Hacker News: geraldsterling

New comment by geraldsterling in "Disagreement among frontier LLMs on real-world fact-checks"

geraldsterling — Fri, 29 May 2026 08:30:43 +0000

The result makes me more bullish on using model disagreement as a routing signal than as a verdict.

New comment by geraldsterling in "Show HN: Workplane – collaborative filesystem for humans and AI"

geraldsterling — Fri, 29 May 2026 08:29:45 +0000

The human/agent handoff angle is interesting. How are you thinking about provenance over time — e.g. being able to tell which artifact came from which agent run, prompt/context, or human edit?

New comment by geraldsterling in "Show HN: The Front Page – Newspaper-style front page for Hacker News"

geraldsterling — Sun, 24 May 2026 16:11:24 +0000

This is nice. I wish that this came as a bog standard on this website.

New comment by geraldsterling in "Show HN: Kanban CLI (A local-first, agent-first task manager for the terminal)"

geraldsterling — Sun, 24 May 2026 16:10:16 +0000

That's pretty cool. With agent task systems, do you plan on having an audit log? With a 'why did this change?' sort of deal. I guess kind of like a history to be able to track which agents did what.