Recent
AI Log 2: Adding an AI PR Reviewer to My Agent Harness
·1381 words·7 mins
I just added a new piece to my agent harness: an AI that reviews every PR before I do.
Not a SaaS product. Not a GitHub App. Just OpenCode wired into my self-hosted GitHub Actions runner, authenticating through my ChatGPT subscription.
Here’s what it does and the harder questions it exposed.
AI Log 1: Claude vs GPT — A Head-to-Head Agent Delegation Experiment
·2713 words·13 mins
I pitted Claude Opus 4.7 via Bedrock API against GPT 5.5 — not as chatbots, but as agentic supervisors. Each was given the same task: write a delegation prompt for a coding agent, dispatch it, review the result, and iterate to correctness. Same codebase. Same delegate model. Same constraints. Only the parent agent changed.
RT Log 8: 5 Vibe Coding techniques
·1194 words·6 mins
This article talks about several techniques I used when I code. It is not meant for direct adoption by readers because we might be writing different types of code. I was focusing mostly on Data Engineering and Software engineering (backend) code. If you were a data scientist, take this with a pinch of salt.
DE Log 9: Extend duckdb beyond the single player mode, by just a little bit
·2705 words·13 mins
Yet another take on poor man’s lakehouse / or how to NOT contribute to Databricks’ IPO success even though it seems inevitable.
RT Log 7: 关于Chatgpt和学习
·48 words·1 min
最近用chatgpt越来越频繁，感触良多。这里简单聊一下最近的一些感想，尤其是在自我学习上的一些辅助作用，如果能给予读者一些启示那再好不过了。
DET Log 1: A first “byte” of Airbyte
·2044 words·10 mins
In this article, I am sharing my first impression on the open-sourced almighty data ingestion tool - Airbyte.
RT Log 6: Career summary v3
·138 words·1 min
刚在看冬奥女子花滑决赛，特鲁索娃太过分了这么多四周跳，不过妹子长大了之后感觉没有原来轻盈了。结果看到有人在询问第三份总结的事情，想了想自从上次跳槽过了快半年了，也差不多是时候写一下新的总结。
DE Log 8: Thoughts on Data Engineering Specialisations
·1653 words·8 mins
Happy New Year everyone! And I am too lazy to change the thumbnail image.