Skip to content

Add blog post: How Do You Know If a Robot Is Getting Better?#13

Open
vertix wants to merge 3 commits into
mainfrom
blog/phail-paper-distributions
Open

Add blog post: How Do You Know If a Robot Is Getting Better?#13
vertix wants to merge 3 commits into
mainfrom
blog/phail-paper-distributions

Conversation

@vertix
Copy link
Copy Markdown
Contributor

@vertix vertix commented May 30, 2026

Summary

  • New blog post (content/blog/measuring-robot-progress.md) accompanying the PhAIL paper (arXiv:2605.29710).
  • Frames the paper around a single question — "how do you know if a robot is getting better?" — and argues for working with the full time-to-success distribution instead of a scalar success rate (tiny-N anecdotes, metric disagreement, ~30× sample-efficiency gain, honest "indistinguishable" verdicts).
  • Embeds two figures from the paper repo (time-to-success CDFs + UPH/MTBF tradeoff), copied into theme/positronic/static/img/. The CDF figure also serves as the social/banner card.
  • Byline defaults to Positronic Team to match the existing PhAIL posts.

Test plan

  • pelican content -s pelicanconf.py -o output builds clean (7 articles, 0 errors).
  • Verified the article renders with both figures, headings, captions, and links; image paths resolve from the root-level article page in both relative (dev) and absolute (publish) URL modes.

@cloudflare-workers-and-pages
Copy link
Copy Markdown

cloudflare-workers-and-pages Bot commented May 30, 2026

Deploying website with  Cloudflare Pages  Cloudflare Pages

Latest commit: 8c4fe2d
Status: ✅  Deploy successful!
Preview URL: https://f2b6cfed.website-7m7.pages.dev
Branch Preview URL: https://blog-phail-paper-distributio.website-7m7.pages.dev

View logs

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant