New post: iterative self-improvement#34
Open
tedspare wants to merge 5 commits into
Open
Conversation
Visual-heavy experiment post building on the colocated-agent theme. Three demos of a long-running agent improving its own work: - UI: Claude Code de-slops a mobile landing page over 4 screenshot/critique passes - Perf: a React dashboard benchmarked in-browser, 13x mount / 90x filter speedup while unit tests stay green - Onboarding: computer-use walkthroughs that smooth a 5-step flow across 3 GIF iterations Includes the skill.md evolution from naive prompt to a polished copyable snippet. All screenshots, benchmark numbers, and GIFs are from real agent runs.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
New route /blog/iterative-self-improvement/demos with a 3-column layout per example so readers can verify the claims directly: - Landing: the three iteration HTML artifacts iframed side by side - Dashboard: three live, filterable 10k-row dashboards (naive / memoized / virtualized) over identical data, each reporting REAL measured mount + filter latency on a 'Run this version' button - Onboarding: three clickable, replayable multi-step flows (friction → smooth) Links from the post's closing. Built by three parallel agents porting their own demo artifacts into interactive React components.
Replace the single combined /demos page with three bare pages under a
[demo] dynamic route: /demos/{landing,dashboard,onboarding}. Each renders
only the 3-column card grid (no section copy/heading) via a new 'bare'
mode on DemoSection. Link to each from its own section in the post instead
of once in the conclusion.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Visual-heavy experiment post building on the colocated-agent theme. Three demos of a long-running agent improving its own work:
Includes the skill.md evolution from naive prompt to a polished copyable snippet. All screenshots, benchmark numbers, and GIFs are from real agent runs.