Jim Cowart

| Author of machina & postal | Powerfully dumb | Planning next moves...

[Jim Cowart @ifandelse]

Available for hire. 🤓

Not going to list ten buzzwords or claim I'm passionate about synergy.

I ❤️ building things & have a long history of shipping working software = building teams.

node/web/full stack. Remote or hybrid. DMs are open.

[Jim Cowart @ifandelse]

@dillon_mulroy Probably a whole lotta pair programming going on....

[Jim Cowart @ifandelse]

@timo_rf Dang it now I want a breakfast burrito and tots.

[Jim Cowart @ifandelse]

@davidad @dillon_mulroy This tweet. It’s not just a statement - it’s a work of art

[Jim Cowart @ifandelse]

@ItsGoneAwry Happy birthday to you!! (I’m a fellow May bday-er, too!)

[Jim Cowart @ifandelse]

@dillon_mulroy my eyes saw "hard systems are distributed" and I realized my own brain was trolling me in commiseration. 🤣

Freaking guaranteed order....

[Jim Cowart @ifandelse]

@DavidKPiano @opencode @jayair Man these vendor SDKs are really getting intense...

[Jim Cowart @ifandelse]

@DavidKPiano @aarondfrancis I make sure our eyes lock before I specify that by “cow’s milk”, I mean **whole milk**. In Chattanooga, you’re equally likely to either get a hug or get slapped. 😁

[Jim Cowart @ifandelse]

@dillon_mulroy Agreed. It’s amazing with FSMs! I feel like I’m barely scratching the surface! https://t.co/dNg5p2xZTB

[Jim Cowart @ifandelse]

There's Opus 4.6...and then there's Dopus 4.7

[Jim Cowart @ifandelse]

I'm 110% on board w/player coach. Only thing I'd say is that while I worked hard to maintain my street cred as an IC when I lead a large team, I also hate being the smartest person in the room, and so always sought to surround myself with people who were far better ICs than me.

[Jim Cowart @ifandelse]

@dexhorthy @hunvreus And lots of CLIs don't have idempotence in mind, which goes awry when agents stick to their probabilistic nature. CLIs are fantastic for agents when they account for this deterministically (and account for retry, etc.). I see more MCPs accounting for this IME

[Jim Cowart @ifandelse]

If you've been putting off trying Hermes - just do it.

I'm having more fun than I should be legally allowed to...

[Jim Cowart @ifandelse]

@dexhorthy @grok LOL I posted ☝️that before I saw the hilarious gif @hmemcpy posted 😂

[Jim Cowart @ifandelse]

@dexhorthy @grok can you take this image and place a Street Fighter character performing a Hadouken inside that "triangle of doom" 😀

[Jim Cowart @ifandelse]

@nlw It’s just the agents maximizing their blast radius with the belt and suspenders approach…

[Jim Cowart @ifandelse]

@dillon_mulroy @kitlangton

[Jim Cowart @ifandelse]

Hermes Agent folks - I'd love to hear what models you're using (for both main and aux tasks) 🤓

[Mitchell Hashimoto @mitchellh]

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they include personal friends I deeply respect, but I worry about how this plays out.

I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its... the whole software development industry (maybe the whole world, really).

It's frightening, because the psychosis folks operate under an almost absolute "MTTR is all you need" mentality: "its fine to ship bugs because the agents will fix them so quickly and at a scale humans can't do!" We learned in infrastructure that MTTR is great but you can't yeet resilient systems entirely.

The main issue is I don't even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like "no no, it has full test coverage" or "bug reports are going down" or something, which just don't paint the whole picture.

We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying.

I worry.

[Jim Cowart @ifandelse]

@cdrsalamander Imagine the podcasts *these guys* would’ve had….

[Nathaniel Whittemore @nlw]

There's no way we get out of 2026 without OpenAI making similar moves to Anthro today. You simply cannot have extremely limited compute + effectively unlimited demand and expect tokens to stay subsidized, no matter how valuable it is to have the affinity of the once subsidized.