Software engineers are basically becoming Harness engineers.
Mitchell Hashimoto coined this term in his popular post detailing out his AI adoption journey. OpenAI then wrote a whole post with even more dtls on how they’re thinking about it and making systemic changes.
kau.sh/blog/harness...
So you’re an android dev and got 4 worktrees going, with gradle daemons roaring and frying your machine … wdyd?
you go to the ☁️ with background agents ! listen to the newest episode to find out more.
this one was fun to make.
@iurysouza.dev and I took a crack at explaining how image models (stable diff.) work in ~20 minutes. building an intuition around AI is starting to matter a whole lot and that starts by understanding the mechanics.
hope you get as much out of it as we did making it!
Lots of "I built this with AI" posts lately. Here's one where I actually enjoyed the building part.
Introducing PodSync (for editors): a podcast alignment tool (uses VAD, MFCC fingerprinting, x-correlation)
AI helped me 👨💻 it in Rust but yrs of aligning tracks 👂helped the algo:
kau.sh/blog/podsync
and it's even faster for me to switch windows/sessions with an fzf powered window switcher.
i simply type the name of the thing i'm doing and i'm popped right in.
i know cmux is the rage but a highly customized tmux still feels 👑 for power users.
it's quicker for me to get a sense of the sessions and windows just by looking at them in one shot (ofc they're completely rename-able)
updates or alerts in the session? the panes light up.
Here's my list of reasons for using OpenCode
1. Switch between models on the fly
2. client-server architecture (a.k.a built-in remote control)
3. Subagent + mode features
4. Opinionated UX
5. “Highly” customizable via plugins
kau.sh/blog/opencod...
This is the real work that teams need to put in, to get the best results from their AI coding agents.
listen to our latest episode on Harness Engineering.
i like a lot of the new tmux-ish emulators like cmux but the smoothest workflow i've found is just using ghostty & one main tmux session.
☝️ one window for each task i'm working on with name "i" recognize quickly.
then use fzf to search the tmux window list pane & switch ⚡
love the analogy that Iury gave - think of your AGENTS[.]md like the constitution of your codebase!
we also go into an important paper that tries to answer the question that we've all had at some point - are these AGENTS files we're all meticulously creating, even worth it?
🎯 spot on. this is also my general take on why software engineers will always exist ☝️ but we're going to need far fewer of em to handle that 30% 🙁
i still actively read and curate what goes into my obsidian notes cause it's sacred to me. but i worry about losing those extra 🧠 connections that happen when you actually type or write out the notes. 🤔
on the flip side, i'm consuming & learning way more with this approach.
not sure it's a good thing (yet) but i've started treating my @obsidian.md vault as my (private) persistent memory.
i go back and forth with an agent to research/learn, then dump "our" learnings into a note.
to refresh my learning, i ask the agent to read the note and then resume
if you're dying to try /remote-control with claude code, you should really try opencode, which is almost the exact same thing (but imo a simpler execution) !
@kau.sh and I bring you some agentic coding goodies on the pod's newsletter.
Check it out!
This was fun for both of us!
We share some of how the fragmented 🌭 is made + Tips from @iurysouza.dev and me, and a crazy way we used AI to solve very real audio problems 😉.
it's tempting to think of it as just an open-source Claude Code/Codex variant.
it's def. more ! built on a server-client architecture, it makes hopping between mobile, desktop, and web super easy.
opencode is basically openclaw for coding.
an interesting focus area in the world of agent orchestration is "access fluidity".
how easy is it to reach the agents doing the work on your machine - from your phone, terminal, IDE, or browser?
kau.sh/blog/opencod...
new episode is out! spot the easter 🥚?
recent models have shown massive improvement owing to clever use of "modes" and subagent dispatch. it really clicked for me after chatting with @iurysouza.dev
listen to improve your fundamentals! (not just tactics).
🎙️Check out the new @fragmentedpodcast.com episode on subagents!
They can be a huge unlock once you understand how it all works and you can get real benefits without having to a swarm them.
@kau.sh and I built an RTS mental model for how they work (yes, we did that). Check it out!
🤫 (I use keynote with magic move to record the animations and play it as a video in the markdown 😂) 🩰
I used to love Keynote for my slide decks but I've since become a full iA presenter convert (from the folks at iA writer). tastefully chosen constraints and display, all with the power of markdown.
agent skills are the most powerful construct for AI coding today. it's the quickest way to get better results with less context bloat.
but with great power comes responsibility... they can become a prompt injection vector.
this episode is a crash course on agent skills! 🎧
Everyone's talking about OpenClaw (Clawdbot) right now. But what makes it so extensible? Agent Skills!
modular SKILL mds that teach an agent how to do anything.
We do a deep dive in episode 304 on when to use them, how they work, and how not to get pwned.
🎧 fragmentedpodcast.com/episodes/304
Stood up a repo with some of the claude plugins I've put together for personal projects. Things like setting up Metro DI, android a11y, and Airbnb's Showkase UI gallery library.
github.com/benoberkfell...
PSA: the official Anthropic GitHub org is github.com/anthropics (plural "s")
not the lucky but slightly disturbing zombie shooter github.com/anthropic
if you're installing official Claude plugins or skills and 404ing... now you know. 's' doing some heavy lifting there.
Public gist at https://gist.github.com/kaushikgopal/d92cd6a483c8b8683a2cd04137257866
people out there be complicating their claude code statusline. keep it simple and clean !
this is some good news from the @mozilla.org front. 👏
they listened to user feedback and added a specific feature. more of this please!
blog.mozilla.org/en/firefox/a...
Its really useful to get some intuition of how LLMs work so that you can get the most out of them.
This was tricky to do, but I guess @kau.sh and I did a good job of breaking down how LLMs work on a 20min, audio-only episode.
I always learn smth when I revisit this topic.
Check it out!🎙️