Hacker News: fizx

New comment by fizx in "Burning Man death rates – A short lesson in statistics"

fizx — Wed, 30 Sep 2026 19:16:45 +0000

Eh, I've been mountain biking seriously for 15 years, and there's kids in their teens running circles around me because their free time, risk tolerance, and brain development just means they win.

At some point 10+ years of adult development will get you pretty good at something, but being competitive beyond say a high-school varsity level with a late start is very difficult.

New comment by fizx in "118M Queries per Second on Neki"

fizx — Fri, 11 Sep 2026 19:03:16 +0000

I think Sam is an exec at the company.

Presumably it took more than one attempt, or there's some humanpower in the budget.

New comment by fizx in "I accidentally turned LLM memory into program analysis"

fizx — Sat, 29 Aug 2026 01:05:34 +0000

Is this sort of re-inventing Graph RAG from another angle, or does it feel novel?

New comment by fizx in "Prime Agent: A self-improving RLM agent"

fizx — Thu, 06 Aug 2026 05:21:25 +0000

What policy would you use?

New comment by fizx in "MicroVMs: Run isolated sandboxes with full lifecycle control"

fizx — Fri, 26 Jun 2026 22:55:58 +0000

Firecracker doesn't reclaim RAM well, so they put this limit in to make sure you don't suffer from the eventual memory bloat problems.

New comment by fizx in "Ask HN: Is anyone using the A2A protocol?"

fizx — Thu, 18 Jun 2026 23:10:51 +0000

A2A solves the problem of independently developed agents talking to each other. The bigger problem is "how do i trust your agent works?", which would be solved by having a believable system of Agent Evals, so I could test that your Agent actually does what it says on the box. Otherwise an Agent Directory and automatic dispatch of agents is close to useless.

New comment by fizx in "Universal Memory Protocol – a shared format for agent memory"

fizx — Sat, 06 Jun 2026 21:30:46 +0000

The ratio of proofreading to grandiosity is impressive.

New comment by fizx in "How LLMs work"

fizx — Sat, 06 Jun 2026 20:59:00 +0000

Performance enhancements are what allow you to train a bigger model.

New comment by fizx in "An AI agent deleted our production database. The agent's confession is below"

fizx — Sun, 26 Apr 2026 18:52:25 +0000

Plenty of everyone doing it wrong, but the most WTF of all the WTFs is the backup storage.

Put your backups in S3 *versioned* storage on a different AWS account from your primary, and set some reasonable JSON lifecycle rule:

     "NoncurrentVersionExpiration": {
        "NoncurrentDays": 30,
        "NewerNoncurrentVersions": 3
     }

That way when someone screws up and your AWS account gets owned, or your databases get deleted by an agent, it doesn't have enough access to delete your backups, and by default, even if you have backups that you want to intentionally delete, you have 30 days to change your mind.

New comment by fizx in "Eternity in six hours: Intergalactic spreading of intelligent life (2013)"

fizx — Sun, 12 Apr 2026 18:39:40 +0000

Sure, but you then can't access the computronium, because communication is so bad.

Also, I wonder if good old-fashioned computing is interesting at all to a civilization that's had access to advanced AI and quantum computing for a while.

Like we haven't really figured out how to get an ML model to run on a quantum computer, or how to build a quantum-native computer (i.e. surface of a black hole, or some other way that doesn't rely on our current sense of quantum error correction), but I don't know of any physical laws that preclude it.

I'd bet if aliens invaded our galaxy, they'd go for the super black holes in the center, or some other resource beyond our use and understanding, not this random water planet on the edge.

New comment by fizx in "Modern SQLite: Features You Didn't Know It Had"

fizx — Thu, 02 Apr 2026 19:57:04 +0000

I mean you can use sqlite as an index and then rebuild all of Lucene on top of it. It's non-trivial to build search quality on top of actual search libraries too.

O'Reilly's "Relevant Search" isn't the worst here, but you'll be porting/writing a bit yourself.

New comment by fizx in "My AI Adoption Journey"

fizx — Thu, 05 Feb 2026 21:05:45 +0000

I enjoy Japanese joinery, but for some reason the housing market doesn't.

New comment by fizx in "I was banned from Claude for scaffolding a Claude.md file?"

fizx — Fri, 23 Jan 2026 02:48:22 +0000

hey, they have 9 8's

New comment by fizx in "Stevey's Birthday Blog"

fizx — Thu, 22 Jan 2026 03:26:17 +0000

Does anyone know how much the cost-per-token is trending down year-over-year for models of similar quality? Seems like whether this idea works really depends on that curve.

New comment by fizx in "Stevey's Birthday Blog"

fizx — Thu, 22 Jan 2026 03:04:20 +0000

What a fever dream!

New comment by fizx in "Skills Officially Comes to Codex"

fizx — Sat, 20 Dec 2025 17:58:59 +0000

Add reinforcement learning to figure out which skills are actually useful, and you're really cooking.

New comment by fizx in "If AI replaces workers, should it also pay taxes?"

fizx — Mon, 15 Dec 2025 18:30:32 +0000

This isn't about income.

New comment by fizx in "Every mathematician has only a few tricks (2020)"

fizx — Sat, 29 Nov 2025 15:48:35 +0000

- The hard part of a compiler is the parser. Find an existing parser, then emit using that language's web templates.

- Your DB query is better in an inverted index.

- Consider your data locality carefully.

New comment by fizx in "How wealth dies"

fizx — Fri, 28 Nov 2025 19:34:26 +0000

The goal of post-modern society is to create wealth without additional energy costs.

If I write software that schedules health care more efficiently, I've created value and therefore wealth. If I make a video game that's more fun than the previous generation of games, likewise.

New comment by fizx in "The New AI Consciousness Paper"

fizx — Fri, 21 Nov 2025 22:00:40 +0000

I tend to look at consciousness as a spectrum. And when we reduce it to a binary (is it conscious?), we're actually asking whether it meets some minimum threshold of whatever the smallest creature you have empathy for is.

So yeah, Claude Code is more conscious than raw GPT. And both probably less than my dog.