Hacker News: newtwilly

New comment by newtwilly in "How we hacked McKinsey's AI platform"

newtwilly — Thu, 12 Mar 2026 15:42:14 +0000

The article does say

> No human in the loop

If true, it's quite irresponsible. They are admitting to allowing a agent to autonomously execute code on the network. Autonomously perform hacking activities.

New comment by newtwilly in "GPT-5.4"

newtwilly — Thu, 05 Mar 2026 23:06:41 +0000

For directed coding (implementing an already specified plan) or asking questions about a codebase I use 5.3 codex with medium reasoning effort. It is relatively quick feeling.

I like Sonnet 4.6 a lot too at medium reasoning effort, but at least in Cursor it is sometimes quite slow because it will start "thinking" for a long time.

New comment by newtwilly in "GPT-5.3-Codex"

newtwilly — Fri, 06 Feb 2026 06:37:34 +0000

I've been using 5.1-codex-max with low reasoning (in Cursor fwiw) recently and it feels like a nice speed while still being effective. Might be worth a shot.

New comment by newtwilly in "We stopped roadmap work for a week and fixed bugs"

newtwilly — Mon, 24 Nov 2025 16:04:03 +0000

Wow, that's pretty epic and satisfying

New comment by newtwilly in "Show HN: I built a synth for my daughter"

newtwilly — Mon, 17 Nov 2025 21:06:27 +0000

Beautifully done!

New comment by newtwilly in "AWS multiple services outage in us-east-1"

newtwilly — Mon, 20 Oct 2025 16:00:27 +0000

We spend ~$20,000 per month in AWS for the product I work on. In the average day we do not launch an EC2 instance. We do not do any dynamic scaling. However, there are many scenarios (especially during outages and such) that it would be critical for us to be able to launch a new instance (and or stop/start an existing instance.)

New comment by newtwilly in "Linux phones are more important now than ever"

newtwilly — Tue, 16 Sep 2025 14:38:34 +0000

FYI, you can get a pixel 8a for $200 or less if you don't care about condition. Support end date in 2031.

New comment by newtwilly in "Claude Code is all you need"

newtwilly — Mon, 11 Aug 2025 17:36:45 +0000

I run with the dangerous option on my work computer. At first I was thinking I would be good if I just regularly kept full disk backups. But my company at least pays lip service to the fact that we want to protect our intellectual property. Plus I think it might be irresponsible to allow an AI model full internet access unsupervised.

So now I use a docker compose setup where I install Claude and run it in a container. I map source code volumes into the container. It uses a different container with dnsmasq with an allowlist.

I initially wanted to do HTTP proxying instead of DNS filtering since it would be more secure, but it was quite hard to set it up satisfactorily.

Running CLI programs with the dangerous full permissions is a lot more comfortable and fast, so I'm quite satisfied.

New comment by newtwilly in "Claude Code IDE integration for Emacs"

newtwilly — Thu, 07 Aug 2025 00:48:02 +0000

No the comment meant that aider and Claude code are CLI programs, so if you can run a terminal in your niche editor, then you are good to go

New comment by newtwilly in "MCP: An (Accidentally) Universal Plugin System"

newtwilly — Sat, 28 Jun 2025 17:37:58 +0000

It's pretty easy if you just use the MCP Python library. You just put an annotation on a function and there's your tool. I was able to do it and it works great without me knowing anything about MCP. Maybe it's a different story if you actually need to know the protocol and implement more for yourself

New comment by newtwilly in "When the Dotcom Bubble Burst"

newtwilly — Mon, 17 Mar 2025 20:43:33 +0000

Firefox has a "reader view" which works well for things like that.

New comment by newtwilly in "My LLM codegen workflow"

newtwilly — Fri, 21 Feb 2025 14:30:11 +0000

Hi, I appreciate you sharing. I've been starting to use this advice with a different tool. Just FYI, this sentence kind of came out of nowhere and it wasn't clear what you meant: > The foundational LLM models right now are what I'd estimate to be at circa 45% accuracy and require frequent steering

Do your rules count as frequent steering and lead to increased 'accuracy', or is that the 'accuracy' you're seeing with your current workflow, rules and all?

New comment by newtwilly in "Marijuana addiction: those struggling often face skepticism"

newtwilly — Tue, 01 Aug 2023 02:59:30 +0000

I've also heard that THCA breaks down into THC over time, so maybe there's a chance that when it's shipped it's compliant with the Hemp bill, but some time later if the cops seize and test it, then you actually now have illegal cannabis in your possession. Not sure to what extent that is true, but seems reasonable.

New comment by newtwilly in "DevOps Is Bullshit (2022)"

newtwilly — Sat, 17 Jun 2023 03:44:26 +0000

Doesn't help that the post didn't define their definition of devops, and then they went on to use it in a variety of contexts, seemingly contradictory. As someone who is a software engineer, but doesn't necessarily keep up on the latest hype, this post made me head spin when I tried to read it casually.

New comment by newtwilly in "916 Days of Emacs"

newtwilly — Thu, 13 Apr 2023 19:05:39 +0000

I recently had GPT 3.5 write me a function for translating the number under point to an ISO timestamp. It handled whether the epoch number was milliseconds or seconds since epoch. I kinda had to iterate on it and ask it to do some things different, but it never wrote invalid code.

New comment by newtwilly in "AI-enhanced development makes me more ambitious with my projects"

newtwilly — Fri, 31 Mar 2023 13:32:39 +0000

What interface are you using? I've so far only used ChatGPT through the web interface. (I pay for plus). I just ask it for things that are standalone snippet-like things. Perfect functions on the standard library, or an emacs lisp snippet for converting a unix epoch to an ISO timestamp. I'm not sure I could allow it to read my company's code, but is that what you're doing when you're using as part of a large project like that?

New comment by newtwilly in "An X11 apologist tries Wayland"

newtwilly — Mon, 19 Sep 2022 03:15:15 +0000

No it's not possible in a newer LTS (> 20.04, don't have laptop on hand) Ubuntu KDE. There's no scroll speed configuration, as sibling comments discuss. Switching driver to libinput or whatever made it configurable, but other bugs popped up, and suddenly every accidental palm touch sent my cursor clicking somewhere.

New comment by newtwilly in "Shamelessness as a strategy (2019)"

newtwilly — Tue, 26 Jul 2022 03:28:54 +0000

Yes, I also really enjoyed this piece. It has a nice and loose style... just throwing ideas out without trying to "prove" them, but nonetheless presenting interesting ideas and likely some useful mental models.

New comment by newtwilly in "Ruby Shield: Shopify donates $1M to stewards of rubygems, bundler"

newtwilly — Thu, 07 Jul 2022 02:43:04 +0000

Donating money to projects that you use heavily doesn't sound like any kind of traditional paid model to me.

New comment by newtwilly in "Blogging with Org-mode for lazy people"

newtwilly — Mon, 06 Jun 2022 02:16:21 +0000

The author's linked page has a horizontal scroll, which seems non-ideal to me https://karl-voit.at/tags/lazyblorg/