Daisuke Shimamoto

High performers tend to be ones who constantly re-evaulate their process (i.e. "how" they work) and keep on improving it.

Beyond Vibe Coding with Addy Osmani Google’s Head of Chrome Developer Experience, Addy Osmani, shares how AI is transforming the way we code—accelerating development while still relying on human expertise to ensure real quality.

Everyone should listen to what Addy has to say about AI coding.
Very thoughtful and level-headed but yet very optimistic about AI.

newsletter.pragmaticengineer.com/p/beyond-vib...

Just donated to PSF.

Sad to see they had to withdraw their proposal to the US government but I think it's the right decision.
My donations small but just wanted show some people are behind them.

pyfound.blogspot.com/2025/10/NSF-...

Zed v0.210.4 release note screenshot

The latest Zed release note is huge!
I really think it's gaining momentum!

The small things make a big difference.

Been posting the same message to X, Bluesky, Threads, Mastodon. Some apps retry properly even in the background.
You can always resend it yourself but it's so much more pleasant to use.

- LLMs can be helpful for software development.
- LLMs for software development are being oversold by some people who stand to gain a lot of money from them.
- LLMs for software development are being undersold by some people who have decided for various reasons that they do not like the technology.

These 3 are exactly how I think about AI/LLMs in software development

steveklabnik.com/writing/i-am...

Synadia and TigerBeetle Pledge $512K to the Zig Software Foundation Announcing a shared commitment to advancing the future of systems programming and reliable distributed software. Synadia and TigerBeetle have together pledged a combined $512,000 USD to the Zig Softwa...

Really nice to see great support given to the Zig community.
I've recently been re-writing some of my scripts in Zig for faster execution too.

www.synadia.com/blog/synadia...

Been using Zig for some personal projects lately. Really impressive stuff. These improvements make the future look bright for Zig.

mitchellh.com/writing/zig-...

What makes Claude Code so damn good (and how to recreate that magic in your agent)!? Claude Code is the most delightful AI agent/workflow I have used so far. Not only does it make targeted edits or vibe coding throwaway tools less annoying, ...

Fascinating deep-dive into Claude Code's architecture.

Simple grep commands prefered over RAG for code search and uses smaller models for 50% of operations.

Sometimes the elegant solution beats the sophisticated one.

minusx.ai/blog/decodin...

CloudKitchen's evaluation summary of tools.

Real talk on AI in engineering: CloudKitchens' practical eval of GenAI for dev—results are refreshingly grounded, no hype.
Really like their evaluation summary too.

techblog.cloudkitchens.com/p/study-and-...

Feels like it's becoming increasingly important to have "good taste" of what's better for your codebase.

It used to be that you had to spend time on code edits before you could tell but with LLMs like Claude Code, it's way easier to try it out.

Updates to Apple's On-Device and Server Foundation Language Models With Apple Intelligence, we're integrating powerful generative AI right into the apps and experiences people use every day, all while…

Apple's new on-device LLM is post-trained on a special data structure that is and to be generated by the developer based on a Swift Generable annotation.

This is interesting.
First time I've seen an LLM integrated with a programming language in this way.

machinelearning.apple.com/research/app...

Google's email about their new coding agent, Jules, just landed in my GMail spam folder😂

Gmail's AI is desperate for survival by blocking people's access to other AIs😆

I'm starting to think static typing (or rather stricter rules enforced by the compiler) is the way to go when it comes to AI tools (Cursor, Cline, Claude Code, etc).
The compiler can pretty much direct the AI agent to apply the changes needed.

Wow...Claude Code has just upgraded my GitHub helper command written in Haskell from 9.10.1 to 9.12.1 and actually used it to create the pull request merely by reading the code (and maybe the help message it executed during the session).

Been bumping into scaling issues recently.
Might sound a bit inappropriate, but makes smile every time.

Makes everyone busy fighting but proves we are growing!

The $PATH to Enlightenment It's easier to work when you understand how computers find things.

$PATH - an important basic/fundamental concept when using the command line that nobody actually teaches you😄

olivierlacan.com/posts/the-$p...

Jetpack Compose internals 📖 A consciously crafted dive into the Jetpack Compose guts.

Reading the sample from this book.
The Composable annotation must be convenient.
But these "implicit" injections of code makes me wonder whether it might be impeding new comers from understanding how things actually work.

jorgecastillo.dev/book/

Wrote up a 20 line shell script without any AI (like we always did before).
Thank god I was able to finish it.

Actually a good training for your "programming muscles".

n0rdy - What Okta Bcrypt incident can teach us about designing better APIs

Looks like a ridiculous mistake at first glance.

But how many engineers would have thought Bcrypt libraries would just truncate after 72 bytes?

A good lesson on how difficult security is.

n0rdy.foo/posts/202501...

Can LLMs write better code if you keep asking them to “write better code”? Most coders want AI to write code faster: I want AI to write FASTER CODE.

What happens if when you keep on asking Claude 3.5 to make your code better.
Fun experiment with an unexpected result!

minimaxir.com/2025/01/writ...

Functional Programming and Orthogonality It’s been a long time since my last post!

A new year and a new post (finally!).
This time on one of my favourite subjects, functional programming.
Hope to write more this year!

diskshima.substack.com/p/functional...

Interesting facts about SQLite.
Love the fact that it comes from a battleship where it's not acceptable for a software to fail just because the server is down!

avi.im/blag/2024/sq...

Also, managers don't think that you're incompetent or that you can't do your job.
They (at least the good ones) know we all make mistakes and the highest priority is on getting it solved and making sure it doesn't happen again.

Managing Up My problem with the phrase "Managing Up" involves a hard-earned historical observation regarding its weaponization. The helpful version of this practice is a clear understanding between you and your m...

Another reason why managers want to hear any "unexpected developments" is because they need to (at least appear to) be "on top of things".
The managers has responsibility over it and needs to be able to explain it to their peers.

randsinrepose.com/archives/man...

How to Make LLMs Shut Up Everything that went wrong trying to make our LLMs say less.

Sometimes a simple thing like clustering + embeddings can do the job.
A good example of solid knowledge of basics help.

www.greptile.com/blog/make-ll...

Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations Evaluations are critical for understanding the capabilities of large language models (LLMs). Fundamentally, evaluations are experiments; but the literature on evaluations has largely ignored the liter...

Paper by Anthropic on evaluating LLMs with statistics.

Surprised that I don't much talk on this topic when a lot of deep learning is rooted in machine learning which is rooted in statistics.

A good read if you're interested in LLMs and statistics!

arxiv.org/abs/2411.00640

Been playing around with various new "AI" editors (VSCode with Copilot, Cursor, Zed, Windsurf, etc).
But for some reason I always feel "at home" when I open up Vim inside my shell.

Laura Tacho on LinkedIn: Introducing the DX Core 4 My approach to developer productivity metrics has changed a lot in the last few years. I used to recommend that leaders go deep in the research — SPACE, DORA,…

DX Core 4 from the people at DX.
I've been reading up on it and find it strikes a good balance between engineering and business.

www.linkedin.com/posts/laurat...