🛠️ All DevTools

Free financial literacy platform for kids – 90 lessons, no paywall

Show HN: Kctx – A read-only Kubernetes context engine for SREs and AI Agents

Show HN: I am building a map of people who lived in the Roman Empire Driving home from work one day, I wanted to know how many people we knew the names of who lived during the Roman era. Searching around, I found lists of Consuls and officials, but nothing that covered ordinary people or even most people like freedmen and slaves. So I ended up building a pipeline to process the more than 500k Latin inscriptions in the Epigraphic Database Clauss-Slaby <a href="https:&#x2F;&#x2F;edcs.hist.uzh.ch&#x2F;en&#x2F;" rel="nofollow">https:&#x2F;&#x2F;edcs.hist.uzh.ch&#x2F;en&#x2F;</a> and extract the names of people (and attempt to cluster them, but this is a work in progress).<p>There are databases where Classicists have done this manually for specific regions, Trismegistos <a href="https:&#x2F;&#x2F;www.trismegistos.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.trismegistos.org&#x2F;</a> and Latin Inscriptions of the Roman Empire (LIRE) <a href="https:&#x2F;&#x2F;pure.au.dk&#x2F;portal&#x2F;en&#x2F;publications&#x2F;latin-inscriptions-of-the-roman-empire-lire&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pure.au.dk&#x2F;portal&#x2F;en&#x2F;publications&#x2F;latin-inscriptions...</a> are two major efforts I found. But there doesn&#x27;t seem to be a project that did what I set out to do, although I have read in some places that it was believed to be possible.<p>I am not a classicist or a web developer, but I have Claude and Gemini and I can sort of read basic Latin - so I set to work. I used LIRE and another database as ground truth and built a pipeline to extract and process the inscriptions to recover the names. The process I developed uses a high end LLM like Sonnet or Gemini Pro to supervise the extraction and tuning process on a regional basis until the obvious error rate is reasonable. For this, so far, reasonable to me means less than 1-2% in the smaller initial samples of 100-500 and no observed systemic issues. The different regions often need different prompts, so this basically became an exercise in letting the higher level AI tune the prompt for the lower level AI. The extraction when measured against LIRE produces an F1 score between 0.64 and 0.87, but take this with a grain of salt.<p>Once I had done a few regions, I wanted to see the work, so I threw together a pretty crude website but as I am not a web developer, it was crude in how it accessed its data. It does look cool and I also added summarization, and machine translation to each entry. I wanted to eventually get feedback from an actual team of classicists and make the website work better, so I am rewriting it as we speak but it is broadly functional now with a few extra bugs but substantially improved performance compared to the old one. All entries link back to the proper sources, and the old web app linked to several additional sources where the data was present, but I haven&#x27;t gotten that working again just yet on the new one. (The old web interface is still available at <a href="https:&#x2F;&#x2F;roman-names.com" rel="nofollow">https:&#x2F;&#x2F;roman-names.com</a>, but I will warn you it is clunky and not mobile friendly at all)<p>Key findings so far:<p>AI supervised AI extraction saved me time. I was manually tuning things for a while and then the runbook became an idea that I feed my instructions in and let the big AI go with sparse oversight from me.<p>The extraction improved significantly (by about 10 F1 points) when I fed the model the raw text including the markers, vs a cleaned up version of the text.<p>I just thought it was a cool little project and wanted to share. If you happen to work in any adjacent space and there is something I could do better etc let me know.

Farmer donates land for a park, city sells it for $10M as data center land

The Dynamo and the Computer: The Modern Productivity Paradox (1989) [pdf] <a href="https:&#x2F;&#x2F;gwern.net&#x2F;doc&#x2F;economics&#x2F;automation&#x2F;1989-david.pdf" rel="nofollow">https:&#x2F;&#x2F;gwern.net&#x2F;doc&#x2F;economics&#x2F;automation&#x2F;1989-david.pdf</a>

I Hacked into the Worst E-Bike and Fixed It [video]

How JPL keeps the 13-year-old Curiosity rover doing science

Meta steals a tactic from Tesla and builds data centers in tents

Show HN: Learn while you wait for your agents to code Hi HN,<p>While waiting for Claude Code to finish running, It&#x27;s very tempting to start another task or browse the internet. This is what happened to me so I built Foyer to try to learn about what the agents are working on instead of losing focus.<p>Product is an early MVP and would love some feedback on this.

The state of building user interfaces in Rust

Show HN: A 150M model that extracts verbatim evidence spans for RAG, no LLM call

Show HN: Extend UI – open-source UI kit for modern document apps We&#x27;re open-sourcing 14 components &amp; examples today for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more. It&#x27;s MIT licensed and fully customizable.<p>Demo video here: <a href="https:&#x2F;&#x2F;share.extend.ai&#x2F;kRmSGKRF">https:&#x2F;&#x2F;share.extend.ai&#x2F;kRmSGKRF</a><p>When we started, we tried every file viewer and document component library we could find. Unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for <a href="https:&#x2F;&#x2F;extend.ai&#x2F;">https:&#x2F;&#x2F;extend.ai&#x2F;</a>. It was only ever meant to be internal, but enough customers kept asking for it that we decided to open source it.<p>It&#x27;s useful for building document processing agents, real-time user facing document intake flows, or all kinds of internal tooling.<p>We naively thought this would be a solved problem. Turns out, making PDF&#x2F;XLSX&#x2F;DOCX viewers that work at scale is not trivial...we use and maintain it for Extend ourselves, so we&#x27;ve fixed a lot of edge cases that came up while running millions of pages &#x2F; day through our own system. Our hope is that with our resources + community support, it&#x27;ll keep getting better over time.

Show HN: HelixDB – A graph database built on object storage Hey HN, it’s been just over a year since we launched HelixDB (<a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=43975423">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=43975423</a>), a project a friend and I started in college. It’s an OLTP graph database built on object-storage, with native vector search and full-text search (FTS).<p>Why graph, vector and FTS? Graph databases provide a natural cognitive model for data, vectors allow for a semantic understanding of the entities and relationships in the graph, and FTS provides more specific filtering. Many AI-driven applications attempt to combine all of these functionalities by stitching together multiple disconnected systems, but even then there’s no native way to perform joins or queries that span all systems. You still need to handle this logic at the application level.<p>Helix started as a graph DB, but we moved to a hybrid graph&#x2F;vector approach after attempting to build an AI memory system, which led us down the GraphRAG and HybridRAG rabbit hole, where we would need separate graph and vector databases.<p>We knew scalability would be a challenge at each stage of our product&#x27;s development, however our initial focus this past year was to prove out the product through local deployments and was only meant to be run on a single node. Scaling graph DBs remained a difficult and expensive problem we’d have to solve later. Some common ways other graph DBs solve scaling is by duplicating entire datasets across distributed machines (extremely expensive per node), or by sharding the data.<p>Sharding databases is effective and affordable, however, graph data doesn’t have explicit partitions like relational databases do. For example, sharding a relational DB involves splitting up tables. When it comes to graph DBs, the edges can span across any of the partitions, and hopping across multiple machines when traversing nodes is ineffective and computationally expensive.<p>Replicating graph DBs for high availability and better throughput drastically increases the operational cost of the db and still has a limit of how big you can vertically scale. The workload that we’re used for requires storing a huge amount of data for agents, where only a subset of that data is ever needed at any one time. So rather than having the whole thing in memory, we can store it all in object-storage and get the bits we need when they’re needed.<p>Agents benefit from better context, which is achieved from more and better data (more relationships etc). By using S3 as the persistence&#x2F;data layer there is <i>no limit</i> to how big the graph can be or how many relationships you can have, and we can scale to serve throughput and requests by horizontally spinning up nodes and caching relevant subsets of the graph on each node. This way, you get extremely low latency for “hot” data and a p99 of ~100ms for writes and ~50ms for reads from cold storage (S3). Plus you get the benefit of dirt cheap storage.<p>Workloads that HelixDB is currently supporting: - Huge amounts of data (TBs) from which the agents need to search and traverse over - Offering affordable graph storage for companies where cost of graph data is a bottleneck - Consolidating multiple databases, enabling AI agents to have autonomy over companies, helping them become more autonomous. - AI memory - Company brains<p>We’re currently working on our own generalised AI memory layer which will use HelixDB under the hood and be completely open-source. Also, we’re finishing up on pre-filtering for vector search which will allow you to pre-filter based on relationships in the graph, metadata, and sub-graphs. And lastly, GA cloud will be available in the coming weeks.<p>If you want to run Helix locally (either on-disk or in-memory), you can find more info on our github (<a href="https:&#x2F;&#x2F;github.com&#x2F;HelixDB&#x2F;helix-db" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;HelixDB&#x2F;helix-db</a>) or via our docs (<a href="https:&#x2F;&#x2F;docs.helix-db.com&#x2F;database&#x2F;local-development">https:&#x2F;&#x2F;docs.helix-db.com&#x2F;database&#x2F;local-development</a>). If you’re interested in getting started with our distributed cloud, please email us founders@helix-db.com.<p>Many thanks! Comments and feedback welcome!

GitHub Authentication issues related to API requests

The iPad was on Tailscale: a WebRTC debugging story

Show HN: Social network where inviting someone makes you accountable for them Chirpper is invite-only. When you vouch someone in, they join your TrustChain. Their behavior affects your TrustRank, and that propagates up the lineage. No moderators. The accountability is architectural, not policy-based. You can be pseudonymous, but you can&#x27;t be unaccountable. Happy to get into the mechanics in comments.

Apache Burr: Build reliable AI agents and applications

Spoiling Linux Kernel with "sanctioned" code

Show HN: Turn your name into a tree in an infinite procedural shanshui landscape Hi HN! I made this after collecting hundreds of &quot;name → tree&quot; submissions at ITP.<p>Live: <a href="https:&#x2F;&#x2F;landscape.bairui.dev&#x2F;" rel="nofollow">https:&#x2F;&#x2F;landscape.bairui.dev&#x2F;</a> Source: <a href="https:&#x2F;&#x2F;github.com&#x2F;pearmini&#x2F;infinite-landscape" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;pearmini&#x2F;infinite-landscape</a> Plant a tree: <a href="https:&#x2F;&#x2F;tree.bairui.dev&#x2F;" rel="nofollow">https:&#x2F;&#x2F;tree.bairui.dev&#x2F;</a><p>Pan and zoom an infinite procedural landscape. Each name is converted to ASCII codes, which grow into a unique tree (breadth-first branching; repeated digits become mathematical roses). Mountains use midpoint displacement + Perlin noise, with SVG radial gradients in the blue&#x2F;green&#x2F;gold palette from Wang Ximeng&#x27;s &quot;A Thousand Li of Rivers and Mountains.&quot;<p>Inspired by Lingdong Huang&#x27;s {Shan, Shui}* (<a href="https:&#x2F;&#x2F;github.com&#x2F;LingDong-&#x2F;shan-shui-inf" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;LingDong-&#x2F;shan-shui-inf</a>). Every tree is someone&#x27;s name, signed with an APack stamp (<a href="https:&#x2F;&#x2F;apack.bairui.dev&#x2F;" rel="nofollow">https:&#x2F;&#x2F;apack.bairui.dev&#x2F;</a>).<p>Try planting your name, then pan along the ridgeline to find it. &quot;My trees&quot; lets you jump back to ones you planted.<p>Happy to answer questions about the terrain algo, name→tree encoding, or the Riso print we tiled at ITP Winter Show!

TorchCodec 0.14: HDR Video Decoding for CPU and CUDA, and Fast Wav Decoder