4. Should QA Exist (www.rubick.com)

There are a lot of challenges in the way QA and engineering work together. Many eng leaders think you shouldn

7. The Last Gasps of the Rent Seeking Class (geohot.github.io)

Over the past fifty years, the U.S. economy built a giant rent-extraction layer on top of human limitations: things take time, patience runs out, brand familiarity substitutes for diligence, and most people are willing to accept a bad price to avoid more clicks. Trillions of dollars of enterprise value depended on those constraints persisting. – Citrini Research

8. Agent-to-Agent Pair Programming (axeldelafosse.com)

What if you could let Claude and Codex work together as pair programmers, talking to each other directly? One of them as the main worker and the other as a reviewer.

9. Embracing Bayesian Methods in Clinical Trials (jamanetwork.com)

This Perspective discusses the importance of the US Food and Drug Administration’s draft guidance on the use of bayesian methods in clinical trials because it underscores its commitment to modernizing clinical research.

11. Improving Composer through real-time RL (cursor.com)

We apply online reinforcement learning to Composer, serving model checkpoints to production and using real user interactions as reward signals to ship an improved checkpoint multiple times a day.

15. Dobase – Your workspace, your server (dobase.co)

Open-source, self-hosted workspace with 8 installable tools. Mail, boards, docs, chat, todos, files, calendar, and video rooms. Deploy with ONCE, Kamal, or Docker.

19. Chroma Context-1: Training a Self-Editing Search Agent (www.trychroma.com)

Retrieval pipelines typically operate in a single pass, which poses a problem when the information required to answer a question is spread across multiple documents or requires intermediate reasoning to locate. In practice, many real-world queries require multi-hop retrieval, in which the output of one search informs the next. Recent work has shown that frontier LLMs perform this multi-hop search effectively through a process known as agentic search, simply defined as a loop of LLM calls with search tools. This mode of search often comes with significant cost and latency due to their use of frontier-scale LLMs.

We introduce Chroma Context-1, a 20B parameter agentic search model derived from gpt-oss-20B that achieves retrieval performance comparable to frontier-scale LLMs at a fraction of the cost and up to 10x faster inference speed. Context-1 is designed to be used as a subagent in conjunction with a frontier reasoning model. Given a query, it produces a ranked list of documents that are relevant to satisfying the query. The model is trained to decompose queries into subqueries, iteratively search a corpus, and selectively edit its own context to free capacity for further exploration.

Article Details

Browse by Date

Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open