Add acknowledgement for Barney Dellar

app/priv/blog/engineering/2026/04-29-my-local-agentic-dev-setup-today.md

@@ -264,10 +264,10 @@ This is an excerpt. Notice that the contextWindow for 27B does not match the set
 Further reading
 ---
 
-- [Coding agent generates its' own extensions](04-19-coding-agent-generates-its-own-extensions.md) — Engineer solutions in the moment for the agent you're in a session with.
-   - [A pair pomodoro with Pi](04-20-a-pair-pomodoro-with-pi.md) — A brief experiment in working in short cycles with a coding agent.
-   - [How to get started with the Pi coding agent (on a VPS)](04-24-how-to-get-started-with-the-pi-coding-agent-on-a-vps.md) — Setting up Pi on a VPS is easier than I thought.
-   - [Smaller open LLMs now work for open agents](04-24-smaller-open-llms-now-work-for-open-agents.md) — A phase shift in quality and speed of open weight models and inference.
+ - [Coding agent generates its' own extensions](/blog/engineering/coding-agent-generates-its-own-extensions) — Engineer solutions in the moment for the agent you're in a session with.
+ - [A pair pomodoro with Pi](/blog/engineering/a-pair-pomodoro-with-pi) — A brief experiment in working in short cycles with a coding agent.
+ - [How to get started with the Pi coding agent (on a VPS)](/blog/engineering/how-to-get-started-with-the-pi-coding-agent-on-a-vps) — Setting up Pi on a VPS is easier than I thought.
+ - [Smaller open LLMs now work for open agents](/blog/engineering/smaller-open-llms-now-work-for-open-agents) — A phase shift in quality and speed of open weight models and inference.
 
 - Nate B Jones had a good podcast / video this week on Apples' play with local models for e.g. legal offices who can not get their work certified if their data leaves the office, no matter how encrypted it is. [Nate B Jones on Apple and the next trillion dollars](https://podcasts.apple.com/gb/podcast/ai-news-strategy-daily-with-nate-b-jones/id1877109372?i=1000763732500)0
 
@@ -283,3 +283,8 @@ What was remarkable to me in the Field Report above is that the writer chose Ope
 > Why don't I just use [..] Claude Code? I had problems due to a lack of optimization for small context windows. Long-running tasks that complete large projects independently matter for me, so no Claude Code. 
 
 So maybe my intuition is right. I am not doing long running tasks like I was doing with Cladue Code _yet_ with Pi and Qwen. This shows it is possible, and might even be better. Detailed prompts and deterministic harnesses make the difference between frontier models and harnesses smaller. More about that maybe later. I hope this helps you, let me know if you have any questions or remarks. 
+
+Acknowledgements
+----
+
+Thanks to [Barney Dellar](https://www.linkedin.com/in/barney-dellar-88487b83/) for reporting that the links to my blog in Further Reading were broken. That was the only part I used AI for in this post...