by default. Today we're launching a significant update: Agents as MCP servers. Currently "agentic" behavior exists only on the MCP client side – clients like Claude or Cursor use MCP servers to solve tasks. With this update, Agents can be MCP servers themselves, so that any MCP client can invoke, coordinate and orchestrate agents the same way it does with any other MCP server. This paradigm shift enables: 1. Agent Composition: Build complex multi-agent systems over the same base protocol (MCP). 2. Platform Independence: Use your agents from a...

Red Programming Language 7 by hotpocket777 | 1 comments on Hacker News.

WireGuard-vanity-keygen: WireGuard vanity key generator 5 by simonpure | 0 comments on Hacker News.

Show HN: A native Hacker News reader with integrated todo/done tracking 3 by coolwulf | 0 comments Hey HN! I'm excited to share a tool I've been working on - a native Hacker News reader built with Rust and egui. Here's a screenshot: https://github.com/haojiang99/hacker_news_reader/blob/main/s... . As a daily HN reader, I've always struggled with keeping track of interesting posts I want to read later. Browser tabs pile up, bookmarks get forgotten, and I lose track of what I've already read. I needed a way to: 1. Browse HN efficiently (across all sections - hot, new, show, ask, jobs, best) 2. Quickly mark posts as "todo" for later reading 3. Mark posts as "done" when finished 4. Filter and search effectively I couldn't find a tool that combined all these features, so I built one. It's been tremendously helpful for my own HN reading workflow, and I thought others might find it useful too. Features: - *Integrated todo tracking*: Mark storie...

The forbidden railway: Vienna-Pyongyang (2008) 12 by 1317 | 5 comments on Hacker News.

Show HN: Stack Error – ergonomic error handling for Rust 6 by garrinm | 3 comments Stack Error reduces the up-front cost of designing an error handling solution for your project, so that you focus on writing great libraries and applications. Stack Error has three goals: 1. Provide ergonomics similar to anyhow. 2. Create informative error messages that facilitate debugging. 3. Provide typed data that facilitates runtime error handling. on Hacker News. Stack Error reduces the up-front cost of designing an error handling solution for your project, so that you focus on writing great libraries and applications. Stack Error has three goals: 1. Provide ergonomics similar to anyhow. 2. Create informative error messages that facilitate debugging. 3. Provide typed data that facilitates runtime error handling.

The Fall of Roam 13 by ingve | 0 comments on Hacker News.

Largest database of nanosatellites, over 4400 nanosats and CubeSats 3 by ohjeez | 0 comments on Hacker News.

Show HN: KVSplit – Run 2-3× longer contexts on Apple Silicon 48 by dipampaul17 | 1 comments I discovered that in LLM inference, keys and values in the KV cache have very different quantization sensitivities. Keys need higher precision than values to maintain quality. I patched llama.cpp to enable different bit-widths for keys vs. values on Apple Silicon. The results are surprising: - K8V4 (8-bit keys, 4-bit values): 59% memory reduction with only 0.86% perplexity loss - K4V8 (4-bit keys, 8-bit values): 59% memory reduction but 6.06% perplexity loss - The configurations use the same number of bits, but K8V4 is 7× better for quality This means you can run LLMs with 2-3× longer context on the same Mac. Memory usage scales with sequence length, so savings compound as context grows. Implementation was straightforward: 1. Added --kvq-key and --kvq-val flags to llama.cpp 2. Applied existing quantization logic separately to K and V tensors 3. Validated with perplexity metrics across context l...

Making code last a long time 10 by robinhouston | 1 comments on Hacker News.

Demystifying Ruby (1/3): It's all about threads 26 by kadrek | 0 comments on Hacker News.

We Made CUDA Optimization Suck Less 6 by jaberjaber23 | 1 comments on Hacker News.

Various Things in MetaPost (2019) 11 by Tomte | 0 comments on Hacker News.

Android and Wear OS are getting a big refresh 24 by whatever3 | 34 comments on Hacker News.

OpenTelemetry Protocol with Apache Arrow 11 by tanelpoder | 1 comments on Hacker News.

Why National Labs are investing (heavily) in AI 11 by LAsteNERD | 7 comments on Hacker News.

Toward a Sparse and Interpretable Audio Codec 5 by cochlear | 0 comments on Hacker News.

An online exhibition of pretty software bugs 12 by tobr | 0 comments on Hacker News.

For $595, you get what nobody else can give you for twice the price (1982) [pdf] 43 by indigodaddy | 10 comments on Hacker News.

Microsoft Teams will soon block screen capture during meetings 19 by josephcsible | 27 comments on Hacker News.

Even Tesla's Insurance Arm Is Getting Wrecked 36 by ryan_j_naughton | 19 comments on Hacker News.

Graphcore unveils GC200 and M2000 IPU Machine–1 petaFLOP "pizza box" AI server 13 by bit_qntum | 2 comments on Hacker News.

Odin, a Pragmatic C Alternative with a Go Flavour 15 by hmac1282 | 5 comments on Hacker News.

Inventing the Adventure Game (1984) 12 by CaesarA | 0 comments on Hacker News.

Show HN: Extension for full-text browser history search 15 by ApbNfMR | 6 comments Hey. I’ve been working on Rearview, a browser extension that makes browsing history more useful. It’s available for Chrome, Edge, and Firefox. What it does: - Full-text Search: Search page content, not just URLs or titles. - More Filter: Organize history by date, time, or visits. - AI Assistant: Get insights from your history. (Optional, with your own api key.) Everything stays local in IndexedDB. Feedback & Feature request welcome. BTW, since Firefox does not provide a favicon URLs implementation ( https://bugzilla.mozilla.org/show_bug.cgi?id=1315616 ),I am currently requesting icons in Firefox via https://icon.horse/ , the performance seems not ideal. Is there a more recommended solution? on Hacker News. Hey. I’ve been working on Rearview, a browser extension that makes browsing history more useful. It’s available for Chrome, Edge, and Firefox. What it does: - Full-text Search: Search page conte...

Block Diffusion: Interpolating Autoregressive and Diffusion Language Models 5 by t55 | 0 comments on Hacker News.

RSC for Astro Developers 13 by feross | 1 comments on Hacker News.

Single hair-like electrode outperforms traditional 21-lead EEG 12 by westurner | 4 comments on Hacker News.

Transform DOCX into LLM-ready data 3 by sergiishcherbak | 2 comments on Hacker News.

GenAI-Accelerated TLA+ Challenge 6 by lemmster | 1 comments on Hacker News.

Show HN: Real-time AI Voice Chat at ~500ms Latency 30 by koljab | 4 comments on Hacker News.

Cursor hits $9B valuation 56 by bookofjoe | 91 comments on Hacker News.

Reading Zanzibar 4 by surprisetalk | 0 comments on Hacker News.

Show HN: Free, 100% in browser PDF editor 38 by philjohnson | 3 comments Add text, input boxes, pictures, signatures, delete pages, merge PDFs and password protect them. All happening in the browser, 100% free and no sign-up. on Hacker News. Add text, input boxes, pictures, signatures, delete pages, merge PDFs and password protect them. All happening in the browser, 100% free and no sign-up.

Elm Test Distributions 10 by todsacerdoti | 0 comments on Hacker News.

Creating beautiful charts with JRuby and JFreeChart 6 by headius | 1 comments on Hacker News.

Hybrid AC/DC distribution system with a shared neutral (2020) 4 by 1970-01-01 | 0 comments on Hacker News.