Hacker News: joshgachnang

New comment by joshgachnang in "Pion, an agent designed to run any company autonomously"

joshgachnang — Mon, 14 Sep 2026 20:09:23 +0000

How are you automating all the parts? OpenClaw/Hermes?

New comment by joshgachnang in "GLP-1s are being linked to fewer serious infections, including TB"

joshgachnang — Thu, 03 Sep 2026 23:22:38 +0000

As low as $69/month through the compounding pharmacies.

New comment by joshgachnang in "Maybe We Shouldn't Be Reviewing All This Code"

joshgachnang — Wed, 02 Sep 2026 23:36:45 +0000

I didn't read this as "pair program every line".

I write a bunch of features. Most are pretty boring. A junior isn't going to learn much by pairing. But occasionally, I do big architecture changes. Those ones are perfect for early collaborative design, pairing, and discussion. The whole team benefits from understanding the architecture better and juniors get to see how seniors think about it. Then you can pair with juniors on the prompting or, more likely, the implementation plan to hand to the agents. That's maybe once a week.

New comment by joshgachnang in "Launch HN: RonanRX (YC S26) – Personalized Peptides and GLP-1s"

joshgachnang — Wed, 02 Sep 2026 22:59:13 +0000

Hey, I love the idea and the fully integrated approach! The feedback loop sounds great, and overall far better than the pretty generic companies I've dealt with for GLP before.

I've led building an EHR totally from scratch at one company and currently advising another as they build their EHR, both totally integrated approaches in industries where you usually have lots of disconnected care (adolescent serious mental illness and ABA/autism care). The state-by-state regulatory challenges are very real! If you want to chat, my email is in my profile!

New comment by joshgachnang in "Tim Curry has died"

joshgachnang — Thu, 27 Aug 2026 00:06:23 +0000

And James Earl Jones!

New comment by joshgachnang in "I like 'em thick: an apology to my English teachers"

joshgachnang — Thu, 20 Aug 2026 18:33:58 +0000

The best class I had in high school was American Dream: a mixture of literature and history/social studies. You'd learn about a time and then read a book for that time, like Grapes of Wrath or The Jungle or All Quiet on the Western Front. It was a double period, had two dynamic teachers (one old hippie and one young fun guy), and most of the grades were from papers about how the book and history related. More schools should have something like that.

New comment by joshgachnang in "Ask HN: What tools are you using for human code review of AI-assisted code?"

joshgachnang — Tue, 18 Aug 2026 22:34:00 +0000

BugBot in Cursor has been great, I rarely find myself looking at it and disagreeing, especially with medium/high impact. I also have a custom architecture reviewer that just runs Claude, that's been great for finding duplicate code, boundary breaking, etc. We still have Github Copilot reviewing because it will (very occasionally) catch something BugBot missed, but the false positive rate is wayyyy higher, to the point I've considered disabling it a few times.

New comment by joshgachnang in "Buyer cancels showing after Deflock shows two cameras utilized by the HOA"

joshgachnang — Mon, 17 Aug 2026 13:02:37 +0000

This assumes the police are always upstanding and never have ulterior motives. Which has proven not to be true. [0] and tons of others

[0] https://www.kcra.com/article/new-bedford-police-officer-on-l...

New comment by joshgachnang in "I turned my RSS feeds into an e-ink newspaper to stop reading on my phone"

joshgachnang — Fri, 14 Aug 2026 17:30:07 +0000

I've been working on the same thing for my ReMarkable, but I get it uploaded as a newspaper doc every morning since you can't install apps on it. Overall it's been working reasonably well!

New comment by joshgachnang in "OpenChamber: An Agentic Development Environment"

joshgachnang — Sun, 09 Aug 2026 18:05:37 +0000

This looks pretty awesome, like almost exactly what I've been hoping for. Is it possible to run the sessions on a remote server to keep tasks running? I mostly work from my laptop and it's nice to fire off tasks to a remote server (mostly been Cursor Cloud Agents lately) and close my laptop, maybe check in from the app later.

New comment by joshgachnang in "Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident"

joshgachnang — Wed, 29 Jul 2026 20:33:12 +0000

They escaped using the package proxy cache. I'm not seeing how a VM would have prevented that.

New comment by joshgachnang in "Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident"

joshgachnang — Wed, 29 Jul 2026 18:51:34 +0000

How would a VM have stopped any of this?

New comment by joshgachnang in "Zig Creator Calls Spade a Spade, Anthropic Blows Smoke"

joshgachnang — Mon, 13 Jul 2026 15:39:11 +0000

I've run into a bunch of segfaults in Bun whenever I went slightly off the beaten path, probably from the "horrifying" Zig code. A huge test suite + a clean rewrite with a path towards more safety is how I would go about it too, personally. Now whether I would do that rewrite in Zig or Rust, I'm not sure. But I have high hopes it's going to work a lot better, especially since Anthropic uses Bun heavily.

Are LLMs better at writing Rust than Zig? I'd assume so, there's way more Rust open source code than Zig. And if so, that's a very solid reason to switch IMO.

New comment by joshgachnang in "Weightlifting beats running for blood sugar control, researchers find (2025)"

joshgachnang — Sat, 11 Jul 2026 23:29:56 +0000

I used Stelo from Dexcom with my Oura Ring, no prescription. I didn't really learn much, other than occasionally realizing I was cranky because of low blood sugar.

New comment by joshgachnang in "U.S. allows Anthropic to release Mythos AI to ‘trusted’ US organizations"

joshgachnang — Sat, 27 Jun 2026 00:14:57 +0000

And yet the rest of the party falls in behind him.

New comment by joshgachnang in "SpaceX to buy Cursor for $60B"

joshgachnang — Tue, 16 Jun 2026 17:24:18 +0000

Just setup my team with Cursor. They actually got back to me on an enterprise plan (Claude keeps ignoring me). Cloud Agents have been great for keeping multiple streams going at the same time. Adding in computer use has been great for actually testing out features and showing they work for PRs. Bugbot so far has been the best AI reviewer I've tested. Composer 2.5 is great, though still using Opus for planning.

I can do most of this with Claude Code, but there's definitely a cost in maintaining it for the whole team.

New comment by joshgachnang in "Waymo Premier"

joshgachnang — Thu, 11 Jun 2026 17:34:09 +0000

Car payment, insurance, parking, gas/electricity? Going to be over $400/mo in almost all cases in any of the cities Waymo is in.

New comment by joshgachnang in "My Agent Skill for Test-Driven Development"

joshgachnang — Fri, 05 Jun 2026 21:02:06 +0000

This overall is pretty close to how I've set up my implementation skill. One thing I'm curious about is how well the analogies like "We don't make dinner in a dirty kitchen." work vs something a lot more straightforward. Any input OP?

New comment by joshgachnang in "Show HN: Boxes.dev: ditch localhost; run Claude Code and Codex in the cloud"

joshgachnang — Thu, 04 Jun 2026 16:27:33 +0000

Nice, this looks exactly like what I've been looking for. I tried Fly.io Sprites and it _almost_ got me there, but I got annoyed logging into my CC every new feature. Unfortunately I wound up going all in on Cursor Cloud Agents, which overall has been decent.

New comment by joshgachnang in "Launch HN: Superset (YC P26) – IDE for the agents era"

joshgachnang — Fri, 22 May 2026 19:10:49 +0000

Amazing, this is exactly what I've been looking for a while now, especially the remote dev box part. I'll give it a try, thank you!