wakeupnuts @wakeupnuts

I wrote a bit about what Codemode actually is and how it works: lucumr.pocoo.org/2026/10/6/code…

本文是我在 2021 年在 PingCAP 担任开发者社群负责人时的感悟，包括如何参与社群，如何维护项目，以及“开心最重要”。 这几天连续讨论了开源的动机和可持续性相关的主题，让我觉得可以把这篇文章稍作修改后发在推特上分享。其中大部分观点经过五年的考验仍然有效，常看常新。 x.com/i/article/2103…

发现一个巨牛的书 The Hitchhiker’s Guide to Agentic AI，覆盖 Agentic AI 全貌 arxiv.org/abs/2606.24937

keyboard_arrow_left Previous keyboard_arrow_right Next

This is too boring to go viral but it will save you someday.

Ryan Carson @ryancarson

4 months ago

x.com/i/article/2064…

4 15 214 103K 686

Sorry if I post this again, but: this is the best post about AI slop you are going to read in the next 2 years.

Caleb Gross @noperator

4 months ago

x.com/i/article/2060…

16 91 799 300K 1K

如果你的 coding agent 在一个稍大些的项目上工作，强烈推荐安装 CodeGraph 使用 用它可以清晰看到代码的依赖关系和范围，是重构和维护的最佳工具。 效果远远优于 claude code 的 explore agent 我几乎用它取代了大部分的 explore ，提高了效率，也降低了成本 github.com/colbymchenry/c…

recommended reading!

R 'Nearest' Nabors (they/them) @rachelnabors

5 months ago

x.com/i/article/2057…

9 19 176 61K 428

Fork your dependencies, trim them to only your use case, never update unless it breaks for your users. I’ve been vocal about this for 10+ years. I’ve always said that updating is way riskier than latent bugs (which can be tracked and CVEs monitored). If you are updating a dependency, it’s on you to analyze every single commit in the full transitive set of dependencies. If you dont see anything compelling, dont update! I remember at HashiCorp once in awhile an engineer would try to update a dep or replace a DIY lib with an external one and id always ask “show me the commit we need.” Dont update for the sake of it. Feeling pretty swell about this mentality with all the supply chain attacks happening.

Due to popular demand, you can now browse all my recommended reading/viewing suggestions here: mariozechner.at/recommended-re… Sadly, Space Karen's hard core engineered Twitter API is absolutey garbage, and I can only get tweets back to April. Will backfile with an export. Enjoy.

I must say, I think I've found a way that works, but people are probably not ready to hear it... It's basically writing and understanding each part of the program you are trying to ship. I am basically writing the program myself, although not in code but literally writing out the outputs, traces & exact program execution I expect. Almost like TDD but not letting the agent invent the tests and also not testing for bullshit but real logical behaviour tests that test if the program does exactly what you want it to do. The earned benefit for me was, that I feel like I am actually engineering again and not like I am just doing some vague instructions. All of a sudden my average input tokens from my side are not 50 but 2000 tokens with real humanly written questions and impulses. And my deep understanding is back. I understand how my programs work again. Which in turns helps me to think more clearly. This is the uncomfortable truth that vibe coders are not going to like. That the reality is, that it takes days to really think through what you are building to the most granular details and actually understand it. Cool side effect is that this has never been in the training data. Deeply understanding architecture and the exact logic you are implementing to the smallest details does not exist much.

Mario Zechner @badlogicgames

5 months ago

imma go sell calendars with this kind of wisdom soon. seems like a more honest way to earn money these days in this industry anyways.

7 7 155 40K 73

jason from the codex team here, heres a draft on codex maxxing and the primatives i use on a daily basis jxnl.github.io/blog/writing/2… would love any feedback

While the industry is pouring resources into programs without GC (rust), I think the Jane Street OCaml folks have it figured out with OxCaml. Almost all your code paths are cold and GC is net positive. 1% of your code is performance sensitive. Don't create GC pressure there.

coming very soon to hunk® - post notes back to your agent

Ben Vinegar @bentlegen

5 months ago

hunk version 0.12.0 is live. Focus on "make sure everyone can use it": 🆕 can install via Homebrew 🆕 Nix support 🆕 works w/ lazygit 🆕 major scroll perf improvements 🆕 runs on Windows ⬇️

27 14 318 71K 124

Claude Code agent files have YAML frontmatter. Claude Code seems to have implemented it's own vibe coded YAML parser, and allows invalid YAML. Now people demand pi also parses YAML in the same broken way as Claude Code does. Glorious. github.com/earendil-works…

Repo here👇 github.com/Kappaemme-git/…

I can't help but feel personally burned by the Claude Code changes announced today. We put so much work into wrapping the (atrocious) Claude Agent SDK in T3 Code. It was the ONLY path they supported, so we made it work. It was hell. Now our users are getting their rate limits cut by 40x, despite us doing everything right. I listened to the Claude Code team. I had my issues with their direction, but I trusted them and took them at their word. I will never make that mistake again. Until we see significant change, it is safe to assume any statement from an Anthropic employee is a lie on a timer. The rug will be pulled, no matter how many promises are made beforehand.

Here’s the prompt: Create a single page html that documents workflows between packages and components in the app. Have all the components/packages on the page and I can click on different actions like "Invite new user" or "todesktop build" or {insert other flows here} and then it will highlight the flow between the packages and annotate how things are passed between each package to complete the action. This should be driven from a JSON document which documents all the flows. Does that make sense? Any questions?

@badlogicgames Love Pi! Freedom of crafting is so much better than swallowing ignorant features!

Hunk is very good. It has completely replaced any other local diff viewer for me. It looks good, its speedy, good keyboard shortcuts, good mouse support for fallback. Great software @bentlegen. github.com/modem-dev/hunk

x.com/i/article/2052…