Home

CanIRun.ai is a machine learning-powered platform that analyzes running form and provides personalized feedback to help runners improve their technique and prevent injuries. The platform uses computer vision and AI algorithms to analyze videos of runners and offer insights on their stride, cadence, and other biomechanical factors.

The article discusses the death of 'bucket squatting,' a technique used by cybercriminals to compromise cloud storage accounts. It explains how recent changes in cloud storage policies have made this practice less effective, reducing the risk of unauthorized access to sensitive data stored in cloud buckets.

The article discusses Senator Ron Wyden's concerns about the NSA's activities under Section 702 of the Foreign Intelligence Surveillance Act, which allows the government to conduct surveillance on non-US citizens abroad. Wyden warns that the public will be 'stunned' by the NSA's actions in this area, which he believes violate privacy rights.

Qatar's helium production shutdown has put the global chip supply chain on a two-week clock, as the country is a major supplier of this critical component for semiconductor manufacturing. This disruption could exacerbate the ongoing chip shortage and impact various industries that rely on semiconductors.

The full source code of Sweden's e-government platform was leaked from a compromised CGI Sverige infrastructure, potentially exposing sensitive government data and infrastructure details.

This article discusses Nanoclaw, a tool that creates Docker-based sandboxes for running untrusted code in a secure environment. It highlights Nanoclaw's ability to isolate and monitor the execution of code, making it useful for tasks like security testing, code reviews, and educational purposes.

The article discusses an issue with the pandas library in Python where the merge function is not properly handling datetime data. Developers are working to address the problem and provide a solution.

The article examines the phenomenon of meta-lobbying, where organizations influence policy decisions not through direct lobbying, but by shaping the broader public discourse and agenda. It also discusses other related findings on the dynamics of political influence and transparency in policymaking.

Prompt-Caching.AI is a platform that allows users to create and cache AI-generated responses, enabling faster and more efficient interactions. The article discusses the platform's features, such as its ability to handle large language models and its potential applications in various industries.

https://web.archive.org/web/20260311145044/https://www.newsc..., https://archive.ph/ZKkD3

Hi HN, we’re Lewis and Edgar, building Captain to simplify unstructured data search (https://runcaptain.com). Captain automates the building and maintenance of file-based RAG pipelines. It indexes cloud storage like S3 and GCS, plus SaaS sources like Google Drive. There’s a quick walkthrough at https://youtu.be/EIQkwAsIPmc.

We also put up this demo site called “Ask PG’s Essays” which lets you ask/search the corpus of pg’s essays, to get a feel for how it works: https://pg.runcaptain.com. The RAG part of this took Captain about 3 minutes to set up.

Here are some sample prompts to get a feel for the experience:

“When do we do things that don't scale? When should we be more cautious?” https://pg.runcaptain.com/?q=When%20do%20we%20do%20things%20...

“Give me some advice, I'm fundraising” https://pg.runcaptain.com/?q=Give%20me%20some%20advice%2C%20...

“What are the biggest advantages of Lisp” https://pg.runcaptain.com/?q=what%20are%20the%20biggest%20ad...

A good production RAG pipeline takes substantial effort to build, especially for file workloads. You have to handle ETL or text extraction, chunking, embedding, storage, search, re-ranking, inference, and often compliance and observability – all while optimizing for latency and reliability. It’s a lot to manage. grep works well in some cases, but for agents, semantic search provides significantly higher performance. Cursor uses both and reports 6.5%–23.5% accuracy gains from vector search over grep (https://cursor.com/blog/semsearch).

We’ve spent the past four years scaling RAG pipelines for companies, and Edgar’s work at Purdue’s NLP lab directly informed our chunking techniques. In conversations with dozens of engineers, we repeatedly saw DIY pipelines produce inconsistent results, even after weeks of tuning. Many teams lacked clarity on which retrieval strategies best fit their data.

We realized that a system to provision storage and embeddings, handle indexing, and continuously update pipelines to reflect the latest search techniques could remove the need for every team to rebuild RAG themselves. That idea became Captain.

In practice, one API call indexes URLs, cloud storage buckets, directories, or individual files. Under the hood, we’re converting everything to Markdown. For this, we’ve had good results with Gemini 3 Pro for images, Reducto for complex documents, and Extend for basic OCR. For embedding models, ‘gemini-embedding-001’ performed reasonably well at first, but we later switched to the Contextualized Embeddings from ‘voyage-context-3’. It produced more relevant results than even the newer Voyage 4 models because its chunk embeddings are encoded with awareness of the surrounding document context. We then applied Voyage’s ‘rerank-2.5’ as second-stage re-ranking, reducing 50 initial chunks to a final top 15 (configurable in Captain’s API). Dense embeddings are just half the picture and full-text search with RRF complete our hybrid retrieval. In the Captain API, these techniques are exposed through a single /query endpoint. Access controls can be configured via metadata filters, and page number citations are returned automatically.

The stack is constantly changing but the Captain API creates a standard interface for this. You can try Captain, 1 month for free, and build your own pipelines at https://runcaptain.com. We’re looking for candid feedback, especially anything that can make it more useful, and look forward to your comments!

The article discusses the discovery of a well-preserved Neanderthal individual, nicknamed 'Shanidar Z,' found in the Shanidar Cave in Iraq. The remains provide new insights into Neanderthal facial features and social behavior, revealing a Neanderthal who may have been cared for by their community despite significant physical disabilities.

We built an open-source proxy that sits between coding agents (Claude Code, OpenClaw, etc.) and the LLM, compressing tool outputs before they enter the context window.

Demo: https://www.youtube.com/watch?v=-vFZ6MPrwjw#t=9s.

Motivation: Agents are terrible at managing context. A single file read or grep can dump thousands of tokens into the window, most of it noise. This isn't just expensive — it actively degrades quality. Long-context benchmarks consistently show steep accuracy drops as context grows (OpenAI's GPT-5.4 eval goes from 97.2% at 32k to 36.6% at 1M https://openai.com/index/introducing-gpt-5-4/).

Our solution uses small language models (SLMs): we look at model internals and train classifiers to detect which parts of the context carry the most signal. When a tool returns output, we compress it conditioned on the intent of the tool call—so if the agent called grep looking for error handling patterns, the SLM keeps the relevant matches and strips the rest.

If the model later needs something we removed, it calls expand() to fetch the original output. We also do background compaction at 85% window capacity and lazy-load tool descriptions so the model only sees tools relevant to the current step.

The proxy also gives you spending caps, a dashboard for tracking running and past sessions, and Slack pings when an agent is sitting there waiting on you.

Repo is here: https://github.com/Compresr-ai/Context-Gateway. You can try it with:

  curl -fsSL https://compresr.ai/api/install | sh

Several long-lost episodes of the classic British sci-fi series 'Doctor Who' have been recovered, including episodes featuring the iconic villain Daleks. The rediscovery of these episodes is a significant event for fans of the show and the preservation of television history.

The article explores the story behind the creation of the Accidental Room, a unique architectural feature in a building in San Francisco. It examines how an unintended space was transformed into a functional and valuable part of the structure, highlighting the unexpected ways buildings can evolve over time.

Hi HN - I'm Ryan a product designer who codes, and I built Mesa. Current IDEs feel wrong for the type of development being done now - the focus is still on files.

Mesa puts the focus on the full workflow: your agent, terminal, browser, and files all live as equal nodes on a canvas with full multiplayer support. (think figma but for code)

I was tired of the overhead of switching windows, tabs, and terminals across multiple projects. Inspired by TouchDesigner and Factorio, I wanted something more fluid and visual. Been using it as a total replacement for Cursor at work every day now. Being able to see multiple repos at once and control agents on each without navigating windows has freed up my headspace and increased productivity.

It's free to try — would love to know what you think!

Vite Plus, a new development tool, is announced as an alpha release. It aims to provide a faster and more efficient development experience by leveraging Vite's build system and offering a range of additional features and improvements.

This article explores the growing influence of 'dark money' in US politics, focusing on the case of Kat Abughazaleh, a social media influencer who has been accused of using undisclosed political donations to sway public opinion. It examines the lack of transparency around political financing and the challenges of regulating political speech on social media platforms.

The article discusses the five layers of progression from writing code to building companies, highlighting the importance of understanding business fundamentals, developing leadership skills, and cultivating a vision beyond just technical implementation.

The article discusses a ruling by the European Court of Justice that requires EU member states to legally recognize a person's desired gender, even if their national laws prohibit such changes. The court concluded that EU law takes precedence over national laws in this matter.