🛠️ Hacker News Tools

Cursed circuits #6: reverse avalanche oscillator

Spider venom kills varroa mites without harming honeybees

What's slowing down the AI buildout

Show HN: I mapped 8.5M research papers into an interactive atlas When I read papers, I have to jump between multiple tabs to find the dataset, code, videos, peer reviews, and so on. I tried to fix this with this project.<p>It started as a project just for papers on arXiv, but after its initial success on Twitter (got like 1.9k views: the most I have gotten for a post), I have now expanded it to include other openly available papers from PubMed Central, bioRxiv, medRxiv, and eLife. These papers have been linked with their genes, proteins, diseases, drugs, clinical trials, 3D protein structures, code, and cited and similar papers.<p>This project now has four parts:<p>First, a map. I embedded nearly 8.5M papers (with SPECTER2), ran UMAP for 2D representation, and rendered them as a scatterplot. The dots can be clicked to see brief information about the papers, like an LLM TLDR, key findings, peer reviews, linked entities, and more. The clusters are also labeled, though you might have to zoom in.<p>Second, I built a detailed paper page for each paper. They give you the paper&#x27;s full text, images, videos, peer reviews (from OpenReview), GitHub links, Hugging Face dataset&#x2F;model links, clinical trials, genes, diseases, 3D protein structures, cited papers, and similar papers. You can also copy the whole page, including the full paper text and image URLs, as markdown for your LLM.<p>Third, I have released an extension so you can read all this information in your sidebar by clicking &quot;open in Tomesphere&quot; that shows up in arXiv, PMC, bioRxiv, Google Scholar, or medRxiv. I have tried to provide as much information as possible in the extension, though for things like viewing all the images or a 3D protein structure, you might still have to go to the paper page using the link provided in the extension.<p>Fourth, all this data is available for your LLM via MCP. The MCP does have a 50-query free limit (this jumps 10x with signup).<p>Note: this project is still in beta, so papers might have some mismatched information. I am rolling out feedback forms soon to improve the data quality. Thank you so much for taking the time to read this.

Show HN: Cyrinx (36kbps Acoustic Transport) Working with Fable 5, a MacBook, and a Pixel phone, I built an acoustic transport library that is several orders of magnitude faster than existing SoTA open source options like ggwave, quiet, minimodem, or Chirp.<p>Paper: <a href="https:&#x2F;&#x2F;cyrinx.org&#x2F;cyrinx-acoustic-link.pdf" rel="nofollow">https:&#x2F;&#x2F;cyrinx.org&#x2F;cyrinx-acoustic-link.pdf</a><p>Apache 2.0 source: <a href="https:&#x2F;&#x2F;github.com&#x2F;dweekly&#x2F;cyrinx" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;dweekly&#x2F;cyrinx</a>

MIRA: Multiplayer Interactive World Models Trained on Rocket League <a href="https:&#x2F;&#x2F;mira-wm.com&#x2F;blog-post&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mira-wm.com&#x2F;blog-post&#x2F;</a>

We made Grok 4.5, GPT-5.5, and Claude build the same apps

The family of a man shot by the Tennessee National Guard demands video release

Show HN: I ran 70 MCP servers in a sandbox and logged what they do

Creatine doesn't just build muscle. It may also help fight cancer

Benchmarking coding agents on Databricks' multi-million line codebase

Separating signal from noise in coding evaluations

Most slopcode projects are abandoned and deleted within months of release

Agentic test processes, LLM benchmarks, and other notes on agentic coding fr

Show HN: Onboard-CLI, a LLM powered and AST-based tool to visualize codebase

Show HN: Hnwork.app – UI for Who is hiring posts Hey HN, I built a UI on top of the &quot;Who is hiring&quot; posts. Take a look at <a href="https:&#x2F;&#x2F;hnwork.app" rel="nofollow">https:&#x2F;&#x2F;hnwork.app</a>!<p>One of the downsides of unstructured text posts is the readability due to it being free-form and having little to no format. While there are other tools that have been built over the years to make perusing Who is hiring posts easier, I took a try on making my own (I actually tried to build this at a YC hackathon a few years back, but got around to completing it recently).<p>Features: - Text search and search filters - Original post text with call outs to important information - Removes posts that aren’t on topic (complaints, seeking work, vague or missing contact info) - Analytics - API<p>In addition, job posters can create accounts to submit postings through the app. While I don’t expect posting to move over to this app, it’s what I envisioned what a Who is hiring thread would like as an app: - Structured postings with required fields (e.g., salary range required) - Job posters get notifications about comments on their posts - Job posters get verified through their email before posting (e.g., someone posting a Sony job has a Sony email address) - Companies with multiple job posters can coordinate postings and view past postings - Admins can audit and approve companies and posts<p>Job seekers can also create an account to post comments or get access to a simple API but otherwise browsing doesn’t require any kind of signup&#x2F;signin.<p>I’m open to feedback: let me know if you’d like me to ingest more data from past months, something is missing or broken, or there’s a new feature you’d like to see. Thanks!

Grok 4.5 <a href="https:&#x2F;&#x2F;cursor.com&#x2F;blog&#x2F;grok-4-5" rel="nofollow">https:&#x2F;&#x2F;cursor.com&#x2F;blog&#x2F;grok-4-5</a>

Show HN: Requirements Engineering with Formal Verification I&#x27;ve been building an open source formal methods system (fizzbee.io) for the past few years.<p>Today I&#x27;m launching a new app built on the same technology. It performs requirements engineering using formal verification to uncover gaps and produce precise instructions for your coding agents to follow.<p>When given a prompt, it - asks high signal follow-up questions - converts to formal spec and identifies complex requirements gaps - generates validation scenario<p>At the end, it produces a specification document that can be shared with coding agents. In my trials on various projects, it produces working code in fewer iterations.<p>Please give it a try and share your feedback. <a href="https:&#x2F;&#x2F;fizzbee.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;fizzbee.ai&#x2F;</a><p>You can also look at a sample project. <a href="https:&#x2F;&#x2F;fizzbee.ai&#x2F;projects&#x2F;94bf2869-97a1-445c-8f5d-4445848bba11&#x2F;view" rel="nofollow">https:&#x2F;&#x2F;fizzbee.ai&#x2F;projects&#x2F;94bf2869-97a1-445c-8f5d-4445848b...</a>

Show HN: Microsoft releases Flint, a visualization language for AI agents Data visualizations are the bridge between user and data.<p>But building AI agents that can generate visualizations reliably can be very tricky:<p>- simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability<p>We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple high-level specs. The result is also very human understandable and adaptable. Flint powers data formulator for generating visualizations (another open source project from microsoft <a href="https:&#x2F;&#x2F;data-formulator.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;data-formulator.ai&#x2F;</a>).<p>Flint is available open source, and we built a MCP server that you can directly plug flint in your favorite agent app to play with data.

PlayStation can delete all your digital games after 3 years of inactivity (EU)