Hacker News: macrolime

New comment by macrolime in "New research suggests people can communicate and practice skills while dreaming"

macrolime — Fri, 01 May 2026 21:58:09 +0000

Most consistent way of achieving it I've managed is use a watch with an alarm that vibrates and is trivial to turn off or turns off by itself, then set it to go off after sleeping 5-6 hours. When waking up, don't move and focus on the black behind the eyes, then after a few seconds it may turn into a dream and you go straight from waking into a lucid dream.

New comment by macrolime in "Google is 'gradually rolling out' option to change your gmail.com address"

macrolime — Thu, 25 Dec 2025 23:15:21 +0000

I had something kinda similar happen to my hotmail account. While I didn't lose access to it, I lost more than a decade of correspondence dating back to my teenage years. The reason was that Microsoft at some point required you to "login" once every 30 days. It seems they only counted logins through their web interface or something like that, so even though I was receiving emails daily, I didn't trigger a "login" in their system. They then deleted all my emails, but I could still login.

New comment by macrolime in "Measuring AI Ability to Complete Long Tasks"

macrolime — Sun, 21 Dec 2025 15:53:09 +0000

I find that surprising. GPT 5.2 is the model I've had working the longest. It frequently works more than 4 hours nonstop, while earlier models would stop to ask if they should continue every 10 minutes. 5.1 and earlier ignores it if I ask it to continue until a task is done, but 5.2 will usually finish it.

New comment by macrolime in "Is it a bubble?"

macrolime — Wed, 10 Dec 2025 23:14:30 +0000

"Can you replay all of your prompts exactly the way you wrote them and get the same behaviour out of the LLM generated code? In that case, the situation might be similar. If that's not the case, probably not." Yes and no. It's possible in theory, but in practice it requires control over the seed, which you typically don't have in the AI coding tools. At least if you're using local models, you can control the seed and have it be deterministic.

That said, you don't necessarily always have 100% deterministic build when compiling code either.

New comment by macrolime in "Is it a bubble?"

macrolime — Wed, 10 Dec 2025 21:43:41 +0000

So you're saying machine code is public domain if it's compiled from C? If not, why would AI generated code be any different?

New comment by macrolime in "Sugars, Gum, Stardust Found in NASA's Asteroid Bennu Samples"

macrolime — Fri, 05 Dec 2025 14:26:31 +0000

So it's made of extraterrestrial bubblegum, got it.

New comment by macrolime in "Gemini 3 Pro Model Card [pdf]"

macrolime — Tue, 18 Nov 2025 14:09:28 +0000

Pretty sure it will beat Sonnet by a wide margin in actual real-world usage.

New comment by macrolime in "Spec-Driven Development: The Waterfall Strikes Back"

macrolime — Sat, 15 Nov 2025 12:39:56 +0000

I've found that SDD is actually what you need to be able to work with code bases when they go above around 100 000 lines of code. It's what unlocked getting LLMs to work well with large codebases for me.

New comment by macrolime in "Using AI to negotiate a $195k hospital bill down to $33k"

macrolime — Tue, 28 Oct 2025 18:56:27 +0000

In the EU you can also generally look up the cost, even in cases where the patient doesn't pay, there is a bill and fixed costs. The costs are what the government pays or what a foreigner with no medical coverage and insurance would pay. It's also generally a tiny fraction of the cost in the US.

New comment by macrolime in "OpenAI researcher announced GPT-5 math breakthrough that never happened"

macrolime — Sun, 19 Oct 2025 15:05:27 +0000

What is "it". Gpt-5 auto? Gpt-5 pro? Deep research? These have wildly different hallucination rates.

New comment by macrolime in "Are touchscreens in cars dangerous?"

macrolime — Sat, 20 Sep 2025 16:57:58 +0000

Voice control is much much much worse than touch screens. You have to try 10-20 times to spell out a command before it maybe does want you want, and that is if you're incredibly lucky

New comment by macrolime in "How to use Claude Code subagents to parallelize development"

macrolime — Sat, 13 Sep 2025 09:42:57 +0000

This is my experience too.

Make agents for tasks, not roles.

I've seen this for coding agents using spec-driven development for example. You can try to divide agents into lots of different roles that roughly correspond to human job positions, like for example BMad does, or you can simply make each agent do a task and have a template for the task. Like make an implementation plan using a template for an implementation plan or make a task list, using a template for a task list. In general, I've gotten much better results with agents that has a specific task to do than trying to give a role, with a job-like description.

For code review, I don't use a code reviewer agent, instead I've defined a dozen code reviewing tasks, that each runs as separate agents (though I group some related tasks together).

New comment by macrolime in "Scientists discover surprising language 'shortcuts' in birdsong – like humans"

macrolime — Mon, 18 Aug 2025 12:14:43 +0000

YouTube videos of birds?

New comment by macrolime in "Show HN: Omnara – Run Claude Code from anywhere"

macrolime — Wed, 13 Aug 2025 06:15:25 +0000

I mean copying from the iOS app.

New comment by macrolime in "Show HN: Omnara – Run Claude Code from anywhere"

macrolime — Tue, 12 Aug 2025 21:07:48 +0000

Seems copying text in the app doesn't work? In that case it is useless. A quick way to copy an entire chat and a selection messages is a requirement for me to be able to use it.

New comment by macrolime in "Cognition (Devin AI) to Acquire Windsurf"

macrolime — Tue, 15 Jul 2025 08:06:22 +0000

Thing is that it took 10-15 years for the stocks of these companies to reach the same marketcap again.

New comment by macrolime in "Cognition (Devin AI) to Acquire Windsurf"

macrolime — Tue, 15 Jul 2025 08:04:41 +0000

If it's so hard, then why are there multiple open source projects that are just as good?

New comment by macrolime in "Cognition (Devin AI) to Acquire Windsurf"

macrolime — Tue, 15 Jul 2025 08:00:57 +0000

You can use Claude Code as a provider if you want it subscription based

https://docs.cline.bot/provider-config/claude-code

New comment by macrolime in "Switching to Claude Code and VSCode Inside Docker"

macrolime — Sun, 13 Jul 2025 09:00:17 +0000

I ssh into my server, then use the devcontainer cli tool to open a shell in the dev container. Found that easier than installing ssh in every container, especially when there's lots of them. I made a simple command line tool for helping the process, so I don't have to type out any long commands. If I run it it will list the running dev containers and I give them each a number to I don't have to use the full ID.

New comment by macrolime in "OpenAI’s Windsurf deal is off, and Windsurf’s CEO is going to Google"

macrolime — Sat, 12 Jul 2025 17:29:11 +0000

Yeah, it's like an idiot savant intern who has memorized all the API docs in the world, but still somehow struggles to work independently.