Ian Harman

Christian. Husband. Father. Son. Chief Hooligan. Building something new @TPNHealth. Creating with AI @CraftingCopyAI. HCB. Atoms to bits and back again.

[Ian Harman @ijharman]

@gfodor This. Most excellent @gfodor. Can’t wait to see what you’re building.

[Ian Harman @ijharman]

@mattvanswol @BasedMikeLee You don't have to do it alone. There are amazing home school communities all over the country that can support you and your family. They don't advertise, you'll have to find the people by word of mouth, but they are there. Keep it up, it's absolutely worth it.

[Ian Harman @ijharman]

@clairevo Looks amazing! Can't wait to see it.

[Chris Tate @ctatedev]

Portless killed :3000

Dev servers got stable names like myapp.localhost

Agents could use worktrees in parallel without stepping on each other

Now it's easier than ever in v0.11

Just run: portless

Zero config. Zero args. Zero code changes.

[Ian Harman @ijharman]

@DokaKuri NinjaTrader for the win here @NinjaTrader

[Ian Harman @ijharman]

Happy Easter! He is risen!

[Simon Willison @simonw]

I wrote about the most ambitious form of AI-assisted software development I've seen yet - Strong DM's "Software Factory" approach, where two of the guiding principles are "Code must not be written by humans" and "Code must not be reviewed by humans" https://t.co/R0VYRwaZP5

[Paper Gains @PaperGainsInc]

Everyone’s focused on crash or rally.

Meanwhile, there’s a type of market that quietly ends trading careers. It’s not a crash.

But I see everyone posting and it looks like they’re about to walk right into it.

What I see coming over the next 3-6 months is not a crash. Not a rip higher. It’s both. Over and over. The kind of move that has you selling the lows and buying the highs until you’re done. Then, after you’ve lost your conviction, your capital, and your patience, the market makes its real move without you.

We’ve seen this movie before.

As a trader, sure, I’m watching tonight, after hours and tomorrow’s premarket. If we bottom in either session, selling might be done for now. We could get a vicious bounce. It’s tradeable.

But don’t mistake it for the bottom.

Friday green candles in a bear market are usually just short covering. Not conviction. And that’s the mistake I think a lot of people are about to make. They’ll see a bounce and think we’re going back to the highs. V-shaped recovery. All clear.

For investors, it can be even worse. Trying to catch falling knives. Pressing the gas right into a failed breakout because they mistook a counter-trend rally for new all-time highs incoming.

The real tell is $RSP.

That “broadening” narrative has been the market’s saving grace. But if $RSP doesn’t bounce AND tech doesn’t reclaim prior support, we’re still in trouble.

Even if we rally for another month, unless $QQQ is making new all-time highs, that rally is getting sold into. And now value is stretched too. Tech doesn’t rally + value pulls back = cycle breakdown.

Watch the tape. Not the headlines.

[Ian Harman @ijharman]

This is the way. What a time to build.

[Arvid Kahl @arvidkahl]

It turns out that writing code manually, rather than having it conjured from the void for you, has been holding back builders from building what they truly wanted.

Agentic coding being adopted by the most experienced product people should be more than enough signal for anyone.

[am.will @LLMJunky]

Bookmark Dillon's post.

Pretty similar to what I'm using to write plans, but far more concise.

Going to adopt some of this language into mine, particularly the testing lang, which I do cover, but I like his better.

[Ian Harman @ijharman]

@yacineMTB Thou mayest

[kache @yacineMTB]

THE COST OF INACTION THROUGH DELIBERATION IS ALWAYS FAR GREATER THAN THE COST OF MAKING A MISTAKE.

DO
THINGS

[Ian Harman @ijharman]

@lichthauch Timshel

[kache @yacineMTB]

Just start
Stop thinking
Literally do anything
Make an order for a PCB that is wrong
Make some magic smoke come out of an IC
Inaction through deliberation comes at a higher cost than the loss of making a mistake
Your goal should be to do something badly

[Arvid Kahl @arvidkahl]

It's still a bit shaky and bleeding-edge, but the "Ralph Wiggum" plugin in Claude Code is the first version of what's to come with autonomous, agentic loops.

It's a "we learn from failure"-centric approach. You define your goal condition and let the agent loop over and over until it has verifiably reached that promised goal.

It might take 2 minutes or a day. But the loop continues to experiment and look at prior work to ultimately get you there.

I've been seeing solid results with that. Takes some massaging and setting things up right (mostly for there not to be any interruptions), but when it works, it WORKS.

You can install this inside your CC by going to /plugin and typing `ralph`

[Boris Cherny @bcherny]

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.

My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.

So, here goes.

[Ian Harman @ijharman]

@karrisaarinen This eloquently captures what this new world is becoming. Thank you!

[Tennessee Football @Vol_Football]

program.Activate("darkMode");

[Ian Harman @ijharman]

Just ordered the @MinimalCompany phone. For the first time since 2009 there appears to be a phone that brings together the technology, capabilities and utility of the blackberry without the addictiveness of the iPhone. Curious to learn from this experiment.

[Tennessee Baseball @Vol_Baseball]

It was one heck of a ride, Coach.

Congratulations to Tony Vitello, making history as the first collegiate head coach to move directly to MLB manager.