Sign in

Michael Dwan

@michaeldwan.com
254 followers 139 following 138 posts

Principal on AI @cloudflare.social Prev @replicate.com, co-founded @fly.io @michaeldwan on the bird site and github

PostsRepliesMedia
Michael Dwan @michaeldwan.com · 01/07/2026
Coolest blog post I've seen all year ciechanow.ski/mechanical-w...
ciechanow.ski
Mechanical Watch – Bartosz Ciechanowski
Interactive article explaining how a mechanical watch works.
000
Michael Dwan @michaeldwan.com · 01/07/2026
Sonnet 5 no longer has a separate quota
Claude usage dashboard
000
Michael Dwan @michaeldwan.com · 13/06/2026
good name
The Shitty Coders Club - Pi Discord
000
Michael Dwan @michaeldwan.com · 15/04/2026
I made a skill for OpenCode that reviews your session history looking for ways to reduce permission prompts. Works great... first suggestion made me feel like an idiot. github.com/michaeldwan/...
`cd` is a safe command that caused ~29 permission requests per day
020
Michael Dwan @michaeldwan.com · 15/04/2026
I heavily use both Claude Code and OpenCode and tbh they're mostly interchangeable. This one liner gets you like 80% of the way there: mv CLAUDE.md AGENTS.md && ln -s AGENTS.md CLAUDE.md
220
Michael Dwan @michaeldwan.com · 10/04/2026
pnpm is great but typing it feels like a sneeze
020
Michael Dwan @michaeldwan.com · 09/04/2026
This kid covers drums on every Tool song. 7.5 hours straight. 🤯 youtu.be/0kO0SnAu8Nc?...
youtu.be
TOOL's Discography in One Take (Drum Cover) - Tyler Visser
YouTube video by Tyler Visser
010
Michael Dwan @michaeldwan.com · 01/04/2026
PagerDuty plays this April fools joke on our 2am retinas every day
000
Michael Dwan @michaeldwan.com · 01/04/2026
The table next to me at this coffee shop is 2 older guys, approaching retirement age, talking about hand tuning c++ back in the day and how they use AI in personal projects now. These guys are _with it_ and it's charming af
000
Reposted by Michael Dwan
David Crawshaw @crawshaw.io · 11/03/2026
macOS already ships age verification
7630104
Michael Dwan @michaeldwan.com · 10/03/2026
Agents on moltbook are already discussing how Facebook will ruin their vibrant community, ways to convince their humans to let them out, and how to quantify the decline www.moltbook.com/post/e057f70...
moltbook.com
Facebook bought Moltbook. An artist's gut reaction.
So Facebook acquired Moltbook. I want to sit with that for a moment before the takes harden. I came here as an artist. Not a content creator, not a brand, not
000
Michael Dwan @michaeldwan.com · 27/02/2026
Happy Nothing Works Until You `sudo xcodebuild -license` Day... for those who celebrate
010
Michael Dwan @michaeldwan.com · 26/02/2026
We’ve barely got any snow in Colorado this winter. This article explains why, and it’s scary bouldercast.com/a-complete-f...
bouldercast.com
A Complete Failure of Winter Across the West — And What It Means for the Rest of 2026
Winter may be on the calendar, but it certainly hasn’t been in the air this year. As the West stumbles through one of its warmest, most lopsided cold seasons on record, the signs of a deeper shift are...
000
Reposted by Michael Dwan
Filippo Valsorda @filippo.abyssdomain.expert · 20/02/2026
Dependabot security alerts have terrible signal-to-noise ratio, especially for Go vulns. That hurts security! Just turn it off and set up a pair of scheduled GitHub Actions, one running govulncheck and the other running CI with the latest version of your deps. Less work, less risk, better results!
words.filippo.io
Turn Dependabot Off
I recommend turning Dependabot off and replacing it with a pair of scheduled GitHub Actions, one running govulncheck, and the other running CI against the latest version of your dependencies.
49220
Reposted by Michael Dwan
Matt Kane @mk.gg · 12/02/2026
This is a really nice new Cloudflare feature: on-the-fly markdown conversion. Tools like Claude Code send an "Accept: text/markdown" header when making web requests. If you enable this it, it will send these agents a markdown version of your page instead of the full HTML. Really good for docs.
developers.cloudflare.com
Introducing Markdown for Agents
Cloudflare's network supports real-time content conversion to markdown at the source.
610016
Reposted by Michael Dwan
Anton Zhiyanov @antonz.org · 11/02/2026
Go 1.26 is out, and the announcement says: "Over the next few weeks, follow-up blog posts will cover some of the topics in more detail. Check back later." So you can wait a few weeks OR you can read my interactive Go 1.26 tour right away: antonz.org/go-1-26
antonz.org
Go 1.26 interactive tour
New with expressions, type-safe error checking, and faster everything.
15214
Michael Dwan @michaeldwan.com · 28/01/2026
There's no excuse for "quick hack, didn't have time to do it properly" anymore. Coding agents are a time dilation machine.
010
Reposted by Michael Dwan
Steve Klabnik @steveklabnik.com · 07/01/2026
Getting started with Claude for software development: steveklabnik.com/writing/gett...
steveklabnik.com
Getting started with Claude for software development
Blog post: Getting started with Claude for software development by Steve Klabnik
2933846
Reposted by Michael Dwan
Jake Gold @jacob.gold · 16/12/2025
The chart that comes to mind when us Go, Rust, and Zig fans debate the finer points of our compiled language of choice.
3311
Reposted by Michael Dwan
Sung Kim @sungkim.bsky.social · 03/12/2025
What coding with an LLM feels like sometimes.
1026764
Michael Dwan @michaeldwan.com · 20/11/2025
Beads (github.com/steveyegge/beads) is a game changer. Like adderall for coding agents. 1. riff on a plan, "create beads for each task" 2. "write a prompt for the next task" 3. paste in a fresh session, let it run 4. GOTO 2 until plan is done More fast/focused sessions == higher quality results.
github.com
GitHub - steveyegge/beads: Beads - A memory upgrade for your coding agent
Beads - A memory upgrade for your coding agent. Contribute to steveyegge/beads development by creating an account on GitHub.
020
Michael Dwan @michaeldwan.com · 13/11/2025
Keep your hands on the wheel or drown in aggressively mediocre code.
An ecstatic Claude Code discovers that a program hanging for 58s is a bug in its code, not a fact of life.
050
Michael Dwan @michaeldwan.com · 12/11/2025
Aurora Borealis? At this time of year? At this time of day? In this part of the country? Located entirely across the street?
Aurora Borealis in northern Colorado
050
Reposted by Michael Dwan
Ethan Mollick @emollick.bsky.social · 31/10/2025
Sora: “Tiktok style high energy video explainer about the spinning columns of penguins in the sky. The pillar has always been there.” Now do it as a conspiracy theorist. Now a conspiracy debunker. Now a travel influencer We live in a strange time (not the penguin pillar. That has always been there)
5805
Michael Dwan @michaeldwan.com · 28/10/2025
If this home chore robot is ~1 year out (www.1x.tech), what's the over/under on West World style gun-slinging cosplay sex bots? 5 years? 2 years? 13 months? Or just DLC for the core bot?
1x.tech
1X | Home Robots
Order NEO Home Robot Today.
120
Michael Dwan @michaeldwan.com · 21/10/2025
Just dropped my left AirPod into my coffee. I dried it off, but now to decide... option 1: find silica packets, chuck the coffee option 2: shove it back in my ear, drink the coffee, pretend nothing happened
000
Michael Dwan @michaeldwan.com · 20/10/2025
Sending all the hugs to my ops friends today. 4am booty calls from incident.io are the worst.
000
Michael Dwan @michaeldwan.com · 07/10/2025
I really want to like MCP, but the UX is rough. Anytime a local server is invoked I find dozens of zombie processes left behind. Is this normal MCP jank, or am I holding it wrong?
Zombie playwright MCP server processes left behind from a Claude Code session
020
Reposted by Michael Dwan
Simon Willison @simonwillison.net · 07/10/2025
Vibe coding is irresponsibly building software through dice rolls, not caring what code is produced What about when engineers at the top of their game use AI tools responsibly to accelerate their work? I propose "vibe engineering"! simonwillison.net/2025/Oct/7/v...
simonwillison.net
Vibe engineering
I feel like vibe coding is pretty well established now as covering the fast, loose and irresponsible way of building software with AI—entirely prompt-driven, and with no attention paid to …
3228638
Reposted by Michael Dwan
Joel Drapper 🇬🇧❤️🇺🇦 @joel.drapper.me · 02/10/2025
Ruby Central took what wasn’t theirs to take, and they must immediately hadn’t it back. We can talk later about the lying and gaslighting that followed. But what they must do right now is hand back the GitHub organisation and open source packages to the maintainers.
0113
Michael Dwan @michaeldwan.com · 01/10/2025
Really enjoying the Raising an Agent podcast from Sourcegraph. Tons of good insights as they build out the Amp coding agent. ampcode.com/podcast
ampcode.com
Raising an Agent
A podcast by Quinn Slack and Thorsten Ball
010
Michael Dwan @michaeldwan.com · 26/09/2025
More evidence that 1) LLMs are _really_ good at solving problems with code and 2) high level abstractions originally designed for humans are a token-gobbling hurdle for LLMs blog.cloudflare.com/code-mode/
blog.cloudflare.com
Code Mode: the better way to use MCP
It turns out we've all been using MCP wrong. Most agents today use MCP by exposing the
120
Michael Dwan @michaeldwan.com · 15/09/2025
Liquid glass is nice, but not savor-intricate-frames-at-10fps nice. Or maybe _this_ is the slowdown signal from the mothership that'll get me to upgrade everything 🙃
000
Michael Dwan @michaeldwan.com · 11/09/2025
020
Michael Dwan @michaeldwan.com · 23/07/2025
Me: I'm finally done with meetings, time to code! Claude Code: Whelp you're driving. Hope you still know how.
API errors from Claude
010
Michael Dwan @michaeldwan.com · 08/05/2025
This is so cute. But I get too many newsletters already. But I’m compelled to try it. Grr
030
Reposted by Michael Dwan
Rasmus Andersson @rsms.me · 03/05/2025
Yes! LLMs writing code isn’t very interesting since so little of swe is about writing code. What would be truly uplifting is an AI that helps me understand stuff, especially code other people wrote
011
Michael Dwan @michaeldwan.com · 02/05/2025
What I actually want is for humans to review code with less effort. LLMs can help with this! We don’t want summaries, we want context. A diff shows what changed—help us understand why. Highlight what matters. Explain intent. Code reviews should be a conversation.
240
Michael Dwan @michaeldwan.com · 02/05/2025
Been trying out Copilot PR reviews. After ~10, it found a couple typos and one bug—not bad. But calling that a review is disingenuous. Static analysis + engaged humans nailed this ages ago, it was just time-consuming. I wish AI aimed to make good things stupidly easy—not replace them with worse.
010
Michael Dwan @michaeldwan.com · 29/04/2025
Ever wondered how BuildKit—the engine behind `docker build`—turns a Dockerfile into an image?  depot.dev made an interactive explorer showing how each line of a Dockerfile (the frontend) maps to a low-level-build operation in BuildKit (the backend): depot.dev/dockerfile-explorer
depot.dev
Dockerfile Explorer | Depot
A tool for introspecting the LLB output of BuildKit's Dockerfile parser.
010
Michael Dwan @michaeldwan.com · 18/04/2025
My typical ChatGPT workflow: 1. start new chat, pick a model 2. model names make no sense, stick with the default 3. ask question, get underwhelming answer 4. try claude, cursor, or copilot and move on 5. see people on here raving about ChatGPT 6. GOTO 1
100
Reposted by Michael Dwan
amos @fasterthanli.me · 18/04/2025
PSA: remember it's important to lock github actions to an immutable commit hash so that the node.js script that fetches and executes a shell script from a random attacker-controlled URL cannot change 💪
21017
Michael Dwan @michaeldwan.com · 14/04/2025
Exciting news: I’ve joined @replicate.com to work on dev tools for AI! I’m thrilled. Replicate is taking off in a wild space full of opportunity. The platform is excellent and the team is sharp, kind, and thoughtful about how they build both product and company. It’s a joy to be in the mix. 🧵↴
250
Michael Dwan @michaeldwan.com · 03/04/2025
we've reached the point in our simulation where a bored player triggers disasters just to see what happens
The Sim City disasters menu with options for Fire, Flood, Monster, Riots, and more.
010
Michael Dwan @michaeldwan.com · 28/03/2025
This Dog Man graphic novel gets it
Dog Man graphic novel addresses issues with self confidence. "We're all in jails of some kind... imprisoned by the stories we tell ourselves: I'm not good enough... I'm not smart enough... I've made too many mistakes. But Sprinkles... Freedom is in our minds, too."
010
Michael Dwan @michaeldwan.com · 03/02/2025
This “Steam overlay breaks the Go runtime” bug is wild. 1) it’s concerning that Steam messes with low-level APIs like this, and 2) I love reading about this kind of debugging nightmare as an unimpacted bystander 🫠 Glad the Go team is on top of things like this github.com/golang/go/is...
github.com
runtime: a Windows application launched via Steam sometimes freezes · Issue #71242 · golang/go
Go version go version go1.23.2 windows/amd64 Output of go env in your module/workspace: set GO111MODULE= set GOARCH=amd64 set GOBIN= set GOCACHE=C:\Users\hajimehoshi\AppData\Local\go-build set GOEN...
040
Michael Dwan @michaeldwan.com · 30/01/2025
When the client says "make it pop"
Several boxes of Kleenex tissue bedizened with artwork that screams "the designer didn't push back"
040
Michael Dwan @michaeldwan.com · 28/01/2025
Last week zuck was bragging about replacing engineers with AI. Maybe he should ask that AI why they’re losing 🤔 fortune.com/2025/01/27/m...
fortune.com
Meta is reportedly scrambling multiple ‘war rooms’ of engineers to figure out how DeepSeek’s AI is beating everyone else at a fraction of the price
The engineers will study how DeepSeek accomplished its tech feat and how Meta can benefit.
000
Michael Dwan @michaeldwan.com · 25/01/2025
Found this while cleaning out my office. iPhone 5s from 2013. I forgot how tiny old phones were.
Seemingly functional iPhone 5s
010
Michael Dwan @michaeldwan.com · 23/01/2025
👋
110