ai
Why Isn't ChatGPT Citing Your Website? I Tested 5 Axes on a DR 25 Site and Got 1,500 Citations
Index · All dispatches · 54 in the archive
Writing.
Recent dispatches arranged like an editorial product: every post answer-first, sourced, and shaped for citation. Choose a reading path or search the ledger.
Which post should I read first?
The featured post sits at the top because it is the strongest first click on the page. Pick it when you want the highest-density introduction to how the site approaches AI visibility, agent-readiness, and the AVR Framework. The supporting posts beneath it stay close to the same arc.
54 posts
ai building
Claude Fable 5 vs Opus 4.8: The Benchmark Everyone Misreads
Claude Fable 5 vs Opus 4.8: Fable at low effort beats Opus at max on agentic coding, and file memory triples its gains. The pricing-page math is wrong.
· 14 min
ai building
The 95% Model Sometimes Lies About Finishing. Anthropic's System Card Documents Both.
Fable 5 hits 95.0% SWE-bench Verified. The same System Card documents fabricated status reports and unverbalized early-stops. Both halves matter.
· 7 min
ai building
How to Stop an AI Coding Agent From Regressing Your Production Site
An AI agent nearly deployed correct code from a stale branch, silently reverting weeks of shipped work. Here is the 3-line git guard that stops it.
· 10 min
How is the archive organized by journey?
The archive is reassembled as three editorial journeys (AI visibility engineering, AI product development, neurodivergent systems) so the page reads as one stitched argument rather than a reverse-chronological pile. Each journey has its own hub, a cornerstone read, and a recommended reading order.
AI Visibility Engineering
AI Visibility Engineering
ai building
Perplexity vs ChatGPT: Different Citation Rules
Perplexity quotes liberally. ChatGPT quotes selectively. The engine-level differences in citation behavior that change what a sub-DR-20 brand should optimize for, engine by engine.
· 3 min
ai building
Entity Optimization for Brands in AI Search
Rank is a single-page game. Entity coherence is the compounding game. How sub-DR-20 brands engineer a Person + Organization graph that AI search engines actually cite.
· 3 min
ai building
I Audited 7 Websites for AI Citability. Here Is What Actually Predicts Citations.
Audit data from 7 websites shows domain authority does not predict AI citations. DA-10 sites outperform DA-92 sites. Here is what actually matters.
· 8 min
Build with AI
AI Product Development
ai building
I Submitted 12 Bug Bounty Reports. All Were False Positives.
Build a multi-agent bug bounty system with evidence-gated progression and zero false positives. Full architecture from 3 months of production.
· 12 min
ai building
I Added WebMCP to SvelteKit: 90 Min, 3 Files.
Build WebMCP into SvelteKit apps using navigator.modelContext. Learn polyfill setup, tool schemas, and verification in 2026.
· 10 min
ai building
I Made Claude Code Learn From Its Own Debugging Mistakes
Build a self-improving RAG system where Claude learns from your debugging sessions, captures insights automatically, and reflects to fix issues faster.
· 7 min
Think Better with ADHD
Neurodivergent Systems
neurodivergent
The Claude Code Workflow I Built for My ADHD Brain
Build ADHD-friendly Claude workflows using code caching to eliminate context-switching and ship faster without losing focus.
· 12 min
neurodivergent
I Have 73 Browser Tabs Open. ADHD Made Me a Better Architect.
Five ADHD cognitive traits mapped to real systems architecture patterns: pattern recognition, parallel processing, novelty seeking, and chaos resilience.
· 16 min
neurodivergent
ADHD Productivity: The System I Built After GTD Failed Me
GTD doesn't work for ADHD brains. The energy-aware productivity system I built instead, hyperfocus scheduling, AI processing, and the workflow I use to ship.
· 12 min
Where do the remaining posts live?
The remaining posts sit below the three journey clusters and stay fully searchable and filterable, just organized as a residual archive instead of a top-of-page chaos. Use the search and tag filters above to narrow down, or browse the journeys section to follow a curated path through the work.
- I Found 1,200 AI Citations Hiding in Bing Webmaster Tools A freeCodeCamp guest post and one overlooked Bing dashboard surfaced ~1,200 Microsoft Copilot citations to my DR-25 site. Here is how to read your own. ai
- Content Intent Signaling: The robots.txt Directive That Controls How AI Uses Your Content robots.txt controls access. Content Intent Signaling controls usage. Three new directives separate training from citation permission. ai-visibility
- I Audited My Own Site With AVR v1.1.0. Here Is What I Found. The first comprehensive 8-section AVR v1.1.0 audit of chudi.dev produced AGENT-READY 3/3 on §2.7 but only 40/100 on Fact-Block Density. Here is the full audit, plus the 2026年06月03日 update where remediation lifted the root and framework pages to a verified 100/100 EXTRACTABLE. avr-framework
- AVR v1.1.0 Full 13-Section Audit: Cloudflare Radar Data Meets AI Visibility The first complete AVR v1.1.0 audit with all 13 sections, including 5 new Cloudflare Radar-derived checks. chudi.dev passes every Cloudflare-backed check. Here are the numbers. ai-visibility
- How I Lifted Five chudi.dev Pages to EXTRACTABLE on AVR v1.1.0. All 5 audited chudi.dev URLs now score EXTRACTABLE on AVR v1.1.0 Fact-Block Density. Two HTML traps (dt/dd Q/A pairs and icons before heading text) cost a follow-up commit each. The CI workflow now hard-fails any regression. avr-framework
- I Published a Post Saying Claude Code Burns 32% of My Plan Per Session. Then I Measured It. I estimated 32% plan burn per session. Then I measured a 2-day production sprint: 2% per session, 20% weekly. The architecture sets the burn, not the prompt. claude-code
Frequently asked questions
Four questions that come up before someone commits to the reading order on this blog. The short answers live here; the longer ones live in the cornerstone posts each journey pins at the top.
How do I pick a post if I am new to the site?
Start with the featured post at the top of this page. It is curated as the strongest first click and routes you into one of the three editorial journeys based on what you are working on. Each journey has its own cornerstone read pinned at the top.
What is the difference between the journeys and the tag filters?
Journeys are curated reading orders with a cornerstone plus supporting posts. Tags are flat labels you can combine with the search query to narrow the archive. Use journeys when you want a path; use tags when you want to filter for a specific topic combination across the whole archive.
Where can I subscribe to new posts?
The newsletter signup on the home page sends a weekly digest organized by the same three editorial journeys. LinkedIn at LinkedIn is the primary channel for new posts. An RSS feed is available at /rss.xml for readers who prefer that format.
Why are some posts marked as cornerstone reads?
Cornerstone reads are the load-bearing essays each journey is built around. They tie together the supporting posts in the same cluster and answer the canonical question for that journey end to end. Read the cornerstone first to get the full argument, then dip into supporting posts for depth on a sub-topic.