posts

I’ve been building my own harness since the Claude Opus 4.8 period. For a while the coding agent kept failing to follow the orchestration logic it had committed to. That made me ask whether I should stop trusting the agent to follow that logic and own it myself, in a layer around the agent. Each entry in this series is a log of something I built (or broke) in that harness, and a place to share my thought process. This is not a tutorial, because nothing is settled in this era and I don’t have much to teach. These are just a few observations that keep showing up behind my decisions.

Snowflake is retesting its 52-week high, still well below its 2021 all-time high. I am long, I called the earnings surge correctly, and I am now asking the question every winning trade forces: when do I leave?

I’ve been doing a lot of AI-assisted coding this year, and somewhere around the hundredth “just write this real quick” request that spiraled into a multi-session debugging odyssey, I realized I needed an actual workflow. Not a tool. Not a prompt. A process — one that works for me and for whatever agent happens to be in the driver’s seat.

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.

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.

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.

Yet another take on poor man’s lakehouse / or how to NOT contribute to Databricks’ IPO success even though it seems inevitable.

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。

In this article, I am sharing my first impression on the open-sourced almighty data ingestion tool - Airbyte.

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。