Hacker News: snoman

New comment by snoman in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

snoman — Mon, 15 Jun 2026 21:43:14 +0000

If the government is going to gate access to frontier models from here on out, even if new releases are a step function change… which they’re not… then it may be even more comparable to what’s available with a subscription.

New comment by snoman in "The Speed of Prototyping in the Age of AI"

snoman — Sun, 31 May 2026 18:33:34 +0000

Considering that engineer never reliably estimated anything beyond a few days remotely accurately before… but now they can…

New comment by snoman in "Microsoft starts canceling Claude Code licenses"

snoman — Sat, 23 May 2026 15:19:21 +0000

As one that does, it’s a difficult discussion to have with the executives. My peers look like their teams are producing more than my teams are and any argument along the lines of “but their code sucks” isn’t going to hold water. The executives care but until there’s actual impact or poor quality, it won’t matter, and it’s a lagging metric. Many still don’t care about technical debt and that’s been well understood in industry for a while.

It’ll take production incidents, impacted customers, and brand damage to make the executives start to prioritize quality over quantity again.

New comment by snoman in "A recent experience with ChatGPT 5.5 Pro"

snoman — Sun, 10 May 2026 04:12:46 +0000

1. And some that are equally skilled that don’t. It matters, internally, to them but it needn’t matter to anyone else.

New comment by snoman in "Measuring Claude 4.7's tokenizer costs"

snoman — Sun, 19 Apr 2026 15:23:03 +0000

I wonder if there are different use cases. You sound like you’re using an LLM in a similar way to me. I think about the problem and solution, describe what I need implemented, provide references in the context (“the endpoint should be structured like this one…”) and then evaluate the output.

It sounds like other folks are more throwing an LLM at the problem to see what it comes up with. More akin to how I delegate a problem to one of my human engineers/architects. I understand, conceptually, why they might be doing that but I know that I stopped trying that because it didn’t produce quality. I wonder if the newer models are better at handling that ambiguity better.

New comment by snoman in "Measuring Claude 4.7's tokenizer costs"

snoman — Sun, 19 Apr 2026 00:59:10 +0000

I agree with you, but my gut tells me that a lot of people don’t know what a good outcome should/could look like and are accepting whatever it delivers.

New comment by snoman in "State of Homelab 2026"

snoman — Mon, 13 Apr 2026 05:34:06 +0000

I just sync down everything from my wife/kids’ Google Drive/Dropbox/whatever nightly to my NAS. Usability of a cloud solution, but with on-prem backup.

New comment by snoman in "Sam Altman's response to Molotov cocktail incident"

snoman — Sat, 11 Apr 2026 02:33:59 +0000

That’s so shockingly ignorant/reductive that you shouldn’t be surprised when people start ignoring you in technical conversations.

New comment by snoman in "Sam Altman's response to Molotov cocktail incident"

snoman — Sat, 11 Apr 2026 02:23:20 +0000

That sentiment always comes from people who are better at fighting with communication.

New comment by snoman in "Anthropic takes legal action against OpenCode"

snoman — Thu, 19 Mar 2026 20:23:58 +0000

My understanding is that, if you directly assist someone violate a ToS, you can be held liable.

Bad analogy but the getaway driver doesn’t need to enter the bank to be guilty in the robbery.

New comment by snoman in "Anthropic takes legal action against OpenCode"

snoman — Thu, 19 Mar 2026 20:21:21 +0000

Yes.

New comment by snoman in "The Appalling Stupidity of Spotify's AI DJ"

snoman — Sun, 15 Mar 2026 16:26:48 +0000

That explains why it is always/only wanting to play stuff that I listened to recently, or in 2023.

New comment by snoman in "Agents that run while I sleep"

snoman — Wed, 11 Mar 2026 15:29:32 +0000

> What is sure is that a lot of capacity is been built and that capacity won't disappear.

They really are subsidizing what will be an incredibly healthy used server equipment market in a year or two. Can’t wait. My homelab is going to be due for an upgrade.

New comment by snoman in "The Singularity will occur on a Tuesday"

snoman — Tue, 10 Feb 2026 21:54:00 +0000

It only has to be right once. Humanity won’t end until it does.

New comment by snoman in "Claude Cowork exfiltrates files"

snoman — Thu, 15 Jan 2026 18:46:21 +0000

But nobody trusts AI. Whenever I leave my circle of engineering people and am along the general public, I hear nothing but contempt for it.

New comment by snoman in "Windows 8 Desktop Environment for Linux"

snoman — Mon, 12 Jan 2026 14:54:58 +0000

I honestly think that the windows phone development experience is where Microsoft majorly shit the bed. The sheer volume of breaking changes (and the severity of those breaks) meant rewriting a non-trivial amount of your app from version to version. I know multiple developers that just dropped support for windows phone as a result.

New comment by snoman in "All AI Videos Are Harmful (2025)"

snoman — Tue, 06 Jan 2026 15:53:27 +0000

It’s almost like people that use the tools to the best of their ability will produce higher quality outputs. This is a new tool like we’ve never seen before with a low skill floor to use it. We don’t know what the skill ceiling is yet.

New comment by snoman in "The suck is why we're here"

snoman — Sun, 04 Jan 2026 07:46:17 +0000

Maybe you’re the person I’ve been looking for but I’ve yet to find someone that actually maintains a zettelkasten that isn’t a researcher/author and doesn’t come to the conclusion that it’s a huge waste of time and energy.

New comment by snoman in "You can't design software you don't work on"

snoman — Mon, 29 Dec 2025 18:28:32 +0000

My reading of it also violates the Boy Scout Rule. That is to say: if improving some portion of the codebase would make it better, but inconsistent, you should avoid the improvement; which is something that I would disagree with.

I think adherence to “consistency is more important than ‘good design’” naturally leads to boiling the ocean refactoring and/or rewrites, which are far riskier endeavors with lower success rates than iterative refactoring of a working system over time.

New comment by snoman in "A guide to local coding models"

snoman — Sun, 21 Dec 2025 23:24:00 +0000

Less of a concern these days with hardware like a Mac Studio or Nvidia dgx which are accessible and aren’t noisy at all.