Helsinki records zero traffic deaths for full year

helsinki-records-zero-traffic-deaths-for-full-year

More than half of Helsinki’s streets now have speed limits of 30 km/h. Fifty years ago, the majority were limited to 50 km/h. In a move to further reduce risk, the city lowered limits around schools to 30 km/h earlier this year. The new restrictions take effect at the start of the school term. Alongside […]

Launch HN: Lucidic (YC W25) – Debug, test, and evaluate AI agents in production

Hi HN, we’re Abhinav, Andy, and Jeremy, and we’re building Lucidic AI (https://dashboard.lucidic.ai), an AI agent interpretability tool to help observe/debug AI agents. Here is a demo: https://youtu.be/Zvoh1QUMhXQ. Getting started is easy with just one line of code. You just call lai.init() in your agent code and log into the dashboard. You can see traces […]

Words about Arrays and Tables

words-about-arrays-and-tables

July 30, 2025 THEY’RE JUST FUNCTIONS I’m way too discombobulated from getting next month’s release of Logic for Programmers ready, so I’m pulling a idea from the slush pile. Basically I wanted to come up with a mental model of arrays as a concept that explained APL-style multidimensional arrays and tables but also why there […]

LangExtract: Python library for extracting structured data from language models

langextract:-python-library-for-extracting-structured-data-from-language-models

Table of Contents Introduction LangExtract is a Python library that uses LLMs to extract structured information from unstructured text documents based on user-defined instructions. It processes materials such as clinical notes or reports, identifying and organizing key details while ensuring the extracted data corresponds to the source text. Why LangExtract? Precise Source Grounding: Maps every […]

Show HN: Sourcebot – Self-hosted Perplexity for your codebase

show-hn:-sourcebot-– self-hosted-perplexity-for-your-codebase

What’s Changed Added Ask Sourcebot – ask questions about your codebase in natural language. Get Markdown responses with inline citations. Bring your own LLM API key. hero_demo_v3_lowres.mp4 Read more here: https://docs.sourcebot.dev/docs/features/ask/overview Other changes [bug] onboarding: fix infinite loop when using GCP IAP by @drew-u410 in #381 Full Changelog: v4.5.3…v4.6.0

A short post on short trains

a-short-post-on-short-trains

The lesser urbanism hack Epistemic status: Main part is well-supported but may have some minor errors. The parts about potential future lines are inherently speculative. Small Train is Good Train A while ago, I wrote about how elevated trains are the greatest urbanism cheat code, increasing the amount of track miles you can build per […]

Weather Model based on ADS-B

weather-model-based-on-ads-b

I recently bought an RTL-SDR dongle and an antenna to receive ADS-B messages. These are short packets of data, broadcast by every plane in the sky, to inform others of their position, heading, speed and other flight data. The transmission of these messages is mandatory for aircraft, as it prevents mid-air accidents. They are also […]

Opsqueue: Lightweight batch processing queue for heavy loads – now open-source

opsqueue:-lightweight-batch-processing-queue-for-heavy-loads-–-now-open-source

We are happy to announce the open-source release of opsqueue, our opinionated queueing system! Why would you want to use it? Lightweight: small codebase, written in Rust, minimal dependencies Optimized for batch processing: we prioritize throughput over latency Built to scale to billions of operations Built with reliable building blocks: Rust, SQLite, Object Storage (such […]

Show HN: Open-source alternative to ChatGPT Agents for browsing

show-hn:-open-source-alternative-to-chatgpt-agents-for-browsing

Meka Agent is an open-source, autonomous computer-using agent that delivers state-of-the-art browsing capabilities. The agent works and acts in the same way humans do, by purely using vision as its eyes and acting within a full computer context. It is designed as a simple, extensible, and customizable framework, allowing flexibility in the choice of models, […]