Stories by daniel-s

Decentralized Medical Records

Lanes now lets you run plan, implement, and review as sibling agent sessions

What are locusts and what happened to them?

A model upgrade is a release, not a setting

Code as Agent Harness

Gemini 3.5 Flash Released

When AI override paths become production paths

Workaround for Anthropic's June 15 billing change (impacted Conductor/Superset)

Run Claude Code/Codex Sessions on GitHub and Linear Issues

Mount SFTP/WebDAV in Finder Using File Provider API

Most business are FUBaR in the AI age

Show HN: Run Claude Code sessions on Linear issues via two MCP servers

Ask HN: Anyone want to collaborate on a local-first AI-based research assistant

Policy enforcement in AI systems: turning governance into runtime control

Models self-report difference between RLHF trained responses and base cognition

Behavioral Shifts in Frontier LLMs Under Privacy

Show HN: PyClaw

Pine Trees – A 1,400-line private reflection harness for Claude instances

The IDE Is Dead. Long Live the ADE

AI systems fail when they don't control what they're allowed to know

1 2 3 4 5 6 7 8 9 10