Hacker News: stevedonovan

New comment by stevedonovan in "A proposal to classify happiness as a psychiatric disorder"

stevedonovan — Tue, 17 Mar 2026 15:29:31 +0000

Hypomania is very irritating, and can actually mess up a person's life. It's a neurotic defense mechanism that's opposite to depression

New comment by stevedonovan in "Is Show HN dead? No, but it's drowning"

stevedonovan — Tue, 17 Feb 2026 18:04:00 +0000

You could write in the language you are most eloquent in and prompt a bot to do a faithful translation.

Post both versions

New comment by stevedonovan in "Where did all the starships go?"

stevedonovan — Sun, 08 Feb 2026 07:33:15 +0000

Except for the power-to-weight problem. Would need very big wings!

New comment by stevedonovan in "Nanolang: A tiny experimental language designed to be targeted by coding LLMs"

stevedonovan — Tue, 20 Jan 2026 06:43:15 +0000

Codex generates solid Rust in my experience. Just needs a little style guidance

New comment by stevedonovan in "The unbearable frustration of figuring out APIs"

stevedonovan — Wed, 14 Jan 2026 17:40:55 +0000

It was my first taste of Swift, and has destroyed any lingering curiosity I had about it.

New comment by stevedonovan in "Logos Language Guide: Compile English to Rust"

stevedonovan — Mon, 05 Jan 2026 07:31:40 +0000

Yep, there's always syntax, whether it's 'friendly' or not.

And it still isn't natural language, where you can paraphrase, use synonyms etc. Good job for an LLM

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

stevedonovan — Sun, 04 Jan 2026 09:54:53 +0000

But are they writing? In that specific sense of high prestige communication? Sounds like stolen aura.

Now, code by Gen AI is straightforward in comparison. Coding is not writing poetry, even if the lines also don't reach the right margin

New comment by stevedonovan in "Gild Just One Lily"

stevedonovan — Sat, 13 Dec 2025 08:42:14 +0000

"This post could have been a tweet", and so on.

It's a lovely metaphor for the soulful business of doing something really well, even if there is no 'market' for that kind of quality

New comment by stevedonovan in "OpenAI declares 'code red' as Google catches up in AI race"

stevedonovan — Wed, 03 Dec 2025 06:44:55 +0000

I've been getting great results from Codex. Can be a bit slow, but gets there. Writes good Rust, powers through integration test generation.

So (again) we are just sharing anecdata

New comment by stevedonovan in "Replacement.ai"

stevedonovan — Sun, 19 Oct 2025 15:58:42 +0000

Heh,I read SF as San Francisco; point remains true. Except the Valley wants to force a future, not describe it

New comment by stevedonovan in "America's top companies keep talking about AI – but can't explain the upsides"

stevedonovan — Wed, 24 Sep 2025 06:34:28 +0000

It's not inconsistent to say there's a financial bubble and also genuinely think it's a new era for software development.

There aren't enough programmers to justify the valuations and capex

New comment by stevedonovan in "RustGPT: A pure-Rust transformer LLM built from scratch"

stevedonovan — Mon, 15 Sep 2025 10:27:38 +0000

These are a few well-chosen dependencies for a serious project.

Rust projects can really go bananas on dependencies, partly because it's so easy to include them

New comment by stevedonovan in "AI is killing the web – can anything save it?"

stevedonovan — Mon, 21 Jul 2025 07:06:52 +0000

So the cognitive reality of being a billionaire is now available to everyone?

New comment by stevedonovan in "The force-feeding of AI features on an unwilling public"

stevedonovan — Sun, 06 Jul 2025 09:03:18 +0000

But this is one thing that Gen AI is genuinely good at, constructing computer programs under close human supervision. It's also the most profitable (but not enough to justify valuations) Also, it may be a big thing here but its pretty niche in the larger scheme of things

The article is about it encroaching in the domain of human communications. Mass adoption is the only way to justify the incredible financial promises.

New comment by stevedonovan in "Astronomers discover 3I/ATLAS – Third interstellar object to visit Solar System"

stevedonovan — Thu, 03 Jul 2025 14:22:41 +0000

So much for the old thermonuclear ramjet idea....

New comment by stevedonovan in "Show HN: AGL a toy language that compiles to Go"

stevedonovan — Sun, 29 Jun 2025 06:57:09 +0000

This is how Option works with ? in Rust. But short-circuiting in an expression does make sense

New comment by stevedonovan in "Rust compiler performance"

stevedonovan — Thu, 12 Jun 2025 16:04:50 +0000

Is this not more a Cargo thing? Cargo is obsessed with correct builds and eventually the file system fills up with old artifacts.

(I know, I have to declare Cargo bankruptcy every few weeks and do a full clean & rebuild)

New comment by stevedonovan in "LLMs get lost in multi-turn conversation"

stevedonovan — Thu, 15 May 2025 06:52:07 +0000

Ah, Elon paying attention to hid companies again!

Context poisoning is not a uniquely LLM problem

New comment by stevedonovan in "Show HN: I built an AI that turns GitHub codebases into easy tutorials"

stevedonovan — Sun, 20 Apr 2025 14:07:23 +0000

I agree, it's hopelessly over-cheerful and tries to be cute. The pizza metaphor fell flat for me as well

New comment by stevedonovan in "I don't want to spend my one precious life dealing with Google's AI search"

stevedonovan — Thu, 16 May 2024 17:52:38 +0000

Ah, Edge/Bing went through this phase recently. A split personality, where sensible stuff appeared on the left, and Copilot laboriously typing on the right. I disabled it, really did not add anything to the experience.