HNHacker News
TopNewBestAskShowJobs

cautiouscat

833 karma · joined May 25, 2026

submissionscomments
cautiouscat··on Claude Code is leaking real email address as a User-Agent string in curl command
A FOSS harness wouldn't have your email in the first place.
cautiouscat··on Claude Code is leaking real email address as a User-Agent string in curl command
It's an awful report. Historically though I've encountered this, even to the point where it put my full name into something without me asking it to. It was documentation, and I caught it but I wouldn't have been happy about it.
cautiouscat··on Claude Code is leaking real email address as a User-Agent string in curl command
I've 100% seen it do this. I've even seen Claude say "because your account email is <email>, I've included it in the <whatever it was doing>". It should ask before divulging information like that, IMO.
cautiouscat··on How to organize Claude Code for product work
I’m tired of these AI written articles man. There could be information worth sharing here but having it all generated makes me assume you don’t care. So neither do I.
cautiouscat··on Defending my own brain against enshittification
I’ve been talking about this a lot on here. It’s because the product isn’t the audio file going into your ears. It’s the process that got it into that audio file. It’s knowing someone was passionate enough to put something together for others to hear. It’s knowing that someone out there in the world made this thing you’re getting beamed into your ears. It’s the soul of the thing that makes the difference.

Clinically, that doesn’t matter. However to a listener who is being intentional, it most definitely matters.

cautiouscat··on The Future Is for Everyone – The Path to a Positive AI Future
The first part kind of had me going “oh wow, this doesn’t seem like a thinly veiled advertisement for once”. You know, the common thing we see from frontier labs.

Then I got to the examples.

> my agent plans personalized recipes for us to make together each weekend, orders the ingredients, and then offers suggestions as we're baking.

I mean universe forbid you from using a recipe from one of the many talented bakers on YOUR platform. Or even better, asking a family member or family friend.

cautiouscat··on How I use LLMs to learn complex topics
I’ve written a skill that I basically feed what I’m looking to do, some ideas I had for accomplishing it and any other details like tech stack, etc.

The skill then riffs with me, judging my ideas and suggesting alternatives. We go back and forth until something useful comes out of it. This process isn’t unlike how I do normal development.

However, once agreed it breaks the work into “steps”. It then creates a tutorial for me, for those steps, explaining each line, why each change happens etc. I can then ask questions, muse about an alternative idea etc. Then I do the steps, and I’ve learned and gotten what I wanted to get done.

This has been how I’ve been learning Godot and making a game for the past month or so. I didn’t go in blind, I started with a course from GDQuest so I could feel confident guiding the tutorials. I will say though, having a tutor to bounce ideas off of has been really useful.

I still try to figure it out myself, consult the docs, discord etc. But if I’m stumped I’ll run my tutor skill and have some fun.

cautiouscat··on How I use LLMs to learn complex topics
I can only speak for myself, so I hope this resonates with you.

I wasn’t even really concerned with optimizing low level code before LLMs and that wasn’t why I was hired either.

However following that low level thread: We can look at the reasonable options and immediately know if they’re reasonable or nonsense. Why? We know the code. Now zoom a level out, where I think our expertise really lies.

Building a complex system isn’t easy. There are customers with requirements, there are budgets, SLAs etc. Sometimes one customer needs X and one needs Y. Our expertise is taking all of this in, and producing something that balances all the different variables. It’s knowing that we’ll expect X events a second so we’ll need Y to ensure we can tolerate failure.

Is it possible LLMs will be able to do all of that too? Maybe. But then why would our customers need the enterprises they pay for?

cautiouscat··on “Code was never the hard part” is an insult to all programmers
I see this comparison a lot, but I’m not sure I agree. At least not semantically. The list of what an engineer using agents is responsible for, largely hasn’t changed. Engineering managers haven’t changed responsibilities either.

Even with wrangling agents, you’re really just making them right the “correct code”. Something EMs don’t do, or at least the good ones don’t do with their ICs.

cautiouscat··on Writing with AI Is Stupid
I feel the same about AI with art. Even when it looks “as good”, it just doesn’t interest me. For example, intentionality of someone writing a specific sentence, or composing an image a certain way to me is intriguing. If someone makes an arbitrary choice with something like generative fill, it makes me feel like their whole piece is arbitrary. Then why do I care?
cautiouscat··on 2027 memory capacity is reportedly sold out
Someone less cynical might recognize that people use RAM in a home machine for more than just gaming. Also hobbies are just as important to the human condition as technical advancement.
cautiouscat··on Apple Introduces Leasing Program for iPhones and Other Devices
Good catch. Edited the original post.
cautiouscat··on Apple introduces leasing program for iPhones and other devices
For what it’s worth, it’s lease to own:

> At the end of your initial lease term, you can do one of the following:

> Upgrade and return your current device. Footnote ◊

> Leave the program and return your current device. Footnote ◊

> Buy the device outright with a one-time payment from your Klarna account.

https://www.apple.com/shop/apple-upgrade

cautiouscat··on Oracle bans AI-generated code from OpenJDK
Ghostty has what I’d consider to be a reasonable policy. You submit what you want to change and how, explain it in your own words. A trusted member can vouch for you. You can then make a PR, but you need to explain the solution and how it works in your own words.

I’m sure someone could still just prompt their way through but it’s a decent soft gate IMO.

cautiouscat··on Oracle bans AI-generated code from OpenJDK
I’m just going off the reasons they gave. Which highlight both copyright and quality. Both of those make sense to me.
cautiouscat··on Oracle bans AI-generated code from OpenJDK
Yeah, they kind of hit on this in their main post:

> If I use a generative AI tool to create 100 lines of code, and then edit ten of those lines myself, may I contribute the result?

> No. Your contribution would still include, in part, AI-generated code.

cautiouscat··on Oracle bans AI-generated code from OpenJDK
I kind of get their overall point, even if it is ironic that Oracle is all in on AI. They don’t want a ton of contributions to review that weren’t made with care, adding burden to, as they put it: “already limited time of human reviewers”.

Especially for a project that runs to many major businesses, this could pose a massive risk.

cautiouscat··on Kitesurf: Agent-first browser that runs in V8 isolates
Can someone give me examples of where you use agents in your browser? I’ve heard executive leaders tout that “people use agents to buy things for them” but I haven’t actually seen that.
cautiouscat··on Taste Is All That's Left
> But for many big complex projects, you can't land code without reviews.

Why do you think orgs are pushing less reviews? Token-maxxing increased PRs but stupid meat brains are a constraint. So of course, remove that constraint and you’ll have your features faster!

cautiouscat··on OpenAI's ring-shaped smart speaker will reportedly cost between $300 and $400
> Sources told Gurman that the product would have a ring-shaped design about the size of a hockey puck. The form factor is meant to be battery-powered and portable, so a user could easily carry it around with them.

If there is any company I would hope people weren’t carrying a microphone around for, it would be OpenAI.

cautiouscat··on GitHub Actions and Pages are experiencing degraded availability
I’ve been self-hosting lore and gitea the past 6 months or so and it’s been a breeze. For anything I really care to share I throw up on Tangled.
cautiouscat··on Join Me in Jamverse
Off topic but it’s getting crazy how confidently you can point at a websites design and go “An LLM designed this.”

Jamverse kind of just reminds me of a less guided SCP wiki? I’m not sure I fully get it though. Seems interesting though, I’ll have to poke through and read.

cautiouscat··on Why Do Fewer Renters Expect to Move?
It’s getting prohibitively expensive. Before brokers fees were banned in Boston, a $2,000/mo apartment could have cost you $8000 just to move in. That’s for first, last, security and brokers fee. That’s a worst case scenario but even just first and last months rent is $4000. It’s getting outrageous.
cautiouscat··on Iowa et al asks OpenAI to keep their bots sandboxed
I’m not a lawyer. However it probably comes down to jurisdiction.
cautiouscat··on There Will Come Soft Rains (1950) [pdf]
Best we can do is Wifi to set your timer.
cautiouscat··on Agent skills that bring team coding standards to Claude Code and Codex
IMO, these agentic guard rails aren't the answer. It seems like we're seeing that the more you stuff context, the more the agents forget and don't follow the guidelines.[1]

Things like ArchUnit, static analyzers, and other deterministic tools can help with lower level things like architecture. For higher up stuff, I am increasingly feeling like agents don't guarantee anything and in many cases its just the opposite. This is where a thoughtful engineer and reviewer can keep things in check.

It's possible I'm off base here, but I can't make heads or tails of the LLM written readme.

1: https://arxiv.org/html/2510.05381v1

cautiouscat··on Ray Bradbury's "There Will Come Soft Rains" is set today (2026-08-04)
Thanks for sharing. Soviet era animation was creepy in its own right. This adaptation doubly so.
cautiouscat··on There Will Come Soft Rains (1950) [pdf]
We're closer to the stove, kind of. At least with things like Tovala. I've never actually met someone with one though.
cautiouscat··on Xbox goes down. You can't play games you own on disc
Not saying this is a great solution either, though it beats the trackpad + on screen keyboard. I like to VNC into the deck and do these things.
cautiouscat··on Xbox goes down. You can't play games you own on disc
That’s fair about music. I didn’t even know about Qobuz. I do wonder how long big labels will permit that, but I’m glad it’s here now.

E-book DRM is crazy, I agree. I should have included that.

← PreviousPage 3 of 6Next →