Hacker News: joshmarlow

New comment by joshmarlow in "GPT‑Live"

joshmarlow — Wed, 08 Jul 2026 18:10:41 +0000

That makes sense and had never occurred to me!

I just asked and Claude says it's Haiku.

New comment by joshmarlow in "GPT‑Live"

joshmarlow — Wed, 08 Jul 2026 17:34:28 +0000

Absolutely the same. Now that Fable is back, the Claude voice interface is... worth dealing with. The app mostly seems to have trouble recovering from networking issues which is jarring in a deep conversation.

New comment by joshmarlow in "GPT‑Live"

joshmarlow — Wed, 08 Jul 2026 17:26:37 +0000

I'm so mad that this might make me re-subscribe to ChatGPT. I wouldn't have believed how much I use the voice feature before LLMs and ChatGPT currently has the best voice interface. I think Grok's interface is the next best, then Claude.

New comment by joshmarlow in "The truth about being a manager"

joshmarlow — Tue, 23 Jun 2026 18:51:22 +0000

One of the more counter-intuitive parts of management that I've found is that your focus shifts from delivering a technical outcome to care-taking a team that delivers technical outcomes. It's a meta-function.

A related physics metaphor - in general as you move from IC to SR to management, your focus shifts from changing the position to changing the velocity and acceleration of those around you.

New comment by joshmarlow in "Stop Using JWTs"

joshmarlow — Tue, 16 Jun 2026 20:05:43 +0000

It definitely violates DRY but if you keep passing the JWT down the call chain, you can do redundant permission checking in your business layer.

Now the reasonable response to the above is that this should be happening in a dedicated authn/z concern - and that is correct! But when paranoia is called for, it's not unreasonable to have redundant checks in logic where authz is critical.

New comment by joshmarlow in "Starfish by Peter Watts (1999)"

joshmarlow — Thu, 11 Jun 2026 13:34:50 +0000

His Blindsight is one of my all time favorite novels (sequel is good to). His short story Malak - about a military drone given a prototype ethical program - is so good.

New comment by joshmarlow in "I'm Eric Ries, author of "The Lean Startup" and new book "Incorruptible" – AMA"

joshmarlow — Wed, 10 Jun 2026 17:18:07 +0000

This feels like this is exploring the reasons for what Doctorow calls "Enshitification" which is really exciting.

New comment by joshmarlow in "DeepSeek 4 Flash local inference engine for Metal"

joshmarlow — Thu, 07 May 2026 18:58:31 +0000

Another suggestion for optimizing local inference - the Hermes team talks a lot on X about how much better results are when you use custom parsers tuned to the nuances of each model. Some models might like to use a trailing `,` in JSON output, some don't - so if your parser can handle the quirks of the specific model, then you get higher-performing functionality.

New comment by joshmarlow in "Hear your agent suffer through your code"

joshmarlow — Fri, 24 Apr 2026 15:21:37 +0000

I propose a claude skill to email glitter bombs where appropriate.

New comment by joshmarlow in "Slop is not necessarily the future"

joshmarlow — Tue, 31 Mar 2026 18:40:43 +0000

> Treat code design and architecture as the thing that lets your slop canons (90% of engineers even pre-ai) move fast without breaking things

I'm currently of the opinion that humans should be laser focused on the data model. If you've got the right data model, the code is simpler. If you've got the relevant logical objects and events in the database with the right expressivity, you have a lot of optionality for pivoting as the architecture evolves.

It's about that solid foundation - and of course lots of tests on the other side.

New comment by joshmarlow in "A proposal to classify happiness as a psychiatric disorder (1992)"

joshmarlow — Tue, 17 Mar 2026 18:57:15 +0000

That's very interesting and is good evidence against the thesis - thanks for sharing!

New comment by joshmarlow in "A proposal to classify happiness as a psychiatric disorder (1992)"

joshmarlow — Tue, 17 Mar 2026 15:23:25 +0000

Very true - which is why this piece "that translations of others words into 'happy' are somewhat approximate." would be very interesting if accurate.

New comment by joshmarlow in "A proposal to classify happiness as a psychiatric disorder (1992)"

joshmarlow — Tue, 17 Mar 2026 15:22:35 +0000

I've not read Aristotle directly but translating eudaimonia was an example in the book that I mentioned. The argument was that eudaimonia is often translated as happiness but that doesn't make sense in contexts where we talk about a soldier dying experiencing eudaimonia (suggesting a loose translation).

New comment by joshmarlow in "A proposal to classify happiness as a psychiatric disorder (1992)"

joshmarlow — Tue, 17 Mar 2026 14:28:28 +0000

A few years ago I read a claim that the word 'happy' is relatively young - ~500 years old - and that translations of others words into 'happy' are somewhat approximate.

My takeaway is that (presuming the argument is correct) that much of human striving is probably better described with specific words (as you suggested - joy, accomplishment, fulfillment, excitement, etc). For most of human history, most people probably didn't think "I want to be happy" but "I want to have a good partner", "I want a big family", "I want my crop to grow so I don't die."

I wonder how much unhappiness is caused by seeking a poorly-defined ideal of happiness.

The book was called "Power, Pleasure, and Profit: Insatiable Appetites from Machiavelli to Madison".

New comment by joshmarlow in "Show HN: Badge that shows how well your codebase fits in an LLM's context window"

joshmarlow — Fri, 27 Feb 2026 17:57:04 +0000

On a related note, this type of reasoning is what made me flip my opinion on microservices. I've generally been skeptical of a many-microservice architecture for the last decade but LLMs change that - a small microservice is more likely to fit in a context window.

I think this gestures at a more general point - we're still focusing on how to integrate LLMs into existing dev tooling paradigms. We squeeze LLMs into IDEs for human dev ergonomics but we should start thinking about LLM dev ergonomics - what idioms and design patterns make software development easiest for AIs?

New comment by joshmarlow in "Warcraft III Peon Voice Notifications for Claude Code"

joshmarlow — Thu, 12 Feb 2026 16:59:44 +0000

Now I want my main agent to be modeled after the Adjutant and any subagents to sound like SCVs.

New comment by joshmarlow in "Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out"

joshmarlow — Fri, 30 Jan 2026 17:18:31 +0000

CoinBase sure does - https://www.x402.org/

New comment by joshmarlow in "Git Rebase for the Terrified"

joshmarlow — Wed, 14 Jan 2026 17:42:20 +0000

Adding to your comment, I've found that frequent squashing of commits on the feature branch makes rebasing considerably easier - you only have to deal with conflicts on one commit.

And of course, making it easier to rebase makes it more likely I will do it frequently.

New comment by joshmarlow in "GPT-5.2"

joshmarlow — Thu, 11 Dec 2025 20:25:55 +0000

I think Grok's voice chat is almost there - only things missing for me: * it's slower to start-up by a couple of seconds * it's harder to switch between voice and text and back again in the same chat (though ChatGPT isn't perfect at this either)

And of course Grok's unhinged persona is... something else.

New comment by joshmarlow in "We Need to Die"

joshmarlow — Wed, 10 Dec 2025 15:58:30 +0000

Agreed! In the Lex Fridman podcast from a few years ago that I referenced, he talked quite a bit about his depression - he was near suicidal for 13 years, IIRC.

He sounds like a different person now.