Ha ha I feel like I could have been a little kinder :)
Thank *you* for all the thoughtful writing!!!
15.02.2026 17:40
👍 0
🔁 0
💬 0
📌 0
Ha ha I feel like I could have been a little kinder :)
Thank *you* for all the thoughtful writing!!!
💯. That's the main takeaway from DORA's research on this stuff so far, as I understand it.
>As we’re entering the phase of single-use plastic software, we might be moving the whole layer of responsibility elsewhere.
"single-use plastic software" is a really a striking way of framing it. It feels very accurate, and I'm not sure how I feel about it.
Who'd I miss?
I also posted this list on LinkedIn to, and got some nice additions from folks: www.linkedin.com/posts/beinga...
@birgitta410.bsky.social
ThoughtWorks Distinguished Engineer, focused on AI-assisted Engineering
Dexter Horthy: x.com/dexhorthy
Coined the term Context Engineering, was into Ralph before it was cool
🧵...
@mitsuhiko.at lucumr.pocoo.org/tags/ai/
Grizzled veteran engineer, using AI a lot but very pragmatic about it
@addyosmani.bsky.social addyosmani.com/blog/ai-codi...
He writes REALLY LONG posts, but they're full of great info
🧵...
@simonwillison.net
the OG LLM user, very plugged in to what's happening, prolific writer, never hyperbolic
Mitchell Hashimoto: mitchellh.com/writing/my-a...
Built Hashicorp (Vagrant, Terraform, etc), now building ghostty, and using AI a lot to do it.
🧵...
It's hard to find balanced opinions on AI coding. Lots of the people pushing the envelope on AI-Assisted Engineering also have somewhat bonkers AI-maximalist perspectives.
Here's some people who're in the thick of it, advancing the field but who I also trust to bring a thoughtful, balanced take
🧵
Unfortunately I'm not aware of a specific "tell" that gives that away. 😔
Also the transition from "my worth is defined by me spending lots of time coding" to "my worth is defined by me keeping my team on track".
Although, these little AI genies are way more lazy/sneaky/mischievous/inept than any ICs your typical newly-minted manager would have to deal with
Hot-ish take: devs should be spending time now learning out how to be *efficient* with the tokens in their agent's context windows
1) it makes the agent perform better
2) tokens are gonna start costing more over the next couple of years
These Ralph shenanigans might look real silly in retrospect
I would LOVE to learn more details about this internal product.
I'm consulting on AI adoption with some similar big enterprise cos with epically brown brownfield codebases ATM. Code understanding for agents is the big challenge.
Would you be able to intro me to this dev, if they're open to it?
I dunno about that - what coding agents are best at building doesn't necessarily impact what you use to build the coding agent itself.
Also, a VS Code extension is basically HTML, which LLMs are very happy with.
Also, the parrot generates pretty impressive visuals already (e.g. nano banana pro).
FYI it looks like the first link (to Cassidy's post) is bad - just took me to the same page I was on.
focus on whether it helps address the LLM’s fundamental limitations by asking:
does this new approach systematically improve how the agent manages context?
does this new approach systematically improve how the agent gets human feedback?
Read on and I’ll elaborate: blog.thepete.net/blog/2026/01...
an extremely cringe genAI image of a robot "programming". It's got a nice cup of coffee on it's desk for some reason.
You’re staring at a breathless social media post (probably with a really cringe AI-generated image of a robot “writing software”) or Slack share talking about the latest AI-coding flavor of the week. You’re wondering “is this actually worth me checking out?”
Here’s the heuristic I use...
🧵...
“Have you tried out Ralph Wiggum loop?!”
“Are you still using beads?”
“Is Gas Town actually legit?”
“Know anyone who’s into BMAD?”
These days I’m glad my family doesn’t know what my Serious Work Conversations sound like. It’s embarrassing.
Let’s talk about how to deal with all this noise.
🧵...
Claude Code is an amazing product. It does amazing things. I love it. Amazing.
It's also most typically used as a CLI tool.
This does not mean that Claude Code is an amazing product BECAUSE it's a CLI.
Tell me why I'm wrong!
CustardSeed is brand new! I’d absolutely love any and all feedback on:
- the concept
- how you'd like to use it
- what's missing - what would stop you using it today?
- the documentation
- the installation experience
- the UX of the session viewer
- the UX overall
Peer review of AI coding sessions brings a lot of the same value as good code review:
- share and learn good prompting practices
- providing feedback on peer's techniques
- understand how the code was built
My hope is that CustardSeed will help teams realize that value.
Devs should be regularly sharing coding agent sessions with colleagues.
I made a thing to make this super duper easy: custardseed.com
🧵...
Really nice measured, balanced and thoughtful writeup of a decidedly unbalanced and unhinged project 🙃
A screenshot of a repo's AGENTS.md, which starts with Guidelines for AI coding agents working in this Rust codebase. RULE NUMBER 1: NO FILE DELETION YOU ARE NEVER ALLOWED TO DELETE A FILE WITHOUT EXPRESS PERMISSION. Even a new file that you yourself created, such as a test code file. You have a horrible track record of deleting critically important files or otherwise throwing away tons of expensive work. As a result, you have permanently lost any and all rights to determine that a file or folder should be deleted. YOU MUST ALWAYS ASK AND RECEIVE CLEAR, WRITTEN PERMISSION BEFORE EVER DELETING A FILE OR FOLDER OF ANY KIND. Irreversible Git & Filesystem Actions — DO NOT EVER BREAK GLASS Absolutely forbidden commands: git reset --hard, git clean -fd, rm -rf, or any command that can delete or overwrite code/data must never be run unless the user explicitly provides the exact command and states, in the same message, that they understand and want the irreversible consequences. No guessing: If there is any uncertainty about what a command might delete or overwrite, stop immediately and ask the user for specific approval. "I think it's safe" is never acceptable. Safer alternatives first:......
who hurt you?
I would guess that it's closer to good old-fashioned plagiarism: someone gave the LLM your post and said "rewrite this in my voice" or something.
Seems way more likely than an LLM is regurgitating close-to-verbatim content from its training set.
Gonna start saying "Clod" when referring to Claude Code.
I've felt a need to use its full name to disambiguate between the Claude Code - the coding agent - vs Claude - the general purpose chat bot, but it's so tedious to type it out in full.
It's either CC or Clod, and Clod is more fun.
Looks amazing!
Number one "complaint" I keep hearing about gridfinity - once you start you really want to do All The Things, and the print times are bruuuuuttal. Someone should sell injection molded snap-fit grids.
sub-agents in particular are a big deal, because each agent uses it's own temporary context window, keeping the main context window clean.
Claude Code also uses this trick for it's built in tools (e.g. WebFetch)
lots more detail in the full post: blog.thepete.net/blog/2025/12...
each coding agent can bring:
- different system prompt
- different tools
- (hidden!) context management tricks to steer the model’s behavior
- task management tools to nudge the LLM into better planning
- sub-agents, which can have a *huge* impact on context management
🧵...
turns out that coding agents are much more than a “wrapper” around an LLM. They do a surprising amount of work under the surface to (a) maximize the useful information available to the LLM, and (b) steer its behavior.
🧵...
"Why is Claude Code better/worse than [other coding agent] - they’re both using the same models under the hood?"
A reasonable question, so I spent some time reverse-engineering Claude Code's interactions with the model to illustrate why coding agent matters
blog.thepete.net/blog/2025/12...
🧵...