xcrashlytics is a macOS command-line tool that connects Firebase Crashlytics and local Xcode Organizer reports to your terminal and AI coding agents, giving immediate access to crash messages, app stacks, impact metrics, and hot files without manually copying data from the console. It’s designed so an agent can be granted crash context (search issues by feature, error, or version; read crash messages and app frames; get exact event and user counts) and then carry out investigations or export findings. Installation is simple (curl installer, Homebrew, direct download, or build from source), it reuses Firebase CLI authentication, and an AGENTS.md file shows how to embed setup instructions into an agent’s workflow.
The tool provides concrete commands and structured output for reproducible workflows: issues, show, events, breakdown (by version/os/device), blame (rank files/symbols), groups, export (Markdown), and open (jump to Xcode). It supports iOS/macOS/.crash and .ips reports, dSYM-based symbolication with atos (warns when dSYMs can’t be verified), and JSON/ndjson outputs with schemaVersion/data/warnings for scripts and agents. Privacy rules strip raw user IDs from exports and network traffic goes only to Google. xcrashlytics retrieves and formats crash evidence for triage and reporting but does not attempt to diagnose or fix code.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Four coding agents were given a $100 budget to build a functional PDF editor, but their implementations had noticeable bugs and shortcomings. The experiment highlights that current AI agents struggle with goal pursuit and user interaction, leading to subpar software quality. (blog.nielstron.de)
Lithos-ai open-sourced lithos-metal, enabling Qwen3.8-27B to run at over 200 tokens per second on an Apple M5 Max laptop. This allows ultra-fast inference for coding agents with a single command. (twitter.com)
Google Cloud introduces the Gemini agent, a universal AI tool that handles questions, content creation, coding, and knowledge work within familiar applications like Gmail and Docs. It features industry-specific skills, security, cost controls, and integrates seamlessly into existing workflows. (cloud.google.com)
Temporal developed pi-temporal to enable the Pi coding agent to recover from machine failures during tasks by leveraging a fleet of workers and durable execution. This setup allows seamless task continuation across machine failures without repeating interrupted commands. (temporal.io)
![OpenAI cannot make AI safe on its own [pdf]](https://hntoday.pixelshot.io/screenshots/20261008/0217d5d1410143c5_tn.jpeg)
OpenAI has acknowledged that it cannot ensure the safety of artificial intelligence systems on its own. The document discusses the challenges and limitations faced by OpenAI in making AI safe without external collaboration or oversight. (mikitabalesni.com)
Yoshua Bengio urges AI researchers at frontier companies to prioritize safety and consider leaving if safety measures are insufficient. He warns that current development races risk pushing humanity toward catastrophic outcomes and calls for slowing AI progress to prevent loss of control. (transformernews.ai)
Today's best Hacker News stories, summarized and screenshotted, one email a day.